m=5 n=5 k=5 ldc=8 (column-major) size=1491308 batch=997 memory=1024 MB

LAPACK/BLAS...
	performance: 4.1 GFLOPS/s
	bandwidth: 6.1 GB/s
	duration: 0.1 s
Inlined...
	performance: 29.9 GFLOPS/s
	bandwidth: 44.6 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 30.8 GFLOPS/s
	bandwidth: 46.0 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 79.1 GFLOPS/s
	bandwidth: 118.0 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=5 n=5 k=13 ldc=8 (column-major) size=789516 batch=725 memory=1024 MB

LAPACK/BLAS...
	performance: 5.1 GFLOPS/s
	bandwidth: 7.7 GB/s
	duration: 0.1 s
Inlined...
	performance: 40.3 GFLOPS/s
	bandwidth: 60.2 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 63.7 GFLOPS/s
	bandwidth: 94.9 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 92.8 GFLOPS/s
	bandwidth: 138.4 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=5 n=5 k=24 ldc=8 (column-major) size=479349 batch=565 memory=1024 MB

LAPACK/BLAS...
	performance: 5.0 GFLOPS/s
	bandwidth: 7.5 GB/s
	duration: 0.1 s
Inlined...
	performance: 39.5 GFLOPS/s
	bandwidth: 59.0 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 77.3 GFLOPS/s
	bandwidth: 115.2 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 91.0 GFLOPS/s
	bandwidth: 135.7 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=5 n=5 k=26 ldc=8 (column-major) size=447392 batch=546 memory=1024 MB

LAPACK/BLAS...
	performance: 5.1 GFLOPS/s
	bandwidth: 7.7 GB/s
	duration: 0.1 s
Inlined...
	performance: 41.4 GFLOPS/s
	bandwidth: 61.8 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 73.2 GFLOPS/s
	bandwidth: 109.2 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 88.0 GFLOPS/s
	bandwidth: 131.2 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=5 n=5 k=32 ldc=8 (column-major) size=372827 batch=499 memory=1024 MB

LAPACK/BLAS...
	performance: 5.2 GFLOPS/s
	bandwidth: 7.8 GB/s
	duration: 0.1 s
Inlined...
	performance: 40.5 GFLOPS/s
	bandwidth: 60.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 75.7 GFLOPS/s
	bandwidth: 112.9 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 85.8 GFLOPS/s
	bandwidth: 128.0 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=5 n=13 k=5 ldc=8 (column-major) size=691843 batch=679 memory=1024 MB

LAPACK/BLAS...
	performance: 5.5 GFLOPS/s
	bandwidth: 5.7 GB/s
	duration: 0.1 s
Inlined...
	performance: 31.7 GFLOPS/s
	bandwidth: 32.8 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 74.7 GFLOPS/s
	bandwidth: 77.3 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 109.1 GFLOPS/s
	bandwidth: 113.0 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=5 n=13 k=13 ldc=8 (column-major) size=397093 batch=515 memory=1024 MB

LAPACK/BLAS...
	performance: 6.4 GFLOPS/s
	bandwidth: 6.6 GB/s
	duration: 0.1 s
Inlined...
	performance: 39.2 GFLOPS/s
	bandwidth: 40.5 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 95.9 GFLOPS/s
	bandwidth: 99.1 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 117.2 GFLOPS/s
	bandwidth: 121.1 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=5 n=13 k=24 ldc=8 (column-major) size=250406 batch=409 memory=1024 MB

LAPACK/BLAS...
	performance: 6.8 GFLOPS/s
	bandwidth: 7.0 GB/s
	duration: 0.1 s
Inlined...
	performance: 44.9 GFLOPS/s
	bandwidth: 46.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 110.9 GFLOPS/s
	bandwidth: 114.5 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 120.6 GFLOPS/s
	bandwidth: 124.5 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=5 n=13 k=26 ldc=8 (column-major) size=234646 batch=396 memory=1024 MB

LAPACK/BLAS...
	performance: 6.8 GFLOPS/s
	bandwidth: 7.0 GB/s
	duration: 0.1 s
Inlined...
	performance: 42.1 GFLOPS/s
	bandwidth: 43.5 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 106.4 GFLOPS/s
	bandwidth: 109.9 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 115.1 GFLOPS/s
	bandwidth: 118.9 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=5 n=13 k=32 ldc=8 (column-major) size=197379 batch=363 memory=1024 MB

LAPACK/BLAS...
	performance: 6.7 GFLOPS/s
	bandwidth: 6.9 GB/s
	duration: 0.1 s
Inlined...
	performance: 40.7 GFLOPS/s
	bandwidth: 42.0 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 108.4 GFLOPS/s
	bandwidth: 111.9 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 114.7 GFLOPS/s
	bandwidth: 118.5 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=5 n=24 k=5 ldc=8 (column-major) size=398272 batch=515 memory=1024 MB

LAPACK/BLAS...
	performance: 6.2 GFLOPS/s
	bandwidth: 5.6 GB/s
	duration: 0.1 s
Inlined...
	performance: 30.0 GFLOPS/s
	bandwidth: 27.1 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 95.5 GFLOPS/s
	bandwidth: 86.4 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 115.9 GFLOPS/s
	bandwidth: 104.9 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=5 n=24 k=13 ldc=8 (column-major) size=235883 batch=397 memory=1024 MB

LAPACK/BLAS...
	performance: 7.9 GFLOPS/s
	bandwidth: 7.1 GB/s
	duration: 0.1 s
Inlined...
	performance: 39.4 GFLOPS/s
	bandwidth: 35.6 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 117.2 GFLOPS/s
	bandwidth: 105.8 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 128.6 GFLOPS/s
	bandwidth: 116.1 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=5 n=24 k=24 ldc=8 (column-major) size=151146 batch=317 memory=1024 MB

LAPACK/BLAS...
	performance: 8.0 GFLOPS/s
	bandwidth: 7.2 GB/s
	duration: 0.1 s
Inlined...
	performance: 47.4 GFLOPS/s
	bandwidth: 42.7 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 132.0 GFLOPS/s
	bandwidth: 119.1 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 138.1 GFLOPS/s
	bandwidth: 124.6 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=5 n=24 k=26 ldc=8 (column-major) size=141879 batch=308 memory=1024 MB

LAPACK/BLAS...
	performance: 7.8 GFLOPS/s
	bandwidth: 7.1 GB/s
	duration: 0.1 s
Inlined...
	performance: 47.9 GFLOPS/s
	bandwidth: 43.2 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 127.8 GFLOPS/s
	bandwidth: 115.2 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 136.2 GFLOPS/s
	bandwidth: 122.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=5 n=24 k=32 ldc=8 (column-major) size=119837 batch=283 memory=1024 MB

LAPACK/BLAS...
	performance: 8.1 GFLOPS/s
	bandwidth: 7.3 GB/s
	duration: 0.1 s
Inlined...
	performance: 47.0 GFLOPS/s
	bandwidth: 42.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 121.8 GFLOPS/s
	bandwidth: 109.8 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 133.7 GFLOPS/s
	bandwidth: 120.5 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=5 n=26 k=5 ldc=8 (column-major) size=369745 batch=496 memory=1024 MB

LAPACK/BLAS...
	performance: 5.9 GFLOPS/s
	bandwidth: 5.3 GB/s
	duration: 0.1 s
Inlined...
	performance: 29.9 GFLOPS/s
	bandwidth: 26.7 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 95.9 GFLOPS/s
	bandwidth: 85.7 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 122.2 GFLOPS/s
	bandwidth: 109.2 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=5 n=26 k=13 ldc=8 (column-major) size=219668 batch=383 memory=1024 MB

LAPACK/BLAS...
	performance: 7.3 GFLOPS/s
	bandwidth: 6.5 GB/s
	duration: 0.1 s
Inlined...
	performance: 39.8 GFLOPS/s
	bandwidth: 35.5 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 114.7 GFLOPS/s
	bandwidth: 102.2 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 128.2 GFLOPS/s
	bandwidth: 114.2 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=5 n=26 k=24 ldc=8 (column-major) size=140985 batch=307 memory=1024 MB

LAPACK/BLAS...
	performance: 8.1 GFLOPS/s
	bandwidth: 7.2 GB/s
	duration: 0.1 s
Inlined...
	performance: 48.1 GFLOPS/s
	bandwidth: 42.8 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 133.2 GFLOPS/s
	bandwidth: 118.6 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 143.3 GFLOPS/s
	bandwidth: 127.5 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=5 n=26 k=26 ldc=8 (column-major) size=132364 batch=297 memory=1024 MB

LAPACK/BLAS...
	performance: 7.8 GFLOPS/s
	bandwidth: 7.0 GB/s
	duration: 0.1 s
Inlined...
	performance: 46.5 GFLOPS/s
	bandwidth: 41.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 120.8 GFLOPS/s
	bandwidth: 107.5 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 130.5 GFLOPS/s
	bandwidth: 116.2 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=5 n=26 k=32 ldc=8 (column-major) size=111848 batch=273 memory=1024 MB

LAPACK/BLAS...
	performance: 7.8 GFLOPS/s
	bandwidth: 7.0 GB/s
	duration: 0.1 s
Inlined...
	performance: 45.0 GFLOPS/s
	bandwidth: 40.1 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 123.2 GFLOPS/s
	bandwidth: 109.6 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 134.6 GFLOPS/s
	bandwidth: 119.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=5 n=32 k=5 ldc=8 (column-major) size=304348 batch=450 memory=1024 MB

LAPACK/BLAS...
	performance: 6.6 GFLOPS/s
	bandwidth: 5.8 GB/s
	duration: 0.1 s
Inlined...
	performance: 31.6 GFLOPS/s
	bandwidth: 27.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 112.2 GFLOPS/s
	bandwidth: 97.3 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 127.7 GFLOPS/s
	bandwidth: 110.7 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=5 n=32 k=13 ldc=8 (column-major) size=182113 batch=348 memory=1024 MB

LAPACK/BLAS...
	performance: 8.0 GFLOPS/s
	bandwidth: 6.9 GB/s
	duration: 0.1 s
Inlined...
	performance: 38.2 GFLOPS/s
	bandwidth: 33.0 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 111.5 GFLOPS/s
	bandwidth: 96.3 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 121.7 GFLOPS/s
	bandwidth: 105.1 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=5 n=32 k=24 ldc=8 (column-major) size=117323 batch=280 memory=1024 MB

LAPACK/BLAS...
	performance: 8.4 GFLOPS/s
	bandwidth: 7.3 GB/s
	duration: 0.1 s
Inlined...
	performance: 46.6 GFLOPS/s
	bandwidth: 40.2 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 130.1 GFLOPS/s
	bandwidth: 112.3 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 136.0 GFLOPS/s
	bandwidth: 117.4 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=5 n=32 k=26 ldc=8 (column-major) size=110195 batch=271 memory=1024 MB

LAPACK/BLAS...
	performance: 8.0 GFLOPS/s
	bandwidth: 6.9 GB/s
	duration: 0.1 s
Inlined...
	performance: 44.8 GFLOPS/s
	bandwidth: 38.6 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 122.6 GFLOPS/s
	bandwidth: 105.8 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 124.3 GFLOPS/s
	bandwidth: 107.3 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=5 n=32 k=32 ldc=8 (column-major) size=93206 batch=249 memory=1024 MB

LAPACK/BLAS...
	performance: 8.0 GFLOPS/s
	bandwidth: 6.9 GB/s
	duration: 0.1 s
Inlined...
	performance: 43.3 GFLOPS/s
	bandwidth: 37.3 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 125.2 GFLOPS/s
	bandwidth: 108.0 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 134.2 GFLOPS/s
	bandwidth: 115.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=6 n=6 k=6 ldc=8 (column-major) size=1118481 batch=864 memory=1024 MB

LAPACK/BLAS...
	performance: 5.6 GFLOPS/s
	bandwidth: 7.0 GB/s
	duration: 0.1 s
Inlined...
	performance: 35.3 GFLOPS/s
	bandwidth: 43.9 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 53.3 GFLOPS/s
	bandwidth: 66.3 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 102.8 GFLOPS/s
	bandwidth: 127.9 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=9 n=9 k=9 ldc=16 (column-major) size=438620 batch=541 memory=1024 MB

LAPACK/BLAS...
	performance: 7.9 GFLOPS/s
	bandwidth: 6.6 GB/s
	duration: 0.1 s
Inlined...
	performance: 57.9 GFLOPS/s
	bandwidth: 48.1 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 105.9 GFLOPS/s
	bandwidth: 88.0 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 138.6 GFLOPS/s
	bandwidth: 115.1 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=9 n=9 k=22 ldc=16 (column-major) size=248551 batch=407 memory=1024 MB

LAPACK/BLAS...
	performance: 9.2 GFLOPS/s
	bandwidth: 7.7 GB/s
	duration: 0.1 s
Inlined...
	performance: 70.7 GFLOPS/s
	bandwidth: 58.6 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 131.2 GFLOPS/s
	bandwidth: 108.8 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 145.8 GFLOPS/s
	bandwidth: 120.9 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=9 n=9 k=32 ldc=16 (column-major) size=186413 batch=353 memory=1024 MB

LAPACK/BLAS...
	performance: 8.6 GFLOPS/s
	bandwidth: 7.2 GB/s
	duration: 0.1 s
Inlined...
	performance: 66.0 GFLOPS/s
	bandwidth: 54.7 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 129.2 GFLOPS/s
	bandwidth: 107.1 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 137.8 GFLOPS/s
	bandwidth: 114.2 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=9 n=22 k=9 ldc=16 (column-major) size=212706 batch=377 memory=1024 MB

LAPACK/BLAS...
	performance: 0.8 GFLOPS/s
	bandwidth: 0.5 GB/s
	duration: 0.9 s
Inlined...
	performance: 58.8 GFLOPS/s
	bandwidth: 34.5 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 141.0 GFLOPS/s
	bandwidth: 82.8 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 172.6 GFLOPS/s
	bandwidth: 101.3 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=9 n=22 k=22 ldc=16 (column-major) size=129804 batch=294 memory=1024 MB

LAPACK/BLAS...
	performance: 1.3 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 80.6 GFLOPS/s
	bandwidth: 47.2 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 162.6 GFLOPS/s
	bandwidth: 95.2 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 183.3 GFLOPS/s
	bandwidth: 107.3 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=9 n=22 k=32 ldc=16 (column-major) size=99864 batch=258 memory=1024 MB

LAPACK/BLAS...
	performance: 1.4 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 72.5 GFLOPS/s
	bandwidth: 42.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 162.7 GFLOPS/s
	bandwidth: 95.2 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 171.5 GFLOPS/s
	bandwidth: 100.3 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=9 n=32 k=9 ldc=16 (column-major) size=152347 batch=319 memory=1024 MB

LAPACK/BLAS...
	performance: 0.9 GFLOPS/s
	bandwidth: 0.5 GB/s
	duration: 0.9 s
Inlined...
	performance: 72.4 GFLOPS/s
	bandwidth: 38.7 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 168.4 GFLOPS/s
	bandwidth: 90.1 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 189.3 GFLOPS/s
	bandwidth: 101.3 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=9 n=32 k=22 ldc=16 (column-major) size=94920 batch=252 memory=1024 MB

LAPACK/BLAS...
	performance: 1.3 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 71.0 GFLOPS/s
	bandwidth: 37.8 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 159.2 GFLOPS/s
	bandwidth: 84.8 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 173.4 GFLOPS/s
	bandwidth: 92.4 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=9 n=32 k=32 ldc=16 (column-major) size=73584 batch=221 memory=1024 MB

LAPACK/BLAS...
	performance: 1.5 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 69.2 GFLOPS/s
	bandwidth: 36.9 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 152.1 GFLOPS/s
	bandwidth: 81.0 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 161.2 GFLOPS/s
	bandwidth: 85.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=12 n=12 k=12 ldc=16 (column-major) size=279620 batch=432 memory=1024 MB

LAPACK/BLAS...
	performance: 10.8 GFLOPS/s
	bandwidth: 6.7 GB/s
	duration: 0.1 s
Inlined...
	performance: 76.1 GFLOPS/s
	bandwidth: 47.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 167.9 GFLOPS/s
	bandwidth: 104.6 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 197.8 GFLOPS/s
	bandwidth: 123.2 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=5 k=5 ldc=16 (column-major) size=789516 batch=725 memory=1024 MB

LAPACK/BLAS...
	performance: 6.1 GFLOPS/s
	bandwidth: 6.3 GB/s
	duration: 0.1 s
Inlined...
	performance: 66.5 GFLOPS/s
	bandwidth: 68.7 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 79.1 GFLOPS/s
	bandwidth: 81.8 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 120.5 GFLOPS/s
	bandwidth: 124.7 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=5 k=13 ldc=16 (column-major) size=427444 batch=534 memory=1024 MB

LAPACK/BLAS...
	performance: 7.0 GFLOPS/s
	bandwidth: 7.2 GB/s
	duration: 0.1 s
Inlined...
	performance: 81.1 GFLOPS/s
	bandwidth: 83.8 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 101.8 GFLOPS/s
	bandwidth: 105.1 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 124.9 GFLOPS/s
	bandwidth: 129.0 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=5 k=24 ldc=16 (column-major) size=262144 batch=418 memory=1024 MB

