Toward Better Hip Kernel Generation for AMD GPUsscalingintelligence.stanford.edu2 points·by skidrow·hace 7 días·0 comments
Toward Better Hip Kernel Generation for AMD GPUsscalingintelligence.stanford.edu2 points·by skidrow·hace 9 días·0 comments
FlashAttention-4: Algorithm and Kernel Pipelining Co-Designresearch.colfax-intl.com1 points·by skidrow·hace 9 días·0 comments
FlashAttention-4: Algorithm and Kernel Pipeliningresearch.colfax-intl.com4 points·by skidrow·hace 10 días·0 comments
Toward Better Hip Kernel Generation for AMD GPUsscalingintelligence.stanford.edu3 points·by skidrow·hace 11 días·0 comments
FlashAttention-4: Algorithm and Kernel Pipeliningresearch.colfax-intl.com2 points·by skidrow·hace 11 días·0 comments
Toward Better Hip Kernel Generation for AMD GPUsscalingintelligence.stanford.edu3 points·by skidrow·hace 11 días·0 comments
Toward Better Hip Kernel Generation for AMD GPUsscalingintelligence.stanford.edu2 points·by skidrow·hace 21 días·0 comments
FlashAttention-4: Algorithm and Kernel Pipelining Co-Designresearch.colfax-intl.com1 points·by skidrow·hace 21 días·0 comments
Occupancy Math on the AMD MI355X: A From-First-Principles Guideindianspeedster.github.io2 points·by skidrow·hace 22 días·0 comments
Computer Vision – Lecture 1.1 (Introduction: Organization) [video]youtube.com2 points·by skidrow·hace 24 días·0 comments
FlashAttention-4: Algorithm and Kernel Pipelining Co-Designresearch.colfax-intl.com2 points·by skidrow·hace 24 días·0 comments
Cutlass Tutorial: Efficient GEMM Kernel Designs with Pipeliningresearch.colfax-intl.com2 points·by skidrow·hace 24 días·0 comments
Toward Better Hip Kernel Generation for AMD GPUsscalingintelligence.stanford.edu2 points·by skidrow·hace 24 días·0 comments
FP8 GEMM Optimization on AMD CDNA4 Architecturerocm.blogs.amd.com2 points·by skidrow·hace 24 días·0 comments
Occupancy Math on the AMD MI355X: A From-First-Principles Guideindianspeedster.github.io2 points·by skidrow·hace 24 días·0 comments