Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on How to Optimize a CUDA Matmul Kernel for CuBLAS-Like Performance: A Worklog. Parent comment
On a 4090 gpu, average of 20 runs of SGEMM_CUDA:
size tflops_cublas tflops_my diff 4096² 50.8-50.9 61.8 +21% 8192² 56.3-56.4 67.1 +19% 16384² 53.6 66.7 +24%
There are no comments on this comment yet.
On a 4090 gpu, average of 20 runs of SGEMM_CUDA:
I guess the right thing to do now would be to hire a B2B salesman and figure out, which company needs it.