LAPACK/BLAS...
	performance: 7.1 GFLOPS/s
	bandwidth: 7.4 GB/s
	duration: 0.1 s
Inlined...
	performance: 83.0 GFLOPS/s
	bandwidth: 85.7 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 113.5 GFLOPS/s
	bandwidth: 117.1 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 124.6 GFLOPS/s
	bandwidth: 128.7 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=5 k=26 ldc=16 (column-major) size=244922 batch=404 memory=1024 MB

LAPACK/BLAS...
	performance: 7.2 GFLOPS/s
	bandwidth: 7.4 GB/s
	duration: 0.1 s
Inlined...
	performance: 65.0 GFLOPS/s
	bandwidth: 67.1 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 112.3 GFLOPS/s
	bandwidth: 116.0 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 125.6 GFLOPS/s
	bandwidth: 129.7 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=5 k=32 ldc=16 (column-major) size=204600 batch=369 memory=1024 MB

LAPACK/BLAS...
	performance: 7.2 GFLOPS/s
	bandwidth: 7.4 GB/s
	duration: 0.1 s
Inlined...
	performance: 80.7 GFLOPS/s
	bandwidth: 83.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 109.4 GFLOPS/s
	bandwidth: 113.0 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 122.0 GFLOPS/s
	bandwidth: 126.0 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=13 k=5 ldc=16 (column-major) size=397093 batch=515 memory=1024 MB

LAPACK/BLAS...
	performance: 9.2 GFLOPS/s
	bandwidth: 5.3 GB/s
	duration: 0.1 s
Inlined...
	performance: 66.7 GFLOPS/s
	bandwidth: 38.5 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 148.3 GFLOPS/s
	bandwidth: 85.5 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 175.1 GFLOPS/s
	bandwidth: 101.0 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=13 k=13 ldc=16 (column-major) size=245820 batch=405 memory=1024 MB

LAPACK/BLAS...
	performance: 11.7 GFLOPS/s
	bandwidth: 6.7 GB/s
	duration: 0.1 s
Inlined...
	performance: 91.8 GFLOPS/s
	bandwidth: 52.8 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 173.7 GFLOPS/s
	bandwidth: 99.9 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 210.1 GFLOPS/s
	bandwidth: 120.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=13 k=24 ldc=16 (column-major) size=161319 batch=328 memory=1024 MB

LAPACK/BLAS...
	performance: 12.5 GFLOPS/s
	bandwidth: 7.2 GB/s
	duration: 0.1 s
Inlined...
	performance: 80.0 GFLOPS/s
	bandwidth: 46.0 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 166.9 GFLOPS/s
	bandwidth: 95.9 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 192.4 GFLOPS/s
	bandwidth: 110.5 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=13 k=26 ldc=16 (column-major) size=151830 batch=318 memory=1024 MB

LAPACK/BLAS...
	performance: 12.8 GFLOPS/s
	bandwidth: 7.4 GB/s
	duration: 0.1 s
Inlined...
	performance: 106.9 GFLOPS/s
	bandwidth: 61.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 200.2 GFLOPS/s
	bandwidth: 114.9 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 216.7 GFLOPS/s
	bandwidth: 124.4 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=13 k=28 ldc=16 (column-major) size=143395 batch=309 memory=1024 MB

LAPACK/BLAS...
	performance: 12.6 GFLOPS/s
	bandwidth: 7.2 GB/s
	duration: 0.1 s
Inlined...
	performance: 111.9 GFLOPS/s
	bandwidth: 64.2 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 196.0 GFLOPS/s
	bandwidth: 112.6 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 214.1 GFLOPS/s
	bandwidth: 122.9 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=13 k=32 ldc=16 (column-major) size=129055 batch=293 memory=1024 MB

LAPACK/BLAS...
	performance: 12.6 GFLOPS/s
	bandwidth: 7.2 GB/s
	duration: 0.1 s
Inlined...
	performance: 109.4 GFLOPS/s
	bandwidth: 62.8 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 199.7 GFLOPS/s
	bandwidth: 114.6 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 212.8 GFLOPS/s
	bandwidth: 122.2 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=13 k=45 ldc=16 (column-major) size=97400 batch=255 memory=1024 MB

LAPACK/BLAS...
	performance: 12.3 GFLOPS/s
	bandwidth: 7.1 GB/s
	duration: 0.1 s
Inlined...
	performance: 105.8 GFLOPS/s
	bandwidth: 60.7 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 160.3 GFLOPS/s
	bandwidth: 92.0 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 166.5 GFLOPS/s
	bandwidth: 95.6 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=24 k=5 ldc=16 (column-major) size=235883 batch=397 memory=1024 MB

LAPACK/BLAS...
	performance: 0.8 GFLOPS/s
	bandwidth: 0.4 GB/s
	duration: 0.9 s
Inlined...
	performance: 72.6 GFLOPS/s
	bandwidth: 32.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 157.5 GFLOPS/s
	bandwidth: 70.3 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 208.1 GFLOPS/s
	bandwidth: 92.9 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=24 k=13 ldc=16 (column-major) size=155165 batch=322 memory=1024 MB

LAPACK/BLAS...
	performance: 1.4 GFLOPS/s
	bandwidth: 0.6 GB/s
	duration: 0.9 s
Inlined...
	performance: 92.0 GFLOPS/s
	bandwidth: 40.9 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 206.8 GFLOPS/s
	bandwidth: 91.8 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 232.3 GFLOPS/s
	bandwidth: 103.1 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=24 k=24 ldc=16 (column-major) size=105517 batch=265 memory=1024 MB

LAPACK/BLAS...
	performance: 1.7 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 106.3 GFLOPS/s
	bandwidth: 47.1 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 223.4 GFLOPS/s
	bandwidth: 99.0 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 241.7 GFLOPS/s
	bandwidth: 107.1 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=24 k=26 ldc=16 (column-major) size=99715 batch=258 memory=1024 MB

LAPACK/BLAS...
	performance: 1.8 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 106.2 GFLOPS/s
	bandwidth: 47.1 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 209.3 GFLOPS/s
	bandwidth: 92.8 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 223.9 GFLOPS/s
	bandwidth: 99.2 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=24 k=32 ldc=16 (column-major) size=85598 batch=239 memory=1024 MB

LAPACK/BLAS...
	performance: 1.9 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 77.4 GFLOPS/s
	bandwidth: 34.3 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 208.8 GFLOPS/s
	bandwidth: 92.5 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 222.2 GFLOPS/s
	bandwidth: 98.4 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=26 k=5 ldc=16 (column-major) size=219668 batch=383 memory=1024 MB

LAPACK/BLAS...
	performance: 0.8 GFLOPS/s
	bandwidth: 0.4 GB/s
	duration: 0.9 s
Inlined...
	performance: 73.7 GFLOPS/s
	bandwidth: 32.0 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 157.3 GFLOPS/s
	bandwidth: 68.4 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 198.3 GFLOPS/s
	bandwidth: 86.2 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=26 k=13 ldc=16 (column-major) size=145414 batch=311 memory=1024 MB

LAPACK/BLAS...
	performance: 1.4 GFLOPS/s
	bandwidth: 0.6 GB/s
	duration: 0.9 s
Inlined...
	performance: 108.0 GFLOPS/s
	bandwidth: 46.7 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 230.8 GFLOPS/s
	bandwidth: 99.7 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 241.7 GFLOPS/s
	bandwidth: 104.4 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=26 k=24 ldc=16 (column-major) size=99273 batch=257 memory=1024 MB

LAPACK/BLAS...
	performance: 1.8 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 100.7 GFLOPS/s
	bandwidth: 43.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 217.6 GFLOPS/s
	bandwidth: 93.9 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 242.4 GFLOPS/s
	bandwidth: 104.5 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=26 k=26 ldc=16 (column-major) size=93858 batch=250 memory=1024 MB

LAPACK/BLAS...
	performance: 1.8 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 104.1 GFLOPS/s
	bandwidth: 44.9 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 213.6 GFLOPS/s
	bandwidth: 92.1 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 219.8 GFLOPS/s
	bandwidth: 94.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=26 k=28 ldc=16 (column-major) size=89003 batch=244 memory=1024 MB

LAPACK/BLAS...
	performance: 1.8 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 101.3 GFLOPS/s
	bandwidth: 43.7 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 202.2 GFLOPS/s
	bandwidth: 87.2 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 218.4 GFLOPS/s
	bandwidth: 94.2 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=26 k=32 ldc=16 (column-major) size=80659 batch=232 memory=1024 MB

LAPACK/BLAS...
	performance: 1.9 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 102.0 GFLOPS/s
	bandwidth: 44.0 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 202.9 GFLOPS/s
	bandwidth: 87.5 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 217.1 GFLOPS/s
	bandwidth: 93.6 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=26 k=45 ldc=16 (column-major) size=61822 batch=203 memory=1024 MB

LAPACK/BLAS...
	performance: 2.0 GFLOPS/s
	bandwidth: 0.9 GB/s
	duration: 0.9 s
Inlined...
	performance: 94.1 GFLOPS/s
	bandwidth: 40.5 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 137.5 GFLOPS/s
	bandwidth: 59.2 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 142.3 GFLOPS/s
	bandwidth: 61.3 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=28 k=13 ldc=16 (column-major) size=136817 batch=302 memory=1024 MB

LAPACK/BLAS...
	performance: 1.4 GFLOPS/s
	bandwidth: 0.6 GB/s
	duration: 0.9 s
Inlined...
	performance: 104.1 GFLOPS/s
	bandwidth: 43.9 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 226.7 GFLOPS/s
	bandwidth: 95.7 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 259.1 GFLOPS/s
	bandwidth: 109.3 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=28 k=26 ldc=16 (column-major) size=88651 batch=243 memory=1024 MB

LAPACK/BLAS...
	performance: 1.8 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 102.1 GFLOPS/s
	bandwidth: 43.0 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 195.3 GFLOPS/s
	bandwidth: 82.2 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 225.6 GFLOPS/s
	bandwidth: 95.0 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=28 k=28 ldc=16 (column-major) size=84096 batch=237 memory=1024 MB

LAPACK/BLAS...
	performance: 1.9 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 102.2 GFLOPS/s
	bandwidth: 43.0 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 206.3 GFLOPS/s
	bandwidth: 86.9 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 216.1 GFLOPS/s
	bandwidth: 91.0 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=28 k=32 ldc=16 (column-major) size=76260 batch=225 memory=1024 MB

LAPACK/BLAS...
	performance: 1.9 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 100.2 GFLOPS/s
	bandwidth: 42.2 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 197.9 GFLOPS/s
	bandwidth: 83.3 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 213.7 GFLOPS/s
	bandwidth: 89.9 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=28 k=45 ldc=16 (column-major) size=58533 batch=198 memory=1024 MB

LAPACK/BLAS...
	performance: 2.1 GFLOPS/s
	bandwidth: 0.9 GB/s
	duration: 0.9 s
Inlined...
	performance: 93.7 GFLOPS/s
	bandwidth: 39.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 134.2 GFLOPS/s
	bandwidth: 56.4 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 137.6 GFLOPS/s
	bandwidth: 57.9 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=32 k=5 ldc=16 (column-major) size=182113 batch=348 memory=1024 MB

LAPACK/BLAS...
	performance: 0.9 GFLOPS/s
	bandwidth: 0.4 GB/s
	duration: 0.9 s
Inlined...
	performance: 70.4 GFLOPS/s
	bandwidth: 28.7 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 163.3 GFLOPS/s
	bandwidth: 66.7 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 195.2 GFLOPS/s
	bandwidth: 79.7 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=32 k=13 ldc=16 (column-major) size=122349 batch=286 memory=1024 MB

LAPACK/BLAS...
	performance: 1.5 GFLOPS/s
	bandwidth: 0.6 GB/s
	duration: 0.9 s
Inlined...
	performance: 94.9 GFLOPS/s
	bandwidth: 38.5 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 227.0 GFLOPS/s
	bandwidth: 92.0 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 255.9 GFLOPS/s
	bandwidth: 103.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=32 k=24 ldc=16 (column-major) size=84307 batch=237 memory=1024 MB

LAPACK/BLAS...
	performance: 1.9 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 99.0 GFLOPS/s
	bandwidth: 40.1 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 218.0 GFLOPS/s
	bandwidth: 88.2 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 236.5 GFLOPS/s
	bandwidth: 95.7 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=32 k=26 ldc=16 (column-major) size=79796 batch=231 memory=1024 MB

LAPACK/BLAS...
	performance: 2.0 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 99.0 GFLOPS/s
	bandwidth: 40.0 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 199.0 GFLOPS/s
	bandwidth: 80.5 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 217.1 GFLOPS/s
	bandwidth: 87.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=32 k=28 ldc=16 (column-major) size=75743 batch=225 memory=1024 MB

LAPACK/BLAS...
	performance: 2.0 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 87.5 GFLOPS/s
	bandwidth: 35.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 206.7 GFLOPS/s
	bandwidth: 83.6 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 220.0 GFLOPS/s
	bandwidth: 89.0 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=32 k=32 ldc=16 (column-major) size=68759 batch=214 memory=1024 MB

LAPACK/BLAS...
	performance: 2.0 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 94.9 GFLOPS/s
	bandwidth: 38.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 205.9 GFLOPS/s
	bandwidth: 83.2 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 218.2 GFLOPS/s
	bandwidth: 88.2 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=32 k=45 ldc=16 (column-major) size=52904 batch=188 memory=1024 MB

LAPACK/BLAS...
	performance: 2.2 GFLOPS/s
	bandwidth: 0.9 GB/s
	duration: 0.9 s
Inlined...
	performance: 89.9 GFLOPS/s
	bandwidth: 36.3 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 138.4 GFLOPS/s
	bandwidth: 55.9 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 140.9 GFLOPS/s
	bandwidth: 56.9 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=45 k=13 ldc=16 (column-major) size=91056 batch=246 memory=1024 MB

LAPACK/BLAS...
	performance: 1.6 GFLOPS/s
	bandwidth: 0.6 GB/s
	duration: 0.9 s
Inlined...
	performance: 95.8 GFLOPS/s
	bandwidth: 35.7 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 207.3 GFLOPS/s
	bandwidth: 77.1 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 232.2 GFLOPS/s
	bandwidth: 86.4 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=45 k=26 ldc=16 (column-major) size=60241 batch=200 memory=1024 MB

LAPACK/BLAS...
	performance: 2.0 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 90.4 GFLOPS/s
	bandwidth: 33.6 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 188.3 GFLOPS/s
	bandwidth: 69.9 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 195.5 GFLOPS/s
	bandwidth: 72.5 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=45 k=28 ldc=16 (column-major) size=57260 batch=195 memory=1024 MB

LAPACK/BLAS...
	performance: 2.0 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 91.7 GFLOPS/s
	bandwidth: 34.0 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 186.9 GFLOPS/s
	bandwidth: 69.3 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 195.6 GFLOPS/s
	bandwidth: 72.6 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=45 k=32 ldc=16 (column-major) size=52103 batch=186 memory=1024 MB

LAPACK/BLAS...
	performance: 2.1 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 88.2 GFLOPS/s
	bandwidth: 32.7 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 183.4 GFLOPS/s
	bandwidth: 68.0 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 198.9 GFLOPS/s
	bandwidth: 73.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=13 n=45 k=45 ldc=16 (column-major) size=40305 batch=164 memory=1024 MB

LAPACK/BLAS...
	performance: 2.3 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 81.6 GFLOPS/s
	bandwidth: 30.2 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 124.1 GFLOPS/s
	bandwidth: 46.0 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 126.4 GFLOPS/s
	bandwidth: 46.9 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=14 n=14 k=14 ldc=16 (column-major) size=217885 batch=381 memory=1024 MB

LAPACK/BLAS...
	performance: 12.4 GFLOPS/s
	bandwidth: 6.6 GB/s
	duration: 0.1 s
Inlined...
	performance: 95.5 GFLOPS/s
	bandwidth: 51.0 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 194.6 GFLOPS/s
	bandwidth: 103.9 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 212.8 GFLOPS/s
	bandwidth: 113.6 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=14 n=14 k=16 ldc=16 (column-major) size=199728 batch=365 memory=1024 MB

LAPACK/BLAS...
	performance: 12.7 GFLOPS/s
	bandwidth: 6.8 GB/s
	duration: 0.1 s
Inlined...
	performance: 88.5 GFLOPS/s
	bandwidth: 47.2 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 185.7 GFLOPS/s
	bandwidth: 99.1 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 211.4 GFLOPS/s
	bandwidth: 112.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=14 n=14 k=29 ldc=16 (column-major) size=129553 batch=294 memory=1024 MB

LAPACK/BLAS...
	performance: 13.1 GFLOPS/s
	bandwidth: 7.0 GB/s
	duration: 0.1 s
Inlined...
	performance: 121.8 GFLOPS/s
	bandwidth: 64.9 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 204.7 GFLOPS/s
	bandwidth: 109.2 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 225.6 GFLOPS/s
	bandwidth: 120.3 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=14 n=14 k=32 ldc=16 (column-major) size=119837 batch=283 memory=1024 MB

