diff --git a/README.md b/README.md index 1753c16a502aec92c2d823aa78c28dbb8d8d2d81..3c8928a7e15e0adf94f130840153211f7665ed2e 100644 --- a/README.md +++ b/README.md @@ -216,6 +216,7 @@ $ export CUDA_VISIBLE_DEVICES=0 # f.x. run on device no. 0 only |Nvidia A30, 1.44GHz | PTX FMA | half2 | 8700 | 34800 | |32x Xeon 8268, 2.90GHz <br> (full Karolina HPE Superdome Flex node) | AVX-512 FMA | double | 3650 | 58400 | |Nvida Quadro RTX 6000, 1.77GHz | PTX WMMA | half | 7.79 | 63816 | +|Nvidia A100-SXM4-40GB, 1.41GHz | PTX FMA | half2 | 17355 | 69420 | |Nvidia RTX 3060 Ti, 1.66GHz | PTX WMMA | half | 8.90 | 72908 | |8x Nvidia A100-SXM4-40GB, 1.41GHz <br> (full Karolina supercomputer acn node) | PTX FMA | double | 38944 | 77888 | |Nvidia TITAN V, 1.46GHz | PTX WMMA | half | 13.40 | 109772 | @@ -225,6 +226,7 @@ $ export CUDA_VISIBLE_DEVICES=0 # f.x. run on device no. 0 only |8x Nvidia A100-SXM4-40GB, 1.41GHz <br> (full Karolina supercomputer acn node) | PTX WMMA | double | 303.6 | 155443 | |Nvidia A100-SXM4-40GB, 1.41GHz | PTX WMMA | half | 37.9 | 310477 | |16x Nvidia V100-SXM3, 1.59GHz (full DGX-2)| PTX FMA | half2 | 128584| 514336 | +|8x Nvidia A100-SXM4-40GB, 1.41GHz <br> (full Karolina supercomputer acn node) | PTX FMA | half2 | 138800 | 555200 | |16x Nvidia V100-SXM3, 1.59GHz (full DGX-2)| PTX WMMA | half | 254.3 | 2083226 | |8x Nvidia A100-SXM4-40GB, 1.41GHz <br> (full Karolina supercomputer acn node) | PTX WMMA | half | 303.1 | 2482995 |