LAPACK/BLAS...
	performance: 13.8 GFLOPS/s
	bandwidth: 7.4 GB/s
	duration: 0.1 s
Inlined...
	performance: 115.8 GFLOPS/s
	bandwidth: 61.8 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 203.1 GFLOPS/s
	bandwidth: 108.3 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 223.5 GFLOPS/s
	bandwidth: 119.2 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=14 n=16 k=14 ldc=16 (column-major) size=198546 batch=364 memory=1024 MB

LAPACK/BLAS...
	performance: 1.4 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 97.5 GFLOPS/s
	bandwidth: 48.8 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 191.4 GFLOPS/s
	bandwidth: 95.8 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 213.2 GFLOPS/s
	bandwidth: 106.7 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=14 n=16 k=16 ldc=16 (column-major) size=182361 batch=349 memory=1024 MB

LAPACK/BLAS...
	performance: 1.4 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 98.5 GFLOPS/s
	bandwidth: 49.3 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 189.0 GFLOPS/s
	bandwidth: 94.6 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 217.7 GFLOPS/s
	bandwidth: 109.0 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=14 n=16 k=29 ldc=16 (column-major) size=119198 batch=282 memory=1024 MB

LAPACK/BLAS...
	performance: 1.7 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 114.3 GFLOPS/s
	bandwidth: 57.1 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 185.6 GFLOPS/s
	bandwidth: 92.8 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 229.3 GFLOPS/s
	bandwidth: 114.6 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=14 n=29 k=14 ldc=16 (column-major) size=125907 batch=290 memory=1024 MB

LAPACK/BLAS...
	performance: 1.6 GFLOPS/s
	bandwidth: 0.6 GB/s
	duration: 0.9 s
Inlined...
	performance: 110.4 GFLOPS/s
	bandwidth: 43.8 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 232.0 GFLOPS/s
	bandwidth: 92.0 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 274.3 GFLOPS/s
	bandwidth: 108.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=14 n=29 k=16 ldc=16 (column-major) size=116508 batch=279 memory=1024 MB

LAPACK/BLAS...
	performance: 1.7 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 112.4 GFLOPS/s
	bandwidth: 44.6 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 246.6 GFLOPS/s
	bandwidth: 97.8 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 254.0 GFLOPS/s
	bandwidth: 100.7 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=14 n=29 k=29 ldc=16 (column-major) size=78444 batch=229 memory=1024 MB

LAPACK/BLAS...
	performance: 2.0 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 108.0 GFLOPS/s
	bandwidth: 42.8 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 201.4 GFLOPS/s
	bandwidth: 79.7 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 209.3 GFLOPS/s
	bandwidth: 82.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=14 n=29 k=32 ldc=16 (column-major) size=72944 batch=221 memory=1024 MB

LAPACK/BLAS...
	performance: 2.1 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 102.9 GFLOPS/s
	bandwidth: 40.7 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 207.4 GFLOPS/s
	bandwidth: 82.1 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 220.4 GFLOPS/s
	bandwidth: 87.2 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=14 n=32 k=14 ldc=16 (column-major) size=116105 batch=278 memory=1024 MB

LAPACK/BLAS...
	performance: 1.6 GFLOPS/s
	bandwidth: 0.6 GB/s
	duration: 0.9 s
Inlined...
	performance: 112.0 GFLOPS/s
	bandwidth: 43.1 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 253.2 GFLOPS/s
	bandwidth: 97.4 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 269.9 GFLOPS/s
	bandwidth: 103.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=14 n=32 k=29 ldc=16 (column-major) size=72707 batch=220 memory=1024 MB

LAPACK/BLAS...
	performance: 2.1 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 106.0 GFLOPS/s
	bandwidth: 40.7 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 206.6 GFLOPS/s
	bandwidth: 79.3 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 219.6 GFLOPS/s
	bandwidth: 84.3 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=14 n=32 k=32 ldc=16 (column-major) size=67650 batch=212 memory=1024 MB

LAPACK/BLAS...
	performance: 2.2 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 101.7 GFLOPS/s
	bandwidth: 39.0 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 213.6 GFLOPS/s
	bandwidth: 82.0 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 229.1 GFLOPS/s
	bandwidth: 87.9 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=16 n=14 k=14 ldc=16 (column-major) size=208412 batch=373 memory=1024 MB

LAPACK/BLAS...
	performance: 14.3 GFLOPS/s
	bandwidth: 7.2 GB/s
	duration: 0.1 s
Inlined...
	performance: 104.6 GFLOPS/s
	bandwidth: 52.3 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 192.5 GFLOPS/s
	bandwidth: 96.3 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 210.7 GFLOPS/s
	bandwidth: 105.4 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=16 n=14 k=16 ldc=16 (column-major) size=190650 batch=357 memory=1024 MB

LAPACK/BLAS...
	performance: 15.1 GFLOPS/s
	bandwidth: 7.6 GB/s
	duration: 0.1 s
Inlined...
	performance: 100.3 GFLOPS/s
	bandwidth: 50.2 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 163.0 GFLOPS/s
	bandwidth: 81.5 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 179.5 GFLOPS/s
	bandwidth: 89.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=16 n=14 k=29 ldc=16 (column-major) size=122685 batch=286 memory=1024 MB

LAPACK/BLAS...
	performance: 13.8 GFLOPS/s
	bandwidth: 6.9 GB/s
	duration: 0.1 s
Inlined...
	performance: 108.1 GFLOPS/s
	bandwidth: 54.0 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 188.8 GFLOPS/s
	bandwidth: 94.4 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 197.2 GFLOPS/s
	bandwidth: 98.6 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=16 n=16 k=14 ldc=16 (column-major) size=190650 batch=357 memory=1024 MB

LAPACK/BLAS...
	performance: 1.5 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 102.0 GFLOPS/s
	bandwidth: 47.7 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 188.0 GFLOPS/s
	bandwidth: 87.8 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 208.3 GFLOPS/s
	bandwidth: 97.3 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=16 n=16 k=16 ldc=16 (column-major) size=174762 batch=341 memory=1024 MB

LAPACK/BLAS...
	performance: 1.6 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 98.6 GFLOPS/s
	bandwidth: 46.0 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 165.1 GFLOPS/s
	bandwidth: 77.1 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 180.6 GFLOPS/s
	bandwidth: 84.3 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=16 n=16 k=29 ldc=16 (column-major) size=113359 batch=275 memory=1024 MB

LAPACK/BLAS...
	performance: 1.9 GFLOPS/s
	bandwidth: 0.9 GB/s
	duration: 0.9 s
Inlined...
	performance: 122.0 GFLOPS/s
	bandwidth: 56.9 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 194.5 GFLOPS/s
	bandwidth: 90.8 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 203.2 GFLOPS/s
	bandwidth: 94.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=16 n=16 k=55 ldc=16 (column-major) size=66576 batch=211 memory=1024 MB

LAPACK/BLAS...
	performance: 2.1 GFLOPS/s
	bandwidth: 1.0 GB/s
	duration: 0.9 s
Inlined...
	performance: 102.3 GFLOPS/s
	bandwidth: 47.7 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 146.5 GFLOPS/s
	bandwidth: 68.3 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 148.4 GFLOPS/s
	bandwidth: 69.2 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=16 n=29 k=14 ldc=16 (column-major) size=122685 batch=286 memory=1024 MB

LAPACK/BLAS...
	performance: 1.8 GFLOPS/s
	bandwidth: 0.6 GB/s
	duration: 0.9 s
Inlined...
	performance: 116.7 GFLOPS/s
	bandwidth: 42.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 263.2 GFLOPS/s
	bandwidth: 95.6 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 290.5 GFLOPS/s
	bandwidth: 105.5 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=16 n=29 k=16 ldc=16 (column-major) size=113359 batch=275 memory=1024 MB

LAPACK/BLAS...
	performance: 1.9 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 119.6 GFLOPS/s
	bandwidth: 43.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 245.4 GFLOPS/s
	bandwidth: 89.1 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 265.9 GFLOPS/s
	bandwidth: 96.5 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=16 n=29 k=29 ldc=16 (column-major) size=75872 batch=225 memory=1024 MB

LAPACK/BLAS...
	performance: 2.2 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 112.3 GFLOPS/s
	bandwidth: 40.7 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 207.7 GFLOPS/s
	bandwidth: 75.3 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 223.5 GFLOPS/s
	bandwidth: 81.0 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=16 n=29 k=55 ldc=16 (column-major) size=45667 batch=174 memory=1024 MB

LAPACK/BLAS...
	performance: 2.5 GFLOPS/s
	bandwidth: 0.9 GB/s
	duration: 0.9 s
Inlined...
	performance: 91.0 GFLOPS/s
	bandwidth: 32.9 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 159.3 GFLOPS/s
	bandwidth: 57.7 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 163.8 GFLOPS/s
	bandwidth: 59.3 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=16 n=55 k=16 ldc=16 (column-major) size=66576 batch=211 memory=1024 MB

LAPACK/BLAS...
	performance: 2.1 GFLOPS/s
	bandwidth: 0.6 GB/s
	duration: 0.9 s
Inlined...
	performance: 100.8 GFLOPS/s
	bandwidth: 30.5 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 231.5 GFLOPS/s
	bandwidth: 70.1 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 250.0 GFLOPS/s
	bandwidth: 75.7 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=16 n=55 k=29 ldc=16 (column-major) size=45667 batch=174 memory=1024 MB

LAPACK/BLAS...
	performance: 2.5 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 96.1 GFLOPS/s
	bandwidth: 29.0 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 198.1 GFLOPS/s
	bandwidth: 59.8 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 203.6 GFLOPS/s
	bandwidth: 61.5 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=16 n=55 k=55 ldc=16 (column-major) size=28049 batch=137 memory=1024 MB

LAPACK/BLAS...
	performance: 3.7 GFLOPS/s
	bandwidth: 1.1 GB/s
	duration: 0.7 s
Inlined...
	performance: 119.4 GFLOPS/s
	bandwidth: 36.0 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 220.4 GFLOPS/s
	bandwidth: 66.5 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 248.9 GFLOPS/s
	bandwidth: 75.1 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=22 n=9 k=9 ldc=24 (column-major) size=271146 batch=425 memory=1024 MB

LAPACK/BLAS...
	performance: 11.0 GFLOPS/s
	bandwidth: 6.5 GB/s
	duration: 0.1 s
Inlined...
	performance: 81.0 GFLOPS/s
	bandwidth: 47.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 162.8 GFLOPS/s
	bandwidth: 95.3 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 186.9 GFLOPS/s
	bandwidth: 109.4 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=22 n=9 k=22 ldc=24 (column-major) size=149462 batch=316 memory=1024 MB

LAPACK/BLAS...
	performance: 11.5 GFLOPS/s
	bandwidth: 6.7 GB/s
	duration: 0.1 s
Inlined...
	performance: 96.4 GFLOPS/s
	bandwidth: 56.3 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 194.5 GFLOPS/s
	bandwidth: 113.7 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 204.5 GFLOPS/s
	bandwidth: 119.5 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=22 n=9 k=32 ldc=24 (column-major) size=111107 batch=272 memory=1024 MB

LAPACK/BLAS...
	performance: 12.1 GFLOPS/s
	bandwidth: 7.1 GB/s
	duration: 0.1 s
Inlined...
	performance: 88.2 GFLOPS/s
	bandwidth: 51.5 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 170.6 GFLOPS/s
	bandwidth: 99.7 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 182.7 GFLOPS/s
	bandwidth: 106.7 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=22 n=22 k=9 ldc=24 (column-major) size=145257 batch=311 memory=1024 MB

LAPACK/BLAS...
	performance: 1.4 GFLOPS/s
	bandwidth: 0.5 GB/s
	duration: 0.9 s
Inlined...
	performance: 87.3 GFLOPS/s
	bandwidth: 29.8 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 249.2 GFLOPS/s
	bandwidth: 85.1 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 283.4 GFLOPS/s
	bandwidth: 96.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=22 n=22 k=22 ldc=24 (column-major) size=89717 batch=245 memory=1024 MB

LAPACK/BLAS...
	performance: 2.1 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 88.3 GFLOPS/s
	bandwidth: 30.0 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 237.9 GFLOPS/s
	bandwidth: 80.9 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 259.1 GFLOPS/s
	bandwidth: 88.1 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=22 n=22 k=32 ldc=24 (column-major) size=69327 batch=215 memory=1024 MB

LAPACK/BLAS...
	performance: 2.4 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 78.9 GFLOPS/s
	bandwidth: 26.8 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 219.6 GFLOPS/s
	bandwidth: 74.6 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 231.6 GFLOPS/s
	bandwidth: 78.7 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=22 n=32 k=9 ldc=24 (column-major) size=107031 batch=267 memory=1024 MB

LAPACK/BLAS...
	performance: 1.6 GFLOPS/s
	bandwidth: 0.5 GB/s
	duration: 0.8 s
Inlined...
	performance: 80.2 GFLOPS/s
	bandwidth: 23.2 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 242.2 GFLOPS/s
	bandwidth: 70.0 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 272.6 GFLOPS/s
	bandwidth: 78.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=22 n=32 k=22 ldc=24 (column-major) size=68618 batch=214 memory=1024 MB

LAPACK/BLAS...
	performance: 2.4 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 80.8 GFLOPS/s
	bandwidth: 23.2 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 227.5 GFLOPS/s
	bandwidth: 65.4 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 265.5 GFLOPS/s
	bandwidth: 76.3 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=22 n=32 k=32 ldc=24 (column-major) size=53773 batch=189 memory=1024 MB

LAPACK/BLAS...
	performance: 2.8 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 75.3 GFLOPS/s
	bandwidth: 21.6 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 221.4 GFLOPS/s
	bandwidth: 63.6 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 233.6 GFLOPS/s
	bandwidth: 67.1 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=23 n=23 k=23 ldc=24 (column-major) size=83365 batch=236 memory=1024 MB

LAPACK/BLAS...
	performance: 2.3 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 92.8 GFLOPS/s
	bandwidth: 30.2 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 252.0 GFLOPS/s
	bandwidth: 82.0 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 267.8 GFLOPS/s
	bandwidth: 87.1 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=24 n=5 k=5 ldc=24 (column-major) size=506481 batch=581 memory=1024 MB

LAPACK/BLAS...
	performance: 7.5 GFLOPS/s
	bandwidth: 6.8 GB/s
	duration: 0.1 s
Inlined...
	performance: 64.2 GFLOPS/s
	bandwidth: 58.0 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 98.6 GFLOPS/s
	bandwidth: 89.1 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 132.9 GFLOPS/s
	bandwidth: 120.0 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=24 n=5 k=13 ldc=24 (column-major) size=270055 batch=424 memory=1024 MB

LAPACK/BLAS...
	performance: 8.3 GFLOPS/s
	bandwidth: 7.5 GB/s
	duration: 0.1 s
Inlined...
	performance: 78.4 GFLOPS/s
	bandwidth: 70.7 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 97.9 GFLOPS/s
	bandwidth: 88.3 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 109.6 GFLOPS/s
	bandwidth: 98.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=24 n=5 k=24 ldc=24 (column-major) size=164482 batch=331 memory=1024 MB

LAPACK/BLAS...
	performance: 8.4 GFLOPS/s
	bandwidth: 7.5 GB/s
	duration: 0.1 s
Inlined...
	performance: 68.1 GFLOPS/s
	bandwidth: 61.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 89.2 GFLOPS/s
	bandwidth: 80.4 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 99.3 GFLOPS/s
	bandwidth: 89.5 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=24 n=5 k=26 ldc=24 (column-major) size=153567 batch=320 memory=1024 MB

LAPACK/BLAS...
	performance: 8.2 GFLOPS/s
	bandwidth: 7.4 GB/s
	duration: 0.1 s
Inlined...
	performance: 79.2 GFLOPS/s
	bandwidth: 71.3 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 115.6 GFLOPS/s
	bandwidth: 104.2 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 120.9 GFLOPS/s
	bandwidth: 109.0 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=24 n=5 k=32 ldc=24 (column-major) size=128070 batch=292 memory=1024 MB

LAPACK/BLAS...
	performance: 8.7 GFLOPS/s
	bandwidth: 7.8 GB/s
	duration: 0.1 s
Inlined...
	performance: 75.2 GFLOPS/s
	bandwidth: 67.8 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 111.6 GFLOPS/s
	bandwidth: 100.6 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 117.7 GFLOPS/s
	bandwidth: 106.1 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=24 n=13 k=5 ldc=24 (column-major) size=270055 batch=424 memory=1024 MB

LAPACK/BLAS...
	performance: 12.1 GFLOPS/s
	bandwidth: 5.4 GB/s
	duration: 0.1 s
Inlined...
	performance: 72.6 GFLOPS/s
	bandwidth: 32.3 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 175.6 GFLOPS/s
	bandwidth: 78.2 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 217.3 GFLOPS/s
	bandwidth: 96.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=24 n=13 k=13 ldc=24 (column-major) size=169253 batch=336 memory=1024 MB

LAPACK/BLAS...
	performance: 14.5 GFLOPS/s
	bandwidth: 6.4 GB/s
	duration: 0.1 s
Inlined...
	performance: 81.0 GFLOPS/s
	bandwidth: 35.9 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 168.0 GFLOPS/s
	bandwidth: 74.5 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 190.1 GFLOPS/s
	bandwidth: 84.3 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=24 n=13 k=24 ldc=24 (column-major) size=111848 batch=273 memory=1024 MB

LAPACK/BLAS...
	performance: 17.1 GFLOPS/s
	bandwidth: 7.6 GB/s
	duration: 0.1 s
Inlined...
	performance: 100.6 GFLOPS/s
	bandwidth: 44.6 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 206.5 GFLOPS/s
	bandwidth: 91.5 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 238.3 GFLOPS/s
	bandwidth: 105.5 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=24 n=13 k=26 ldc=24 (column-major) size=105351 batch=265 memory=1024 MB

LAPACK/BLAS...
	performance: 16.4 GFLOPS/s
	bandwidth: 7.3 GB/s
	duration: 0.1 s
Inlined...
	performance: 95.5 GFLOPS/s
	bandwidth: 42.3 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 208.8 GFLOPS/s
	bandwidth: 92.5 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 215.6 GFLOPS/s
	bandwidth: 95.5 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=24 n=13 k=32 ldc=24 (column-major) size=89717 batch=245 memory=1024 MB

LAPACK/BLAS...
	performance: 17.0 GFLOPS/s
	bandwidth: 7.5 GB/s
	duration: 0.1 s
Inlined...
	performance: 94.7 GFLOPS/s
	bandwidth: 41.9 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 207.1 GFLOPS/s
	bandwidth: 91.7 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 218.4 GFLOPS/s
	bandwidth: 96.7 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=24 n=24 k=5 ldc=24 (column-major) size=164482 batch=331 memory=1024 MB

LAPACK/BLAS...
	performance: 1.1 GFLOPS/s
	bandwidth: 0.3 GB/s
	duration: 0.9 s
Inlined...
	performance: 64.1 GFLOPS/s
	bandwidth: 20.2 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 196.0 GFLOPS/s
	bandwidth: 61.7 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 241.0 GFLOPS/s
	bandwidth: 75.9 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=24 n=24 k=13 ldc=24 (column-major) size=111848 batch=273 memory=1024 MB

LAPACK/BLAS...
	performance: 1.9 GFLOPS/s
	bandwidth: 0.6 GB/s
	duration: 0.9 s
Inlined...
	performance: 97.3 GFLOPS/s
	bandwidth: 30.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 252.8 GFLOPS/s
	bandwidth: 79.0 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 274.9 GFLOPS/s
	bandwidth: 85.9 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=24 n=24 k=24 ldc=24 (column-major) size=77672 batch=228 memory=1024 MB

LAPACK/BLAS...
	performance: 2.3 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 93.0 GFLOPS/s
	bandwidth: 29.0 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 252.3 GFLOPS/s
	bandwidth: 78.7 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 264.2 GFLOPS/s
	bandwidth: 82.4 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=24 n=24 k=26 ldc=24 (column-major) size=73584 batch=221 memory=1024 MB

LAPACK/BLAS...
	performance: 2.4 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 90.7 GFLOPS/s
	bandwidth: 28.3 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 237.8 GFLOPS/s
	bandwidth: 74.1 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 249.7 GFLOPS/s
	bandwidth: 77.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=24 n=24 k=32 ldc=24 (column-major) size=63550 batch=206 memory=1024 MB

LAPACK/BLAS...
	performance: 2.6 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 88.8 GFLOPS/s
	bandwidth: 27.7 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 245.4 GFLOPS/s
	bandwidth: 76.5 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 252.9 GFLOPS/s
	bandwidth: 78.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=24 n=26 k=5 ldc=24 (column-major) size=153567 batch=320 memory=1024 MB

LAPACK/BLAS...
	performance: 1.1 GFLOPS/s
	bandwidth: 0.3 GB/s
	duration: 0.9 s
Inlined...
	performance: 80.5 GFLOPS/s
	bandwidth: 24.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 219.1 GFLOPS/s
	bandwidth: 66.4 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 281.3 GFLOPS/s
	bandwidth: 85.3 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=24 n=26 k=13 ldc=24 (column-major) size=105351 batch=265 memory=1024 MB

LAPACK/BLAS...
	performance: 1.9 GFLOPS/s
	bandwidth: 0.6 GB/s
	duration: 0.9 s
Inlined...
	performance: 94.0 GFLOPS/s
	bandwidth: 28.3 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 251.3 GFLOPS/s
	bandwidth: 75.6 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 281.0 GFLOPS/s
	bandwidth: 84.5 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=24 n=26 k=24 ldc=24 (column-major) size=73584 batch=221 memory=1024 MB

LAPACK/BLAS...
	performance: 2.4 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 91.9 GFLOPS/s
	bandwidth: 27.6 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 260.1 GFLOPS/s
	bandwidth: 78.0 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 277.1 GFLOPS/s
	bandwidth: 83.1 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=24 n=26 k=26 ldc=24 (column-major) size=69759 batch=216 memory=1024 MB

LAPACK/BLAS...
	performance: 2.6 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 90.3 GFLOPS/s
	bandwidth: 27.1 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 243.6 GFLOPS/s
	bandwidth: 73.0 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 255.7 GFLOPS/s
	bandwidth: 76.7 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=24 n=26 k=32 ldc=24 (column-major) size=60349 batch=201 memory=1024 MB

LAPACK/BLAS...
	performance: 2.7 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 88.9 GFLOPS/s
	bandwidth: 26.6 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 242.2 GFLOPS/s
	bandwidth: 72.6 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 251.7 GFLOPS/s
	bandwidth: 75.4 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=24 n=32 k=5 ldc=24 (column-major) size=128070 batch=292 memory=1024 MB

LAPACK/BLAS...
	performance: 1.2 GFLOPS/s
	bandwidth: 0.3 GB/s
	duration: 0.8 s
Inlined...
	performance: 75.1 GFLOPS/s
	bandwidth: 20.8 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 207.7 GFLOPS/s
	bandwidth: 57.5 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 267.7 GFLOPS/s
	bandwidth: 74.1 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=24 n=32 k=13 ldc=24 (column-major) size=89717 batch=245 memory=1024 MB

LAPACK/BLAS...
	performance: 2.1 GFLOPS/s
	bandwidth: 0.6 GB/s
	duration: 0.8 s
Inlined...
	performance: 86.7 GFLOPS/s
	bandwidth: 23.8 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 253.0 GFLOPS/s
	bandwidth: 69.3 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 279.5 GFLOPS/s
	bandwidth: 76.6 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=24 n=32 k=24 ldc=24 (column-major) size=63550 batch=206 memory=1024 MB

LAPACK/BLAS...
	performance: 2.6 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 87.0 GFLOPS/s
	bandwidth: 23.8 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 256.2 GFLOPS/s
	bandwidth: 70.0 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 271.0 GFLOPS/s
	bandwidth: 74.0 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=24 n=32 k=26 ldc=24 (column-major) size=60349 batch=201 memory=1024 MB

LAPACK/BLAS...
	performance: 2.8 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 88.1 GFLOPS/s
	bandwidth: 24.1 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 236.5 GFLOPS/s
	bandwidth: 64.6 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 249.2 GFLOPS/s
	bandwidth: 68.0 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=24 n=32 k=32 ldc=24 (column-major) size=52428 batch=187 memory=1024 MB

LAPACK/BLAS...
	performance: 2.9 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 83.3 GFLOPS/s
	bandwidth: 22.7 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 242.2 GFLOPS/s
	bandwidth: 66.1 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 250.8 GFLOPS/s
	bandwidth: 68.4 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=5 k=5 ldc=32 (column-major) size=426088 batch=533 memory=1024 MB

LAPACK/BLAS...
	performance: 6.9 GFLOPS/s
	bandwidth: 6.2 GB/s
	duration: 0.1 s
Inlined...
	performance: 58.2 GFLOPS/s
	bandwidth: 51.9 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 90.6 GFLOPS/s
	bandwidth: 80.8 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 125.1 GFLOPS/s
	bandwidth: 111.5 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=5 k=13 ldc=32 (column-major) size=238397 batch=399 memory=1024 MB

LAPACK/BLAS...
	performance: 8.0 GFLOPS/s
	bandwidth: 7.1 GB/s
	duration: 0.1 s
Inlined...
	performance: 81.1 GFLOPS/s
	bandwidth: 72.1 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 111.3 GFLOPS/s
	bandwidth: 99.1 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 121.5 GFLOPS/s
	bandwidth: 108.1 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=5 k=24 ldc=32 (column-major) size=148470 batch=315 memory=1024 MB

LAPACK/BLAS...
	performance: 8.2 GFLOPS/s
	bandwidth: 7.3 GB/s
	duration: 0.1 s
Inlined...
	performance: 82.0 GFLOPS/s
	bandwidth: 73.0 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 115.4 GFLOPS/s
	bandwidth: 102.7 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 121.2 GFLOPS/s
	bandwidth: 107.9 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=5 k=26 ldc=32 (column-major) size=138941 batch=304 memory=1024 MB

LAPACK/BLAS...
	performance: 8.6 GFLOPS/s
	bandwidth: 7.6 GB/s
	duration: 0.1 s
Inlined...
	performance: 86.1 GFLOPS/s
	bandwidth: 76.6 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 110.1 GFLOPS/s
	bandwidth: 97.9 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 118.6 GFLOPS/s
	bandwidth: 105.5 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=5 k=32 ldc=32 (column-major) size=116508 batch=279 memory=1024 MB

LAPACK/BLAS...
	performance: 8.1 GFLOPS/s
	bandwidth: 7.2 GB/s
	duration: 0.1 s
Inlined...
	performance: 59.8 GFLOPS/s
	bandwidth: 53.2 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 105.5 GFLOPS/s
	bandwidth: 93.8 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 111.3 GFLOPS/s
	bandwidth: 99.0 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=13 k=5 ldc=32 (column-major) size=219668 batch=383 memory=1024 MB

LAPACK/BLAS...
	performance: 11.4 GFLOPS/s
	bandwidth: 4.9 GB/s
	duration: 0.1 s
Inlined...
	performance: 72.7 GFLOPS/s
	bandwidth: 31.6 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 159.2 GFLOPS/s
	bandwidth: 69.2 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 204.4 GFLOPS/s
	bandwidth: 88.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=13 k=13 ldc=32 (column-major) size=145414 batch=311 memory=1024 MB

LAPACK/BLAS...
	performance: 14.6 GFLOPS/s
	bandwidth: 6.3 GB/s
	duration: 0.1 s
Inlined...
	performance: 100.9 GFLOPS/s
	bandwidth: 43.6 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 211.9 GFLOPS/s
	bandwidth: 91.6 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 239.7 GFLOPS/s
	bandwidth: 103.6 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=13 k=24 ldc=32 (column-major) size=99273 batch=257 memory=1024 MB

LAPACK/BLAS...
	performance: 14.8 GFLOPS/s
	bandwidth: 6.4 GB/s
	duration: 0.1 s
Inlined...
	performance: 99.2 GFLOPS/s
	bandwidth: 42.8 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 198.3 GFLOPS/s
	bandwidth: 85.5 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 199.8 GFLOPS/s
	bandwidth: 86.2 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=13 k=26 ldc=32 (column-major) size=93858 batch=250 memory=1024 MB

LAPACK/BLAS...
	performance: 15.6 GFLOPS/s
	bandwidth: 6.7 GB/s
	duration: 0.1 s
Inlined...
	performance: 97.8 GFLOPS/s
	bandwidth: 42.2 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 190.3 GFLOPS/s
	bandwidth: 82.1 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 200.5 GFLOPS/s
	bandwidth: 86.5 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=13 k=28 ldc=32 (column-major) size=89003 batch=244 memory=1024 MB

LAPACK/BLAS...
	performance: 15.4 GFLOPS/s
	bandwidth: 6.6 GB/s
	duration: 0.1 s
Inlined...
	performance: 99.5 GFLOPS/s
	bandwidth: 42.9 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 187.8 GFLOPS/s
	bandwidth: 81.0 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 198.5 GFLOPS/s
	bandwidth: 85.6 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=13 k=32 ldc=32 (column-major) size=80659 batch=232 memory=1024 MB

LAPACK/BLAS...
	performance: 15.8 GFLOPS/s
	bandwidth: 6.8 GB/s
	duration: 0.1 s
Inlined...
	performance: 92.9 GFLOPS/s
	bandwidth: 40.1 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 180.3 GFLOPS/s
	bandwidth: 77.7 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 192.0 GFLOPS/s
	bandwidth: 82.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=13 k=45 ldc=32 (column-major) size=61822 batch=203 memory=1024 MB

LAPACK/BLAS...
	performance: 16.4 GFLOPS/s
	bandwidth: 7.1 GB/s
	duration: 0.1 s
Inlined...
	performance: 80.2 GFLOPS/s
	bandwidth: 34.5 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 148.9 GFLOPS/s
	bandwidth: 64.2 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 152.7 GFLOPS/s
	bandwidth: 65.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=24 k=5 ldc=32 (column-major) size=131844 batch=296 memory=1024 MB

LAPACK/BLAS...
	performance: 1.0 GFLOPS/s
	bandwidth: 0.3 GB/s
	duration: 0.8 s
Inlined...
	performance: 76.1 GFLOPS/s
	bandwidth: 23.2 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 183.1 GFLOPS/s
	bandwidth: 55.8 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 222.5 GFLOPS/s
	bandwidth: 67.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=24 k=13 ldc=32 (column-major) size=94652 batch=251 memory=1024 MB

LAPACK/BLAS...
	performance: 1.8 GFLOPS/s
	bandwidth: 0.5 GB/s
	duration: 0.9 s
Inlined...
	performance: 92.1 GFLOPS/s
	bandwidth: 27.7 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 213.7 GFLOPS/s
	bandwidth: 64.4 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 263.5 GFLOPS/s
	bandwidth: 79.4 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=24 k=24 ldc=32 (column-major) size=68200 batch=213 memory=1024 MB

LAPACK/BLAS...
	performance: 2.3 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 92.5 GFLOPS/s
	bandwidth: 27.8 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 212.0 GFLOPS/s
	bandwidth: 63.7 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 228.6 GFLOPS/s
	bandwidth: 68.6 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=24 k=26 ldc=32 (column-major) size=64902 batch=208 memory=1024 MB

LAPACK/BLAS...
	performance: 2.3 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 93.8 GFLOPS/s
	bandwidth: 28.2 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 206.4 GFLOPS/s
	bandwidth: 62.0 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 222.1 GFLOPS/s
	bandwidth: 66.7 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=24 k=32 ldc=32 (column-major) size=56679 batch=194 memory=1024 MB

LAPACK/BLAS...
	performance: 2.6 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 88.5 GFLOPS/s
	bandwidth: 26.5 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 201.2 GFLOPS/s
	bandwidth: 60.4 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 209.5 GFLOPS/s
	bandwidth: 62.9 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=26 k=5 ldc=32 (column-major) size=122910 batch=286 memory=1024 MB

LAPACK/BLAS...
	performance: 1.0 GFLOPS/s
	bandwidth: 0.3 GB/s
	duration: 0.8 s
Inlined...
	performance: 70.7 GFLOPS/s
	bandwidth: 20.7 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 166.9 GFLOPS/s
	bandwidth: 48.9 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 229.3 GFLOPS/s
	bandwidth: 67.2 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=26 k=13 ldc=32 (column-major) size=89003 batch=244 memory=1024 MB

LAPACK/BLAS...
	performance: 1.8 GFLOPS/s
	bandwidth: 0.5 GB/s
	duration: 0.9 s
Inlined...
	performance: 94.3 GFLOPS/s
	bandwidth: 27.3 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 219.4 GFLOPS/s
	bandwidth: 63.5 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 252.0 GFLOPS/s
	bandwidth: 72.9 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=26 k=24 ldc=32 (column-major) size=64527 batch=207 memory=1024 MB

LAPACK/BLAS...
	performance: 2.3 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 90.7 GFLOPS/s
	bandwidth: 26.2 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 217.2 GFLOPS/s
	bandwidth: 62.7 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 224.2 GFLOPS/s
	bandwidth: 64.7 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=26 k=26 ldc=32 (column-major) size=61455 batch=202 memory=1024 MB

LAPACK/BLAS...
	performance: 2.4 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 91.9 GFLOPS/s
	bandwidth: 26.5 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 207.4 GFLOPS/s
	bandwidth: 59.8 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 217.7 GFLOPS/s
	bandwidth: 62.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=26 k=28 ldc=32 (column-major) size=58661 batch=198 memory=1024 MB

LAPACK/BLAS...
	performance: 2.4 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 91.4 GFLOPS/s
	bandwidth: 26.3 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 202.3 GFLOPS/s
	bandwidth: 58.3 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 211.8 GFLOPS/s
	bandwidth: 61.0 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=26 k=32 ldc=32 (column-major) size=53773 batch=189 memory=1024 MB

LAPACK/BLAS...
	performance: 2.6 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 87.0 GFLOPS/s
	bandwidth: 25.1 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 205.7 GFLOPS/s
	bandwidth: 59.3 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 210.1 GFLOPS/s
	bandwidth: 60.5 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=26 k=45 ldc=32 (column-major) size=42313 batch=168 memory=1024 MB

LAPACK/BLAS...
	performance: 2.8 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 74.2 GFLOPS/s
	bandwidth: 21.3 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 156.2 GFLOPS/s
	bandwidth: 45.0 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 159.8 GFLOPS/s
	bandwidth: 46.0 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=28 k=13 ldc=32 (column-major) size=83991 batch=237 memory=1024 MB

LAPACK/BLAS...
	performance: 1.8 GFLOPS/s
	bandwidth: 0.5 GB/s
	duration: 0.9 s
Inlined...
	performance: 91.7 GFLOPS/s
	bandwidth: 25.6 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 245.2 GFLOPS/s
	bandwidth: 68.5 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 248.6 GFLOPS/s
	bandwidth: 69.4 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=28 k=26 ldc=32 (column-major) size=58355 batch=197 memory=1024 MB

LAPACK/BLAS...
	performance: 2.5 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 92.3 GFLOPS/s
	bandwidth: 25.7 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 206.0 GFLOPS/s
	bandwidth: 57.3 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 214.5 GFLOPS/s
	bandwidth: 59.7 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=28 k=28 ldc=32 (column-major) size=55738 batch=193 memory=1024 MB

LAPACK/BLAS...
	performance: 2.6 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 88.2 GFLOPS/s
	bandwidth: 24.5 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 202.1 GFLOPS/s
	bandwidth: 56.2 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 208.4 GFLOPS/s
	bandwidth: 57.9 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=28 k=32 ldc=32 (column-major) size=51150 batch=185 memory=1024 MB

LAPACK/BLAS...
	performance: 2.6 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 87.5 GFLOPS/s
	bandwidth: 24.3 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 194.9 GFLOPS/s
	bandwidth: 54.1 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 204.4 GFLOPS/s
	bandwidth: 56.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=28 k=45 ldc=32 (column-major) size=40354 batch=164 memory=1024 MB

LAPACK/BLAS...
	performance: 2.9 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 71.7 GFLOPS/s
	bandwidth: 19.9 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 151.0 GFLOPS/s
	bandwidth: 41.9 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 158.4 GFLOPS/s
	bandwidth: 44.0 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=32 k=5 ldc=32 (column-major) size=102144 batch=261 memory=1024 MB

LAPACK/BLAS...
	performance: 1.1 GFLOPS/s
	bandwidth: 0.3 GB/s
	duration: 0.8 s
Inlined...
	performance: 73.5 GFLOPS/s
	bandwidth: 19.6 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 181.2 GFLOPS/s
	bandwidth: 48.3 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 214.9 GFLOPS/s
	bandwidth: 57.3 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=32 k=13 ldc=32 (column-major) size=75488 batch=224 memory=1024 MB

LAPACK/BLAS...
	performance: 1.9 GFLOPS/s
	bandwidth: 0.5 GB/s
	duration: 0.8 s
Inlined...
	performance: 90.5 GFLOPS/s
	bandwidth: 23.8 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 227.5 GFLOPS/s
	bandwidth: 59.8 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 246.9 GFLOPS/s
	bandwidth: 64.9 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=32 k=24 ldc=32 (column-major) size=55553 batch=192 memory=1024 MB

LAPACK/BLAS...
	performance: 2.6 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.8 s
Inlined...
	performance: 87.9 GFLOPS/s
	bandwidth: 23.0 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 216.8 GFLOPS/s
	bandwidth: 56.7 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 225.8 GFLOPS/s
	bandwidth: 59.1 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=32 k=26 ldc=32 (column-major) size=53008 batch=188 memory=1024 MB

LAPACK/BLAS...
	performance: 2.6 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 86.9 GFLOPS/s
	bandwidth: 22.7 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 205.6 GFLOPS/s
	bandwidth: 53.8 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 216.9 GFLOPS/s
	bandwidth: 56.7 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=32 k=28 ldc=32 (column-major) size=50686 batch=184 memory=1024 MB

LAPACK/BLAS...
	performance: 2.7 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 87.1 GFLOPS/s
	bandwidth: 22.8 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 202.2 GFLOPS/s
	bandwidth: 52.9 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 211.6 GFLOPS/s
	bandwidth: 55.3 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=32 k=32 ldc=32 (column-major) size=46603 batch=176 memory=1024 MB

LAPACK/BLAS...
	performance: 2.7 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 80.3 GFLOPS/s
	bandwidth: 21.0 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 202.6 GFLOPS/s
	bandwidth: 53.0 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 206.8 GFLOPS/s
	bandwidth: 54.0 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=32 k=45 ldc=32 (column-major) size=36933 batch=157 memory=1024 MB

LAPACK/BLAS...
	performance: 3.2 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 106.2 GFLOPS/s
	bandwidth: 27.7 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 252.0 GFLOPS/s
	bandwidth: 65.8 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 260.3 GFLOPS/s
	bandwidth: 67.9 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=45 k=13 ldc=32 (column-major) size=56799 batch=195 memory=1024 MB

LAPACK/BLAS...
	performance: 2.0 GFLOPS/s
	bandwidth: 0.5 GB/s
	duration: 0.8 s
Inlined...
	performance: 83.7 GFLOPS/s
	bandwidth: 19.2 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 221.3 GFLOPS/s
	bandwidth: 50.8 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 230.0 GFLOPS/s
	bandwidth: 52.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=45 k=26 ldc=32 (column-major) size=40845 batch=165 memory=1024 MB

LAPACK/BLAS...
	performance: 2.8 GFLOPS/s
	bandwidth: 0.6 GB/s
	duration: 0.9 s
Inlined...
	performance: 79.8 GFLOPS/s
	bandwidth: 18.2 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 199.6 GFLOPS/s
	bandwidth: 45.6 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 198.6 GFLOPS/s
	bandwidth: 45.3 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=45 k=28 ldc=32 (column-major) size=39153 batch=162 memory=1024 MB

LAPACK/BLAS...
	performance: 2.9 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 79.9 GFLOPS/s
	bandwidth: 18.2 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 193.6 GFLOPS/s
	bandwidth: 44.2 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 206.1 GFLOPS/s
	bandwidth: 47.0 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=45 k=32 ldc=32 (column-major) size=36157 batch=155 memory=1024 MB

LAPACK/BLAS...
	performance: 3.1 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 121.0 GFLOPS/s
	bandwidth: 27.6 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 288.9 GFLOPS/s
	bandwidth: 65.8 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 299.1 GFLOPS/s
	bandwidth: 68.2 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=26 n=45 k=45 ldc=32 (column-major) size=28957 batch=139 memory=1024 MB

LAPACK/BLAS...
	performance: 4.1 GFLOPS/s
	bandwidth: 0.9 GB/s
	duration: 0.7 s
Inlined...
	performance: 96.7 GFLOPS/s
	bandwidth: 22.0 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 226.9 GFLOPS/s
	bandwidth: 51.6 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 239.1 GFLOPS/s
	bandwidth: 54.4 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=28 n=13 k=13 ldc=32 (column-major) size=141430 batch=307 memory=1024 MB

LAPACK/BLAS...
	performance: 14.9 GFLOPS/s
	bandwidth: 6.3 GB/s
	duration: 0.1 s
Inlined...
	performance: 104.0 GFLOPS/s
	bandwidth: 43.8 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 209.1 GFLOPS/s
	bandwidth: 88.2 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 237.3 GFLOPS/s
	bandwidth: 100.1 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=28 n=13 k=26 ldc=32 (column-major) size=90565 batch=246 memory=1024 MB

LAPACK/BLAS...
	performance: 15.2 GFLOPS/s
	bandwidth: 6.4 GB/s
	duration: 0.1 s
Inlined...
	performance: 105.7 GFLOPS/s
	bandwidth: 44.5 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 178.1 GFLOPS/s
	bandwidth: 75.0 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 191.7 GFLOPS/s
	bandwidth: 80.7 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=28 n=13 k=28 ldc=32 (column-major) size=85816 batch=239 memory=1024 MB

LAPACK/BLAS...
	performance: 15.8 GFLOPS/s
	bandwidth: 6.6 GB/s
	duration: 0.1 s
Inlined...
	performance: 107.1 GFLOPS/s
	bandwidth: 45.1 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 179.3 GFLOPS/s
	bandwidth: 75.5 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 188.8 GFLOPS/s
	bandwidth: 79.4 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=28 n=13 k=32 ldc=32 (column-major) size=77672 batch=228 memory=1024 MB

LAPACK/BLAS...
	performance: 16.8 GFLOPS/s
	bandwidth: 7.1 GB/s
	duration: 0.1 s
Inlined...
	performance: 99.9 GFLOPS/s
	bandwidth: 42.0 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 176.8 GFLOPS/s
	bandwidth: 74.4 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 186.9 GFLOPS/s
	bandwidth: 78.6 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=28 n=13 k=45 ldc=32 (column-major) size=59362 batch=199 memory=1024 MB

LAPACK/BLAS...
	performance: 16.5 GFLOPS/s
	bandwidth: 7.0 GB/s
	duration: 0.1 s
Inlined...
	performance: 87.9 GFLOPS/s
	bandwidth: 37.0 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 147.9 GFLOPS/s
	bandwidth: 62.2 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 151.6 GFLOPS/s
	bandwidth: 63.7 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=28 n=26 k=13 ldc=32 (column-major) size=87495 batch=242 memory=1024 MB

LAPACK/BLAS...
	performance: 1.9 GFLOPS/s
	bandwidth: 0.5 GB/s
	duration: 0.9 s
Inlined...
	performance: 99.5 GFLOPS/s
	bandwidth: 27.8 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 242.7 GFLOPS/s
	bandwidth: 67.7 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 249.9 GFLOPS/s
	bandwidth: 69.7 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=28 n=26 k=26 ldc=32 (column-major) size=60025 batch=200 memory=1024 MB

LAPACK/BLAS...
	performance: 2.5 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 99.3 GFLOPS/s
	bandwidth: 27.6 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 210.3 GFLOPS/s
	bandwidth: 58.5 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 216.3 GFLOPS/s
	bandwidth: 60.1 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=28 n=26 k=28 ldc=32 (column-major) size=57260 batch=195 memory=1024 MB

LAPACK/BLAS...
	performance: 2.6 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 98.0 GFLOPS/s
	bandwidth: 27.2 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 205.2 GFLOPS/s
	bandwidth: 57.0 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 215.4 GFLOPS/s
	bandwidth: 59.9 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=28 n=26 k=32 ldc=32 (column-major) size=52428 batch=187 memory=1024 MB

LAPACK/BLAS...
	performance: 2.7 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 94.9 GFLOPS/s
	bandwidth: 26.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 201.0 GFLOPS/s
	bandwidth: 55.8 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 210.5 GFLOPS/s
	bandwidth: 58.5 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=28 n=26 k=45 ldc=32 (column-major) size=41145 batch=166 memory=1024 MB

LAPACK/BLAS...
	performance: 2.9 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 80.1 GFLOPS/s
	bandwidth: 22.2 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 158.0 GFLOPS/s
	bandwidth: 43.8 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 162.5 GFLOPS/s
	bandwidth: 45.1 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=28 n=28 k=13 ldc=32 (column-major) size=82646 batch=235 memory=1024 MB

LAPACK/BLAS...
	performance: 1.9 GFLOPS/s
	bandwidth: 0.5 GB/s
	duration: 0.9 s
Inlined...
	performance: 96.6 GFLOPS/s
	bandwidth: 26.0 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 233.7 GFLOPS/s
	bandwidth: 62.8 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 251.8 GFLOPS/s
	bandwidth: 67.7 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=28 n=28 k=26 ldc=32 (column-major) size=57065 batch=195 memory=1024 MB

LAPACK/BLAS...
	performance: 2.6 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 98.4 GFLOPS/s
	bandwidth: 26.3 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 211.9 GFLOPS/s
	bandwidth: 56.7 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 219.8 GFLOPS/s
	bandwidth: 58.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=28 n=28 k=28 ldc=32 (column-major) size=54471 batch=191 memory=1024 MB

LAPACK/BLAS...
	performance: 2.6 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 97.0 GFLOPS/s
	bandwidth: 26.0 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 196.9 GFLOPS/s
	bandwidth: 52.7 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 208.3 GFLOPS/s
	bandwidth: 55.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=28 n=28 k=32 ldc=32 (column-major) size=49932 batch=182 memory=1024 MB

LAPACK/BLAS...
	performance: 2.8 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 92.5 GFLOPS/s
	bandwidth: 24.8 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 200.9 GFLOPS/s
	bandwidth: 53.8 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 207.7 GFLOPS/s
	bandwidth: 55.6 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=28 n=28 k=45 ldc=32 (column-major) size=39290 batch=162 memory=1024 MB

LAPACK/BLAS...
	performance: 3.0 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 79.7 GFLOPS/s
	bandwidth: 21.3 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 157.6 GFLOPS/s
	bandwidth: 42.1 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 162.7 GFLOPS/s
	bandwidth: 43.5 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=28 n=32 k=13 ldc=32 (column-major) size=74400 batch=223 memory=1024 MB

LAPACK/BLAS...
	performance: 2.1 GFLOPS/s
	bandwidth: 0.5 GB/s
	duration: 0.8 s
Inlined...
	performance: 97.0 GFLOPS/s
	bandwidth: 24.5 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 236.2 GFLOPS/s
	bandwidth: 59.6 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 253.9 GFLOPS/s
	bandwidth: 64.1 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=28 n=32 k=26 ldc=32 (column-major) size=51941 batch=186 memory=1024 MB

LAPACK/BLAS...
	performance: 2.7 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 94.7 GFLOPS/s
	bandwidth: 23.8 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 210.0 GFLOPS/s
	bandwidth: 52.8 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 219.6 GFLOPS/s
	bandwidth: 55.2 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=28 n=32 k=28 ldc=32 (column-major) size=49636 batch=182 memory=1024 MB

LAPACK/BLAS...
	performance: 2.8 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 91.6 GFLOPS/s
	bandwidth: 23.0 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 208.2 GFLOPS/s
	bandwidth: 52.3 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 216.2 GFLOPS/s
	bandwidth: 54.3 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=28 n=32 k=32 ldc=32 (column-major) size=45590 batch=174 memory=1024 MB

LAPACK/BLAS...
	performance: 2.9 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 89.7 GFLOPS/s
	bandwidth: 22.5 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 204.6 GFLOPS/s
	bandwidth: 51.4 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 210.4 GFLOPS/s
	bandwidth: 52.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=28 n=32 k=45 ldc=32 (column-major) size=36041 batch=155 memory=1024 MB

LAPACK/BLAS...
	performance: 3.3 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 125.2 GFLOPS/s
	bandwidth: 31.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 269.0 GFLOPS/s
	bandwidth: 67.4 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 273.6 GFLOPS/s
	bandwidth: 68.6 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=28 n=45 k=13 ldc=32 (column-major) size=56181 batch=194 memory=1024 MB

LAPACK/BLAS...
	performance: 2.1 GFLOPS/s
	bandwidth: 0.5 GB/s
	duration: 0.9 s
Inlined...
	performance: 89.3 GFLOPS/s
	bandwidth: 19.6 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 220.9 GFLOPS/s
	bandwidth: 48.4 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 244.3 GFLOPS/s
	bandwidth: 53.6 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=28 n=45 k=26 ldc=32 (column-major) size=40209 batch=164 memory=1024 MB

LAPACK/BLAS...
	performance: 2.9 GFLOPS/s
	bandwidth: 0.6 GB/s
	duration: 0.9 s
Inlined...
	performance: 86.0 GFLOPS/s
	bandwidth: 18.7 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 203.4 GFLOPS/s
	bandwidth: 44.3 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 211.7 GFLOPS/s
	bandwidth: 46.1 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=28 n=45 k=28 ldc=32 (column-major) size=38524 batch=160 memory=1024 MB

LAPACK/BLAS...
	performance: 3.0 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 94.8 GFLOPS/s
	bandwidth: 20.6 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 224.5 GFLOPS/s
	bandwidth: 48.9 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 239.9 GFLOPS/s
	bandwidth: 52.2 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=28 n=45 k=32 ldc=32 (column-major) size=35544 batch=154 memory=1024 MB

LAPACK/BLAS...
	performance: 3.3 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 129.1 GFLOPS/s
	bandwidth: 28.1 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 304.0 GFLOPS/s
	bandwidth: 66.1 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 327.2 GFLOPS/s
	bandwidth: 71.2 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=28 n=45 k=45 ldc=32 (column-major) size=28405 batch=138 memory=1024 MB

LAPACK/BLAS...
	performance: 4.4 GFLOPS/s
	bandwidth: 1.0 GB/s
	duration: 0.7 s
Inlined...
	performance: 110.5 GFLOPS/s
	bandwidth: 24.0 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 246.7 GFLOPS/s
	bandwidth: 53.6 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 249.4 GFLOPS/s
	bandwidth: 54.2 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=29 n=14 k=14 ldc=32 (column-major) size=127826 batch=292 memory=1024 MB

LAPACK/BLAS...
	performance: 15.2 GFLOPS/s
	bandwidth: 6.0 GB/s
	duration: 0.1 s
Inlined...
	performance: 112.3 GFLOPS/s
	bandwidth: 44.5 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 224.1 GFLOPS/s
	bandwidth: 88.9 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 255.9 GFLOPS/s
	bandwidth: 101.5 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=29 n=14 k=16 ldc=32 (column-major) size=118149 batch=281 memory=1024 MB

LAPACK/BLAS...
	performance: 16.5 GFLOPS/s
	bandwidth: 6.5 GB/s
	duration: 0.1 s
Inlined...
	performance: 113.2 GFLOPS/s
	bandwidth: 44.9 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 218.3 GFLOPS/s
	bandwidth: 86.5 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 234.4 GFLOPS/s
	bandwidth: 92.9 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=29 n=14 k=29 ldc=32 (column-major) size=79184 batch=230 memory=1024 MB

LAPACK/BLAS...
	performance: 16.9 GFLOPS/s
	bandwidth: 6.7 GB/s
	duration: 0.1 s
Inlined...
	performance: 105.1 GFLOPS/s
	bandwidth: 41.6 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 193.3 GFLOPS/s
	bandwidth: 76.5 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 203.4 GFLOPS/s
	bandwidth: 80.5 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=29 n=14 k=32 ldc=32 (column-major) size=73584 batch=221 memory=1024 MB

LAPACK/BLAS...
	performance: 17.1 GFLOPS/s
	bandwidth: 6.8 GB/s
	duration: 0.1 s
Inlined...
	performance: 100.4 GFLOPS/s
	bandwidth: 39.7 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 186.7 GFLOPS/s
	bandwidth: 73.9 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 196.5 GFLOPS/s
	bandwidth: 77.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=29 n=16 k=14 ldc=32 (column-major) size=117528 batch=280 memory=1024 MB

LAPACK/BLAS...
	performance: 1.7 GFLOPS/s
	bandwidth: 0.6 GB/s
	duration: 0.9 s
Inlined...
	performance: 105.9 GFLOPS/s
	bandwidth: 38.5 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 231.8 GFLOPS/s
	bandwidth: 84.2 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 264.6 GFLOPS/s
	bandwidth: 96.2 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=29 n=16 k=16 ldc=32 (column-major) size=108942 batch=269 memory=1024 MB

LAPACK/BLAS...
	performance: 1.8 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 112.6 GFLOPS/s
	bandwidth: 40.9 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 226.6 GFLOPS/s
	bandwidth: 82.3 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 236.8 GFLOPS/s
	bandwidth: 86.0 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=29 n=16 k=29 ldc=32 (column-major) size=73867 batch=222 memory=1024 MB

LAPACK/BLAS...
	performance: 2.2 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 99.9 GFLOPS/s
	bandwidth: 36.2 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 197.6 GFLOPS/s
	bandwidth: 71.7 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 207.9 GFLOPS/s
	bandwidth: 75.4 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=29 n=16 k=55 ldc=32 (column-major) size=44933 batch=173 memory=1024 MB

LAPACK/BLAS...
	performance: 2.5 GFLOPS/s
	bandwidth: 0.9 GB/s
	duration: 0.9 s
Inlined...
	performance: 73.5 GFLOPS/s
	bandwidth: 26.6 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 147.9 GFLOPS/s
	bandwidth: 53.5 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 154.0 GFLOPS/s
	bandwidth: 55.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=29 n=29 k=14 ldc=32 (column-major) size=77136 batch=227 memory=1024 MB

LAPACK/BLAS...
	performance: 2.1 GFLOPS/s
	bandwidth: 0.5 GB/s
	duration: 0.9 s
Inlined...
	performance: 95.5 GFLOPS/s
	bandwidth: 24.8 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 240.1 GFLOPS/s
	bandwidth: 62.3 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 256.0 GFLOPS/s
	bandwidth: 66.4 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=29 n=29 k=16 ldc=32 (column-major) size=72315 batch=220 memory=1024 MB

LAPACK/BLAS...
	performance: 2.3 GFLOPS/s
	bandwidth: 0.6 GB/s
	duration: 0.9 s
Inlined...
	performance: 90.8 GFLOPS/s
	bandwidth: 23.6 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 236.6 GFLOPS/s
	bandwidth: 61.3 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 253.1 GFLOPS/s
	bandwidth: 65.6 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=29 n=29 k=29 ldc=32 (column-major) size=51424 batch=185 memory=1024 MB

LAPACK/BLAS...
	performance: 2.7 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 97.4 GFLOPS/s
	bandwidth: 25.2 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 211.8 GFLOPS/s
	bandwidth: 54.7 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 221.5 GFLOPS/s
	bandwidth: 57.2 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=29 n=29 k=32 ldc=32 (column-major) size=48210 batch=179 memory=1024 MB

LAPACK/BLAS...
	performance: 2.9 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 91.3 GFLOPS/s
	bandwidth: 23.6 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 208.1 GFLOPS/s
	bandwidth: 53.8 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 217.5 GFLOPS/s
	bandwidth: 56.2 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=29 n=29 k=55 ldc=32 (column-major) size=32592 batch=147 memory=1024 MB

LAPACK/BLAS...
	performance: 3.6 GFLOPS/s
	bandwidth: 0.9 GB/s
	duration: 0.8 s
Inlined...
	performance: 97.4 GFLOPS/s
	bandwidth: 25.1 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 260.7 GFLOPS/s
	bandwidth: 67.2 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 262.6 GFLOPS/s
	bandwidth: 67.7 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=29 n=32 k=14 ldc=32 (column-major) size=71468 batch=218 memory=1024 MB

LAPACK/BLAS...
	performance: 2.2 GFLOPS/s
	bandwidth: 0.5 GB/s
	duration: 0.9 s
Inlined...
	performance: 98.8 GFLOPS/s
	bandwidth: 24.5 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 247.1 GFLOPS/s
	bandwidth: 61.2 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 264.7 GFLOPS/s
	bandwidth: 65.5 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=29 n=32 k=29 ldc=32 (column-major) size=48055 batch=179 memory=1024 MB

LAPACK/BLAS...
	performance: 2.9 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 94.4 GFLOPS/s
	bandwidth: 23.3 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 209.7 GFLOPS/s
	bandwidth: 51.7 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 216.6 GFLOPS/s
	bandwidth: 53.4 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=29 n=32 k=32 ldc=32 (column-major) size=45100 batch=173 memory=1024 MB

LAPACK/BLAS...
	performance: 3.0 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 89.8 GFLOPS/s
	bandwidth: 22.1 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 206.4 GFLOPS/s
	bandwidth: 50.9 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 217.3 GFLOPS/s
	bandwidth: 53.5 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=29 n=32 k=55 ldc=32 (column-major) size=30650 batch=143 memory=1024 MB

LAPACK/BLAS...
	performance: 4.0 GFLOPS/s
	bandwidth: 1.0 GB/s
	duration: 0.8 s
Inlined...
	performance: 94.8 GFLOPS/s
	bandwidth: 23.3 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 243.0 GFLOPS/s
	bandwidth: 59.8 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 246.6 GFLOPS/s
	bandwidth: 60.6 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=29 n=55 k=16 ldc=32 (column-major) size=43240 batch=170 memory=1024 MB

LAPACK/BLAS...
	performance: 2.6 GFLOPS/s
	bandwidth: 0.5 GB/s
	duration: 0.8 s
Inlined...
	performance: 73.9 GFLOPS/s
	bandwidth: 14.7 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 220.8 GFLOPS/s
	bandwidth: 44.0 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 225.4 GFLOPS/s
	bandwidth: 44.9 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=29 n=55 k=29 ldc=32 (column-major) size=31987 batch=146 memory=1024 MB

LAPACK/BLAS...
	performance: 3.9 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.8 s
Inlined...
	performance: 132.7 GFLOPS/s
	bandwidth: 26.3 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 290.4 GFLOPS/s
	bandwidth: 57.5 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 300.6 GFLOPS/s
	bandwidth: 59.6 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=29 n=55 k=32 ldc=32 (column-major) size=30174 batch=142 memory=1024 MB

LAPACK/BLAS...
	performance: 4.1 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.8 s
Inlined...
	performance: 125.2 GFLOPS/s
	bandwidth: 24.8 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 293.8 GFLOPS/s
	bandwidth: 58.2 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 297.6 GFLOPS/s
	bandwidth: 58.9 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=29 n=55 k=55 ldc=32 (column-major) size=21037 batch=118 memory=1024 MB

LAPACK/BLAS...
	performance: 5.8 GFLOPS/s
	bandwidth: 1.1 GB/s
	duration: 0.6 s
Inlined...
	performance: 105.8 GFLOPS/s
	bandwidth: 20.9 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 240.0 GFLOPS/s
	bandwidth: 47.4 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 243.6 GFLOPS/s
	bandwidth: 48.1 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=5 k=5 ldc=32 (column-major) size=389036 batch=509 memory=1024 MB

LAPACK/BLAS...
	performance: 7.5 GFLOPS/s
	bandwidth: 6.5 GB/s
	duration: 0.1 s
Inlined...
	performance: 81.0 GFLOPS/s
	bandwidth: 70.0 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 95.2 GFLOPS/s
	bandwidth: 82.3 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 123.4 GFLOPS/s
	bandwidth: 106.6 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=5 k=13 ldc=32 (column-major) size=209388 batch=374 memory=1024 MB

LAPACK/BLAS...
	performance: 8.2 GFLOPS/s
	bandwidth: 7.1 GB/s
	duration: 0.1 s
Inlined...
	performance: 85.8 GFLOPS/s
	bandwidth: 74.1 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 93.9 GFLOPS/s
	bandwidth: 81.0 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 104.2 GFLOPS/s
	bandwidth: 89.9 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=5 k=24 ldc=32 (column-major) size=128070 batch=292 memory=1024 MB

LAPACK/BLAS...
	performance: 8.4 GFLOPS/s
	bandwidth: 7.2 GB/s
	duration: 0.1 s
Inlined...
	performance: 89.6 GFLOPS/s
	bandwidth: 77.3 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 126.7 GFLOPS/s
	bandwidth: 109.3 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 140.4 GFLOPS/s
	bandwidth: 121.1 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=5 k=26 ldc=32 (column-major) size=119623 batch=282 memory=1024 MB

LAPACK/BLAS...
	performance: 8.5 GFLOPS/s
	bandwidth: 7.3 GB/s
	duration: 0.1 s
Inlined...
	performance: 89.8 GFLOPS/s
	bandwidth: 77.5 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 113.2 GFLOPS/s
	bandwidth: 97.7 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 127.8 GFLOPS/s
	bandwidth: 110.2 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=5 k=32 ldc=32 (column-major) size=99864 batch=258 memory=1024 MB

LAPACK/BLAS...
	performance: 9.8 GFLOPS/s
	bandwidth: 8.4 GB/s
	duration: 0.1 s
Inlined...
	performance: 94.9 GFLOPS/s
	bandwidth: 81.8 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 122.3 GFLOPS/s
	bandwidth: 105.4 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 129.5 GFLOPS/s
	bandwidth: 111.7 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=9 k=9 ldc=32 (column-major) size=204288 batch=369 memory=1024 MB

LAPACK/BLAS...
	performance: 12.7 GFLOPS/s
	bandwidth: 6.8 GB/s
	duration: 0.1 s
Inlined...
	performance: 94.6 GFLOPS/s
	bandwidth: 50.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 161.9 GFLOPS/s
	bandwidth: 86.2 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 188.3 GFLOPS/s
	bandwidth: 100.3 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=9 k=22 ldc=32 (column-major) size=112788 batch=274 memory=1024 MB

LAPACK/BLAS...
	performance: 14.0 GFLOPS/s
	bandwidth: 7.5 GB/s
	duration: 0.1 s
Inlined...
	performance: 116.2 GFLOPS/s
	bandwidth: 61.8 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 170.1 GFLOPS/s
	bandwidth: 90.4 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 187.2 GFLOPS/s
	bandwidth: 99.5 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=9 k=32 ldc=32 (column-major) size=83886 batch=236 memory=1024 MB

LAPACK/BLAS...
	performance: 13.9 GFLOPS/s
	bandwidth: 7.4 GB/s
	duration: 0.1 s
Inlined...
	performance: 103.9 GFLOPS/s
	bandwidth: 55.2 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 187.8 GFLOPS/s
	bandwidth: 99.8 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 195.0 GFLOPS/s
	bandwidth: 103.6 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=13 k=5 ldc=32 (column-major) size=209388 batch=374 memory=1024 MB

LAPACK/BLAS...
	performance: 13.5 GFLOPS/s
	bandwidth: 5.5 GB/s
	duration: 0.1 s
Inlined...
	performance: 84.7 GFLOPS/s
	bandwidth: 34.5 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 180.0 GFLOPS/s
	bandwidth: 73.2 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 227.0 GFLOPS/s
	bandwidth: 92.4 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=13 k=13 ldc=32 (column-major) size=134083 batch=299 memory=1024 MB

LAPACK/BLAS...
	performance: 17.2 GFLOPS/s
	bandwidth: 7.0 GB/s
	duration: 0.1 s
Inlined...
	performance: 114.6 GFLOPS/s
	bandwidth: 46.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 220.6 GFLOPS/s
	bandwidth: 89.3 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 234.5 GFLOPS/s
	bandwidth: 94.9 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=13 k=24 ldc=32 (column-major) size=89717 batch=245 memory=1024 MB

LAPACK/BLAS...
	performance: 18.0 GFLOPS/s
	bandwidth: 7.3 GB/s
	duration: 0.1 s
Inlined...
	performance: 107.3 GFLOPS/s
	bandwidth: 43.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 233.7 GFLOPS/s
	bandwidth: 94.5 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 255.6 GFLOPS/s
	bandwidth: 103.3 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=13 k=26 ldc=32 (column-major) size=84626 batch=238 memory=1024 MB

LAPACK/BLAS...
	performance: 17.1 GFLOPS/s
	bandwidth: 6.9 GB/s
	duration: 0.1 s
Inlined...
	performance: 116.8 GFLOPS/s
	bandwidth: 47.2 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 215.3 GFLOPS/s
	bandwidth: 87.0 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 224.9 GFLOPS/s
	bandwidth: 90.9 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=13 k=28 ldc=32 (column-major) size=80082 batch=231 memory=1024 MB

LAPACK/BLAS...
	performance: 16.7 GFLOPS/s
	bandwidth: 6.8 GB/s
	duration: 0.1 s
Inlined...
	performance: 114.7 GFLOPS/s
	bandwidth: 46.3 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 204.0 GFLOPS/s
	bandwidth: 82.4 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 213.9 GFLOPS/s
	bandwidth: 86.4 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=13 k=32 ldc=32 (column-major) size=72315 batch=220 memory=1024 MB

LAPACK/BLAS...
	performance: 19.1 GFLOPS/s
	bandwidth: 7.7 GB/s
	duration: 0.1 s
Inlined...
	performance: 111.1 GFLOPS/s
	bandwidth: 44.9 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 163.2 GFLOPS/s
	bandwidth: 65.9 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 232.6 GFLOPS/s
	bandwidth: 94.0 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=13 k=45 ldc=32 (column-major) size=54984 batch=191 memory=1024 MB

LAPACK/BLAS...
	performance: 16.6 GFLOPS/s
	bandwidth: 6.7 GB/s
	duration: 0.1 s
Inlined...
	performance: 102.4 GFLOPS/s
	bandwidth: 41.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 179.1 GFLOPS/s
	bandwidth: 72.3 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 187.9 GFLOPS/s
	bandwidth: 75.9 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=14 k=14 ldc=32 (column-major) size=122910 batch=286 memory=1024 MB

LAPACK/BLAS...
	performance: 17.2 GFLOPS/s
	bandwidth: 6.6 GB/s
	duration: 0.1 s
Inlined...
	performance: 105.5 GFLOPS/s
	bandwidth: 40.6 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 219.4 GFLOPS/s
	bandwidth: 84.3 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 238.6 GFLOPS/s
	bandwidth: 91.7 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=14 k=29 ldc=32 (column-major) size=75318 batch=224 memory=1024 MB

LAPACK/BLAS...
	performance: 17.9 GFLOPS/s
	bandwidth: 6.9 GB/s
	duration: 0.1 s
Inlined...
	performance: 114.5 GFLOPS/s
	bandwidth: 43.9 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 212.0 GFLOPS/s
	bandwidth: 81.3 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 222.5 GFLOPS/s
	bandwidth: 85.4 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=14 k=32 ldc=32 (column-major) size=69905 batch=216 memory=1024 MB

LAPACK/BLAS...
	performance: 19.8 GFLOPS/s
	bandwidth: 7.6 GB/s
	duration: 0.1 s
Inlined...
	performance: 105.4 GFLOPS/s
	bandwidth: 40.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 232.9 GFLOPS/s
	bandwidth: 89.3 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 244.6 GFLOPS/s
	bandwidth: 93.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=22 k=9 ldc=32 (column-major) size=112788 batch=274 memory=1024 MB

LAPACK/BLAS...
	performance: 1.7 GFLOPS/s
	bandwidth: 0.5 GB/s
	duration: 0.9 s
Inlined...
	performance: 110.7 GFLOPS/s
	bandwidth: 32.0 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 261.0 GFLOPS/s
	bandwidth: 75.4 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 305.5 GFLOPS/s
	bandwidth: 88.2 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=22 k=22 ldc=32 (column-major) size=70939 batch=217 memory=1024 MB

LAPACK/BLAS...
	performance: 2.4 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 112.6 GFLOPS/s
	bandwidth: 32.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 244.0 GFLOPS/s
	bandwidth: 70.1 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 259.2 GFLOPS/s
	bandwidth: 74.5 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=22 k=32 ldc=32 (column-major) size=55188 batch=192 memory=1024 MB

LAPACK/BLAS...
	performance: 2.8 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 105.4 GFLOPS/s
	bandwidth: 30.2 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 248.5 GFLOPS/s
	bandwidth: 71.3 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 266.3 GFLOPS/s
	bandwidth: 76.4 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=24 k=5 ldc=32 (column-major) size=128070 batch=292 memory=1024 MB

LAPACK/BLAS...
	performance: 1.2 GFLOPS/s
	bandwidth: 0.3 GB/s
	duration: 0.8 s
Inlined...
	performance: 93.1 GFLOPS/s
	bandwidth: 25.8 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 233.0 GFLOPS/s
	bandwidth: 64.5 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 270.4 GFLOPS/s
	bandwidth: 74.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=24 k=13 ldc=32 (column-major) size=89717 batch=245 memory=1024 MB

LAPACK/BLAS...
	performance: 2.0 GFLOPS/s
	bandwidth: 0.5 GB/s
	duration: 0.9 s
Inlined...
	performance: 96.5 GFLOPS/s
	bandwidth: 26.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 248.3 GFLOPS/s
	bandwidth: 68.0 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 269.6 GFLOPS/s
	bandwidth: 73.9 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=24 k=24 ldc=32 (column-major) size=63550 batch=206 memory=1024 MB

LAPACK/BLAS...
	performance: 2.6 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 111.2 GFLOPS/s
	bandwidth: 30.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 270.8 GFLOPS/s
	bandwidth: 74.0 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 286.4 GFLOPS/s
	bandwidth: 78.2 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=24 k=26 ldc=32 (column-major) size=60349 batch=201 memory=1024 MB

LAPACK/BLAS...
	performance: 2.6 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 112.0 GFLOPS/s
	bandwidth: 30.6 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 247.7 GFLOPS/s
	bandwidth: 67.7 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 262.7 GFLOPS/s
	bandwidth: 71.7 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=24 k=32 ldc=32 (column-major) size=52428 batch=187 memory=1024 MB

LAPACK/BLAS...
	performance: 2.9 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 106.2 GFLOPS/s
	bandwidth: 29.0 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 256.3 GFLOPS/s
	bandwidth: 70.0 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 262.6 GFLOPS/s
	bandwidth: 71.7 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=26 k=5 ldc=32 (column-major) size=119623 batch=282 memory=1024 MB

LAPACK/BLAS...
	performance: 1.2 GFLOPS/s
	bandwidth: 0.3 GB/s
	duration: 0.8 s
Inlined...
	performance: 91.1 GFLOPS/s
	bandwidth: 24.1 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 210.3 GFLOPS/s
	bandwidth: 55.7 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 263.4 GFLOPS/s
	bandwidth: 69.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=26 k=13 ldc=32 (column-major) size=84626 batch=238 memory=1024 MB

LAPACK/BLAS...
	performance: 2.1 GFLOPS/s
	bandwidth: 0.5 GB/s
	duration: 0.9 s
Inlined...
	performance: 112.3 GFLOPS/s
	bandwidth: 29.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 254.4 GFLOPS/s
	bandwidth: 66.7 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 270.0 GFLOPS/s
	bandwidth: 70.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=26 k=24 ldc=32 (column-major) size=60349 batch=201 memory=1024 MB

LAPACK/BLAS...
	performance: 2.7 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 112.3 GFLOPS/s
	bandwidth: 29.3 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 276.0 GFLOPS/s
	bandwidth: 72.1 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 285.2 GFLOPS/s
	bandwidth: 74.5 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=26 k=26 ldc=32 (column-major) size=57358 batch=196 memory=1024 MB

LAPACK/BLAS...
	performance: 2.8 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 109.4 GFLOPS/s
	bandwidth: 28.6 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 255.3 GFLOPS/s
	bandwidth: 66.7 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 262.8 GFLOPS/s
	bandwidth: 68.6 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=26 k=28 ldc=32 (column-major) size=54648 batch=191 memory=1024 MB

LAPACK/BLAS...
	performance: 2.8 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 108.9 GFLOPS/s
	bandwidth: 28.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 242.4 GFLOPS/s
	bandwidth: 63.3 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 248.6 GFLOPS/s
	bandwidth: 64.9 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=26 k=32 ldc=32 (column-major) size=49932 batch=182 memory=1024 MB

LAPACK/BLAS...
	performance: 2.9 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 104.3 GFLOPS/s
	bandwidth: 27.2 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 255.4 GFLOPS/s
	bandwidth: 66.6 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 264.6 GFLOPS/s
	bandwidth: 69.0 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=26 k=45 ldc=32 (column-major) size=38994 batch=161 memory=1024 MB

LAPACK/BLAS...
	performance: 3.2 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 92.4 GFLOPS/s
	bandwidth: 24.1 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 198.6 GFLOPS/s
	bandwidth: 51.8 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 209.6 GFLOPS/s
	bandwidth: 54.6 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=28 k=13 ldc=32 (column-major) size=80082 batch=231 memory=1024 MB

LAPACK/BLAS...
	performance: 2.2 GFLOPS/s
	bandwidth: 0.6 GB/s
	duration: 0.9 s
Inlined...
	performance: 112.3 GFLOPS/s
	bandwidth: 28.3 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 259.4 GFLOPS/s
	bandwidth: 65.3 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 271.5 GFLOPS/s
	bandwidth: 68.4 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=28 k=26 ldc=32 (column-major) size=54648 batch=191 memory=1024 MB

LAPACK/BLAS...
	performance: 2.8 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 109.2 GFLOPS/s
	bandwidth: 27.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 255.8 GFLOPS/s
	bandwidth: 64.2 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 267.3 GFLOPS/s
	bandwidth: 67.1 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=28 k=28 ldc=32 (column-major) size=52103 batch=186 memory=1024 MB

LAPACK/BLAS...
	performance: 2.8 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 107.2 GFLOPS/s
	bandwidth: 26.9 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 243.1 GFLOPS/s
	bandwidth: 61.0 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 251.2 GFLOPS/s
	bandwidth: 63.0 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=28 k=32 ldc=32 (column-major) size=47662 batch=178 memory=1024 MB

LAPACK/BLAS...
	performance: 3.0 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 97.3 GFLOPS/s
	bandwidth: 24.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 247.9 GFLOPS/s
	bandwidth: 62.2 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 266.2 GFLOPS/s
	bandwidth: 66.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=28 k=45 ldc=32 (column-major) size=37324 batch=158 memory=1024 MB

LAPACK/BLAS...
	performance: 3.3 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 135.6 GFLOPS/s
	bandwidth: 34.0 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 315.8 GFLOPS/s
	bandwidth: 79.1 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 324.0 GFLOPS/s
	bandwidth: 81.2 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=29 k=14 ldc=32 (column-major) size=75318 batch=224 memory=1024 MB

LAPACK/BLAS...
	performance: 2.2 GFLOPS/s
	bandwidth: 0.6 GB/s
	duration: 0.9 s
Inlined...
	performance: 108.9 GFLOPS/s
	bandwidth: 26.9 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 249.5 GFLOPS/s
	bandwidth: 61.7 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 264.0 GFLOPS/s
	bandwidth: 65.3 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=29 k=29 ldc=32 (column-major) size=49765 batch=182 memory=1024 MB

LAPACK/BLAS...
	performance: 3.0 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 104.8 GFLOPS/s
	bandwidth: 25.8 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 237.9 GFLOPS/s
	bandwidth: 58.6 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 250.2 GFLOPS/s
	bandwidth: 61.6 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=29 k=32 ldc=32 (column-major) size=46603 batch=176 memory=1024 MB

LAPACK/BLAS...
	performance: 3.0 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 102.7 GFLOPS/s
	bandwidth: 25.3 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 259.4 GFLOPS/s
	bandwidth: 63.9 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 269.2 GFLOPS/s
	bandwidth: 66.3 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=29 k=55 ldc=32 (column-major) size=31337 batch=145 memory=1024 MB

LAPACK/BLAS...
	performance: 3.9 GFLOPS/s
	bandwidth: 1.0 GB/s
	duration: 0.8 s
Inlined...
	performance: 124.0 GFLOPS/s
	bandwidth: 30.5 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 311.7 GFLOPS/s
	bandwidth: 76.6 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 316.2 GFLOPS/s
	bandwidth: 77.7 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=32 k=5 ldc=32 (column-major) size=99864 batch=258 memory=1024 MB

LAPACK/BLAS...
	performance: 1.3 GFLOPS/s
	bandwidth: 0.3 GB/s
	duration: 0.8 s
Inlined...
	performance: 87.3 GFLOPS/s
	bandwidth: 20.8 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 212.2 GFLOPS/s
	bandwidth: 50.6 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 239.9 GFLOPS/s
	bandwidth: 57.3 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=32 k=9 ldc=32 (column-major) size=83886 batch=236 memory=1024 MB

LAPACK/BLAS...
	performance: 1.9 GFLOPS/s
	bandwidth: 0.5 GB/s
	duration: 0.8 s
Inlined...
	performance: 102.4 GFLOPS/s
	bandwidth: 24.2 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 261.8 GFLOPS/s
	bandwidth: 61.9 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 285.9 GFLOPS/s
	bandwidth: 67.6 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=32 k=13 ldc=32 (column-major) size=72315 batch=220 memory=1024 MB

LAPACK/BLAS...
	performance: 2.2 GFLOPS/s
	bandwidth: 0.5 GB/s
	duration: 0.9 s
Inlined...
	performance: 106.8 GFLOPS/s
	bandwidth: 25.2 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 249.3 GFLOPS/s
	bandwidth: 58.7 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 265.2 GFLOPS/s
	bandwidth: 62.4 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=32 k=14 ldc=32 (column-major) size=69905 batch=216 memory=1024 MB

LAPACK/BLAS...
	performance: 2.4 GFLOPS/s
	bandwidth: 0.6 GB/s
	duration: 0.8 s
Inlined...
	performance: 106.6 GFLOPS/s
	bandwidth: 25.1 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 239.8 GFLOPS/s
	bandwidth: 56.4 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 261.7 GFLOPS/s
	bandwidth: 61.6 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=32 k=22 ldc=32 (column-major) size=55188 batch=192 memory=1024 MB

LAPACK/BLAS...
	performance: 2.7 GFLOPS/s
	bandwidth: 0.6 GB/s
	duration: 0.9 s
Inlined...
	performance: 101.8 GFLOPS/s
	bandwidth: 23.9 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 248.8 GFLOPS/s
	bandwidth: 58.4 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 260.2 GFLOPS/s
	bandwidth: 61.0 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=32 k=24 ldc=32 (column-major) size=52428 batch=187 memory=1024 MB

LAPACK/BLAS...
	performance: 3.0 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 106.4 GFLOPS/s
	bandwidth: 24.9 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 270.3 GFLOPS/s
	bandwidth: 63.4 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 283.9 GFLOPS/s
	bandwidth: 66.6 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=32 k=26 ldc=32 (column-major) size=49932 batch=182 memory=1024 MB

LAPACK/BLAS...
	performance: 3.0 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 105.4 GFLOPS/s
	bandwidth: 24.7 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 252.5 GFLOPS/s
	bandwidth: 59.2 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 263.1 GFLOPS/s
	bandwidth: 61.7 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=32 k=28 ldc=32 (column-major) size=47662 batch=178 memory=1024 MB

LAPACK/BLAS...
	performance: 3.1 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 103.1 GFLOPS/s
	bandwidth: 24.2 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 241.4 GFLOPS/s
	bandwidth: 56.6 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 250.2 GFLOPS/s
	bandwidth: 58.6 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=32 k=29 ldc=32 (column-major) size=46603 batch=176 memory=1024 MB

LAPACK/BLAS...
	performance: 3.2 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 102.6 GFLOPS/s
	bandwidth: 24.0 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 238.9 GFLOPS/s
	bandwidth: 56.0 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 245.6 GFLOPS/s
	bandwidth: 57.5 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=32 k=32 ldc=32 (column-major) size=43690 batch=171 memory=1024 MB

LAPACK/BLAS...
	performance: 3.1 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 100.8 GFLOPS/s
	bandwidth: 23.6 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 261.5 GFLOPS/s
	bandwidth: 61.2 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 273.3 GFLOPS/s
	bandwidth: 64.0 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=32 k=45 ldc=32 (column-major) size=34379 batch=151 memory=1024 MB

LAPACK/BLAS...
	performance: 3.7 GFLOPS/s
	bandwidth: 0.9 GB/s
	duration: 0.8 s
Inlined...
	performance: 129.4 GFLOPS/s
	bandwidth: 30.3 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 333.8 GFLOPS/s
	bandwidth: 78.1 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 342.6 GFLOPS/s
	bandwidth: 80.2 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=32 k=55 ldc=32 (column-major) size=29537 batch=140 memory=1024 MB

LAPACK/BLAS...
	performance: 4.4 GFLOPS/s
	bandwidth: 1.0 GB/s
	duration: 0.8 s
Inlined...
	performance: 121.5 GFLOPS/s
	bandwidth: 28.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 314.6 GFLOPS/s
	bandwidth: 73.6 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 321.5 GFLOPS/s
	bandwidth: 75.2 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=45 k=13 ldc=32 (column-major) size=54984 batch=191 memory=1024 MB

LAPACK/BLAS...
	performance: 2.4 GFLOPS/s
	bandwidth: 0.5 GB/s
	duration: 0.9 s
Inlined...
	performance: 100.2 GFLOPS/s
	bandwidth: 20.3 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 248.0 GFLOPS/s
	bandwidth: 50.2 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 261.0 GFLOPS/s
	bandwidth: 52.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=45 k=26 ldc=32 (column-major) size=38994 batch=161 memory=1024 MB

LAPACK/BLAS...
	performance: 3.3 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 97.5 GFLOPS/s
	bandwidth: 19.6 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 250.4 GFLOPS/s
	bandwidth: 50.3 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 263.7 GFLOPS/s
	bandwidth: 53.0 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=45 k=28 ldc=32 (column-major) size=37324 batch=158 memory=1024 MB

LAPACK/BLAS...
	performance: 3.4 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 151.8 GFLOPS/s
	bandwidth: 30.5 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 380.4 GFLOPS/s
	bandwidth: 76.4 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 387.3 GFLOPS/s
	bandwidth: 77.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=45 k=32 ldc=32 (column-major) size=34379 batch=151 memory=1024 MB

LAPACK/BLAS...
	performance: 3.8 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.8 s
Inlined...
	performance: 143.1 GFLOPS/s
	bandwidth: 28.7 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 395.9 GFLOPS/s
	bandwidth: 79.5 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 414.3 GFLOPS/s
	bandwidth: 83.2 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=45 k=45 ldc=32 (column-major) size=27363 batch=135 memory=1024 MB

LAPACK/BLAS...
	performance: 4.9 GFLOPS/s
	bandwidth: 1.0 GB/s
	duration: 0.7 s
Inlined...
	performance: 120.4 GFLOPS/s
	bandwidth: 24.1 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 316.4 GFLOPS/s
	bandwidth: 63.4 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 320.5 GFLOPS/s
	bandwidth: 64.2 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=55 k=29 ldc=32 (column-major) size=31337 batch=145 memory=1024 MB

LAPACK/BLAS...
	performance: 4.1 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.8 s
Inlined...
	performance: 138.7 GFLOPS/s
	bandwidth: 25.8 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 352.6 GFLOPS/s
	bandwidth: 65.6 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 357.1 GFLOPS/s
	bandwidth: 66.4 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=55 k=32 ldc=32 (column-major) size=29537 batch=140 memory=1024 MB

LAPACK/BLAS...
	performance: 4.5 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.7 s
Inlined...
	performance: 132.0 GFLOPS/s
	bandwidth: 24.5 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 379.5 GFLOPS/s
	bandwidth: 70.5 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 382.4 GFLOPS/s
	bandwidth: 71.0 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=32 n=55 k=55 ldc=32 (column-major) size=20506 batch=117 memory=1024 MB

LAPACK/BLAS...
	performance: 6.4 GFLOPS/s
	bandwidth: 1.2 GB/s
	duration: 0.6 s
Inlined...
	performance: 126.1 GFLOPS/s
	bandwidth: 23.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 293.6 GFLOPS/s
	bandwidth: 54.4 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 302.3 GFLOPS/s
	bandwidth: 56.0 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=45 n=13 k=13 ldc=48 (column-major) size=97400 batch=255 memory=1024 MB

LAPACK/BLAS...
	performance: 16.8 GFLOPS/s
	bandwidth: 6.3 GB/s
	duration: 0.1 s
Inlined...
	performance: 104.3 GFLOPS/s
	bandwidth: 38.8 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 192.6 GFLOPS/s
	bandwidth: 71.6 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 210.3 GFLOPS/s
	bandwidth: 78.2 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=45 n=13 k=26 ldc=48 (column-major) size=62953 batch=205 memory=1024 MB

LAPACK/BLAS...
	performance: 17.2 GFLOPS/s
	bandwidth: 6.4 GB/s
	duration: 0.1 s
Inlined...
	performance: 95.8 GFLOPS/s
	bandwidth: 35.5 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 159.5 GFLOPS/s
	bandwidth: 59.2 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 164.6 GFLOPS/s
	bandwidth: 61.0 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=45 n=13 k=28 ldc=48 (column-major) size=59705 batch=200 memory=1024 MB

LAPACK/BLAS...
	performance: 17.9 GFLOPS/s
	bandwidth: 6.6 GB/s
	duration: 0.1 s
Inlined...
	performance: 96.8 GFLOPS/s
	bandwidth: 35.9 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 158.0 GFLOPS/s
	bandwidth: 58.6 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 163.6 GFLOPS/s
	bandwidth: 60.7 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=45 n=13 k=32 ldc=48 (column-major) size=54120 batch=190 memory=1024 MB

LAPACK/BLAS...
	performance: 18.3 GFLOPS/s
	bandwidth: 6.8 GB/s
	duration: 0.1 s
Inlined...
	performance: 91.9 GFLOPS/s
	bandwidth: 34.1 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 153.6 GFLOPS/s
	bandwidth: 56.9 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 157.1 GFLOPS/s
	bandwidth: 58.2 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=45 n=13 k=45 ldc=48 (column-major) size=41502 batch=166 memory=1024 MB

LAPACK/BLAS...
	performance: 17.9 GFLOPS/s
	bandwidth: 6.6 GB/s
	duration: 0.1 s
Inlined...
	performance: 74.7 GFLOPS/s
	bandwidth: 27.7 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 134.7 GFLOPS/s
	bandwidth: 49.9 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 138.2 GFLOPS/s
	bandwidth: 51.2 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=45 n=26 k=13 ldc=48 (column-major) size=61822 batch=203 memory=1024 MB

LAPACK/BLAS...
	performance: 2.1 GFLOPS/s
	bandwidth: 0.5 GB/s
	duration: 0.9 s
Inlined...
	performance: 93.2 GFLOPS/s
	bandwidth: 21.3 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 226.4 GFLOPS/s
	bandwidth: 51.9 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 231.5 GFLOPS/s
	bandwidth: 53.0 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=45 n=26 k=26 ldc=48 (column-major) size=43380 batch=170 memory=1024 MB

LAPACK/BLAS...
	performance: 3.1 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.8 s
Inlined...
	performance: 91.5 GFLOPS/s
	bandwidth: 20.9 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 200.1 GFLOPS/s
	bandwidth: 45.6 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 204.9 GFLOPS/s
	bandwidth: 46.7 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=45 n=26 k=28 ldc=48 (column-major) size=41476 batch=166 memory=1024 MB

LAPACK/BLAS...
	performance: 2.9 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 86.7 GFLOPS/s
	bandwidth: 19.7 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 193.3 GFLOPS/s
	bandwidth: 44.0 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 203.3 GFLOPS/s
	bandwidth: 46.3 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=45 n=26 k=32 ldc=48 (column-major) size=38130 batch=159 memory=1024 MB

LAPACK/BLAS...
	performance: 3.2 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 141.0 GFLOPS/s
	bandwidth: 32.1 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 301.2 GFLOPS/s
	bandwidth: 68.6 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 303.4 GFLOPS/s
	bandwidth: 69.1 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=45 n=26 k=45 ldc=48 (column-major) size=30208 batch=142 memory=1024 MB

LAPACK/BLAS...
	performance: 4.2 GFLOPS/s
	bandwidth: 0.9 GB/s
	duration: 0.8 s
Inlined...
	performance: 113.5 GFLOPS/s
	bandwidth: 25.8 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 249.7 GFLOPS/s
	bandwidth: 56.8 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 254.5 GFLOPS/s
	bandwidth: 57.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=45 n=28 k=13 ldc=48 (column-major) size=58533 batch=198 memory=1024 MB

LAPACK/BLAS...
	performance: 2.2 GFLOPS/s
	bandwidth: 0.5 GB/s
	duration: 0.9 s
Inlined...
	performance: 95.3 GFLOPS/s
	bandwidth: 20.9 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 223.3 GFLOPS/s
	bandwidth: 48.9 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 235.2 GFLOPS/s
	bandwidth: 51.5 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=45 n=28 k=26 ldc=48 (column-major) size=41399 batch=166 memory=1024 MB

LAPACK/BLAS...
	performance: 3.1 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 89.7 GFLOPS/s
	bandwidth: 19.5 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 197.9 GFLOPS/s
	bandwidth: 43.1 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 202.3 GFLOPS/s
	bandwidth: 44.0 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=45 n=28 k=28 ldc=48 (column-major) size=39615 batch=163 memory=1024 MB

LAPACK/BLAS...
	performance: 3.0 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 88.5 GFLOPS/s
	bandwidth: 19.3 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 195.7 GFLOPS/s
	bandwidth: 42.6 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 202.9 GFLOPS/s
	bandwidth: 44.1 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=45 n=28 k=32 ldc=48 (column-major) size=36472 batch=156 memory=1024 MB

LAPACK/BLAS...
	performance: 3.4 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 141.8 GFLOPS/s
	bandwidth: 30.8 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 305.1 GFLOPS/s
	bandwidth: 66.3 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 304.2 GFLOPS/s
	bandwidth: 66.1 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=45 n=28 k=45 ldc=48 (column-major) size=28994 batch=139 memory=1024 MB

LAPACK/BLAS...
	performance: 4.3 GFLOPS/s
	bandwidth: 0.9 GB/s
	duration: 0.8 s
Inlined...
	performance: 110.7 GFLOPS/s
	bandwidth: 24.0 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 251.6 GFLOPS/s
	bandwidth: 54.6 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 254.8 GFLOPS/s
	bandwidth: 55.3 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=45 n=32 k=13 ldc=48 (column-major) size=52904 batch=188 memory=1024 MB

LAPACK/BLAS...
	performance: 2.4 GFLOPS/s
	bandwidth: 0.5 GB/s
	duration: 0.8 s
Inlined...
	performance: 91.9 GFLOPS/s
	bandwidth: 18.6 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 219.7 GFLOPS/s
	bandwidth: 44.5 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 232.2 GFLOPS/s
	bandwidth: 47.0 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=45 n=32 k=26 ldc=48 (column-major) size=37936 batch=159 memory=1024 MB

LAPACK/BLAS...
	performance: 3.3 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.9 s
Inlined...
	performance: 144.2 GFLOPS/s
	bandwidth: 29.0 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 318.9 GFLOPS/s
	bandwidth: 64.1 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 328.6 GFLOPS/s
	bandwidth: 66.1 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=45 n=32 k=28 ldc=48 (column-major) size=36353 batch=156 memory=1024 MB

LAPACK/BLAS...
	performance: 3.5 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.8 s
Inlined...
	performance: 145.3 GFLOPS/s
	bandwidth: 29.2 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 316.8 GFLOPS/s
	bandwidth: 63.7 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 321.0 GFLOPS/s
	bandwidth: 64.5 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=45 n=32 k=32 ldc=48 (column-major) size=33554 batch=150 memory=1024 MB

LAPACK/BLAS...
	performance: 3.9 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.8 s
Inlined...
	performance: 130.9 GFLOPS/s
	bandwidth: 26.3 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 308.4 GFLOPS/s
	bandwidth: 61.9 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 318.1 GFLOPS/s
	bandwidth: 63.9 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=45 n=32 k=45 ldc=48 (column-major) size=26838 batch=134 memory=1024 MB

LAPACK/BLAS...
	performance: 4.9 GFLOPS/s
	bandwidth: 1.0 GB/s
	duration: 0.7 s
Inlined...
	performance: 107.1 GFLOPS/s
	bandwidth: 21.5 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 249.6 GFLOPS/s
	bandwidth: 50.1 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 264.0 GFLOPS/s
	bandwidth: 52.9 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=45 n=45 k=13 ldc=48 (column-major) size=40305 batch=164 memory=1024 MB

LAPACK/BLAS...
	performance: 2.5 GFLOPS/s
	bandwidth: 0.4 GB/s
	duration: 0.8 s
Inlined...
	performance: 83.3 GFLOPS/s
	bandwidth: 14.1 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 216.7 GFLOPS/s
	bandwidth: 36.7 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 216.7 GFLOPS/s
	bandwidth: 36.7 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=45 n=45 k=26 ldc=48 (column-major) size=29826 batch=141 memory=1024 MB

LAPACK/BLAS...
	performance: 4.2 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.7 s
Inlined...
	performance: 127.6 GFLOPS/s
	bandwidth: 21.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 305.2 GFLOPS/s
	bandwidth: 51.2 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 310.0 GFLOPS/s
	bandwidth: 52.0 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=45 n=45 k=28 ldc=48 (column-major) size=28679 batch=138 memory=1024 MB

LAPACK/BLAS...
	performance: 4.4 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.7 s
Inlined...
	performance: 131.0 GFLOPS/s
	bandwidth: 22.0 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 304.9 GFLOPS/s
	bandwidth: 51.1 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 306.4 GFLOPS/s
	bandwidth: 51.4 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=45 n=45 k=32 ldc=48 (column-major) size=26630 batch=133 memory=1024 MB

LAPACK/BLAS...
	performance: 4.9 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.7 s
Inlined...
	performance: 114.9 GFLOPS/s
	bandwidth: 19.2 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 286.3 GFLOPS/s
	bandwidth: 47.9 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 309.7 GFLOPS/s
	bandwidth: 51.9 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=45 n=45 k=45 ldc=48 (column-major) size=21613 batch=120 memory=1024 MB

LAPACK/BLAS...
	performance: 6.3 GFLOPS/s
	bandwidth: 1.0 GB/s
	duration: 0.6 s
Inlined...
	performance: 122.1 GFLOPS/s
	bandwidth: 20.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 258.0 GFLOPS/s
	bandwidth: 43.1 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 261.1 GFLOPS/s
	bandwidth: 43.6 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=55 n=16 k=16 ldc=56 (column-major) size=66052 batch=210 memory=1024 MB

LAPACK/BLAS...
	performance: 2.1 GFLOPS/s
	bandwidth: 0.6 GB/s
	duration: 0.9 s
Inlined...
	performance: 84.0 GFLOPS/s
	bandwidth: 25.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 180.9 GFLOPS/s
	bandwidth: 54.8 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 189.5 GFLOPS/s
	bandwidth: 57.4 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=55 n=16 k=29 ldc=56 (column-major) size=45420 batch=174 memory=1024 MB

LAPACK/BLAS...
	performance: 2.6 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.9 s
Inlined...
	performance: 83.9 GFLOPS/s
	bandwidth: 25.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 165.9 GFLOPS/s
	bandwidth: 50.1 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 170.2 GFLOPS/s
	bandwidth: 51.4 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=55 n=16 k=55 ldc=56 (column-major) size=27956 batch=137 memory=1024 MB

LAPACK/BLAS...
	performance: 3.6 GFLOPS/s
	bandwidth: 1.1 GB/s
	duration: 0.7 s
Inlined...
	performance: 87.9 GFLOPS/s
	bandwidth: 26.5 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 217.0 GFLOPS/s
	bandwidth: 65.4 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 220.9 GFLOPS/s
	bandwidth: 66.6 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=55 n=29 k=16 ldc=56 (column-major) size=45221 batch=174 memory=1024 MB

LAPACK/BLAS...
	performance: 2.7 GFLOPS/s
	bandwidth: 0.5 GB/s
	duration: 0.9 s
Inlined...
	performance: 82.4 GFLOPS/s
	bandwidth: 16.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 206.3 GFLOPS/s
	bandwidth: 41.0 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 220.1 GFLOPS/s
	bandwidth: 43.8 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=55 n=29 k=29 ldc=56 (column-major) size=33058 batch=148 memory=1024 MB

LAPACK/BLAS...
	performance: 3.8 GFLOPS/s
	bandwidth: 0.7 GB/s
	duration: 0.8 s
Inlined...
	performance: 125.5 GFLOPS/s
	bandwidth: 24.8 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 302.7 GFLOPS/s
	bandwidth: 59.9 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 308.5 GFLOPS/s
	bandwidth: 61.1 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=55 n=29 k=32 ldc=56 (column-major) size=31126 batch=144 memory=1024 MB

LAPACK/BLAS...
	performance: 4.1 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.8 s
Inlined...
	performance: 122.6 GFLOPS/s
	bandwidth: 24.3 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 295.8 GFLOPS/s
	bandwidth: 58.5 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 300.7 GFLOPS/s
	bandwidth: 59.5 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=55 n=29 k=55 ldc=56 (column-major) size=21495 batch=120 memory=1024 MB

LAPACK/BLAS...
	performance: 6.0 GFLOPS/s
	bandwidth: 1.2 GB/s
	duration: 0.6 s
Inlined...
	performance: 103.6 GFLOPS/s
	bandwidth: 20.4 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 246.2 GFLOPS/s
	bandwidth: 48.6 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 251.1 GFLOPS/s
	bandwidth: 49.5 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=55 n=32 k=29 ldc=56 (column-major) size=31104 batch=144 memory=1024 MB

LAPACK/BLAS...
	performance: 4.1 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.8 s
Inlined...
	performance: 124.7 GFLOPS/s
	bandwidth: 23.2 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 312.0 GFLOPS/s
	bandwidth: 58.0 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 318.8 GFLOPS/s
	bandwidth: 59.3 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=55 n=32 k=32 ldc=56 (column-major) size=29330 batch=140 memory=1024 MB

LAPACK/BLAS...
	performance: 4.6 GFLOPS/s
	bandwidth: 0.9 GB/s
	duration: 0.7 s
Inlined...
	performance: 116.5 GFLOPS/s
	bandwidth: 21.7 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 303.8 GFLOPS/s
	bandwidth: 56.5 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 318.0 GFLOPS/s
	bandwidth: 59.1 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=55 n=32 k=55 ldc=56 (column-major) size=20407 batch=117 memory=1024 MB

LAPACK/BLAS...
	performance: 6.5 GFLOPS/s
	bandwidth: 1.2 GB/s
	duration: 0.6 s
Inlined...
	performance: 100.5 GFLOPS/s
	bandwidth: 18.6 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 244.9 GFLOPS/s
	bandwidth: 45.4 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 250.9 GFLOPS/s
	bandwidth: 46.5 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=55 n=55 k=16 ldc=56 (column-major) size=27730 batch=136 memory=1024 MB

LAPACK/BLAS...
	performance: 4.0 GFLOPS/s
	bandwidth: 0.6 GB/s
	duration: 0.7 s
Inlined...
	performance: 112.2 GFLOPS/s
	bandwidth: 15.6 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 322.2 GFLOPS/s
	bandwidth: 44.8 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 326.0 GFLOPS/s
	bandwidth: 45.3 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=55 n=55 k=29 ldc=56 (column-major) size=21406 batch=119 memory=1024 MB

LAPACK/BLAS...
	performance: 6.1 GFLOPS/s
	bandwidth: 0.8 GB/s
	duration: 0.6 s
Inlined...
	performance: 120.9 GFLOPS/s
	bandwidth: 16.6 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 302.5 GFLOPS/s
	bandwidth: 41.6 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 306.3 GFLOPS/s
	bandwidth: 42.2 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=55 n=55 k=32 ldc=56 (column-major) size=20336 batch=116 memory=1024 MB

LAPACK/BLAS...
	performance: 6.6 GFLOPS/s
	bandwidth: 0.9 GB/s
	duration: 0.6 s
Inlined...
	performance: 115.0 GFLOPS/s
	bandwidth: 15.8 GB/s
	duration: 0.0 s
	diff=0.000000
Dispatched...
	performance: 295.3 GFLOPS/s
	bandwidth: 40.6 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 305.0 GFLOPS/s
	bandwidth: 41.9 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

m=55 n=55 k=55 ldc=56 (column-major) size=14700 batch=99 memory=1024 MB

LAPACK/BLAS...
	performance: 9.8 GFLOPS/s
	bandwidth: 1.3 GB/s
	duration: 0.5 s
Inlined...
	performance: 86.9 GFLOPS/s
	bandwidth: 11.9 GB/s
	duration: 0.1 s
	diff=0.000000
Dispatched...
	performance: 237.0 GFLOPS/s
	bandwidth: 32.4 GB/s
	duration: 0.0 s
	diff=0.000000
Specialized...
	performance: 242.0 GFLOPS/s
	bandwidth: 33.1 GB/s
	duration: 0.0 s
	diff=0.000000
Finished

