forward performance tuning for MI350#4925

Open

liligwu wants to merge 28 commits intopytorch:mainfrom

Commits on Sep 24, 2025

Add gfx950 build support + fp16 fix + index type fix

avbokovoy
authored and
liligwu
committed
Change int64_t to index_t as template parameters in load_raw_per_warp

avbokovoy
authored and
liligwu
committed
Implement llvm fp16 buffer load for gfx950

avbokovoy
authored and
liligwu
committed
Fix c-style half to float cast

avbokovoy
authored and
liligwu
committed
Patch 256 half stores

avbokovoy
authored and
liligwu
committed
cta_per_row workgroup optim

shbiswas834
authored and
liligwu
committed
Added mi350 guards

shbiswas834
authored and
liligwu
committed
Fix index overflow in row load

shbiswas834
authored and
liligwu
committed
cta_per_row workgroup reduce by 4 optim

shbiswas834
authored and
liligwu
committed
Fix mixed_D frontend to backend connection

avbokovoy
authored and
liligwu
committed
changed max_segment_length_per_cta to 4096

kudomcho
authored and
liligwu
committed
added rocm guards and removed comment

shbiswas834
authored and
liligwu
committed
clean debug statements in Hip.cmake
liligwu
committed
Merge pull request #121

shbiswas834
authored and
liligwu
committed
Guard f16 llvm intrinsics with ROCm >=7.0

avbokovoy
authored and
liligwu
committed
fix the bug in dimention 160 in ROCm optimization
liligwu
committed
Cleanup optimized warp_per_raw kernel

avbokovoy
authored and
liligwu
committed
Add 320 embedding dim support for optimized warp_per_row kernel

avbokovoy
authored and
liligwu
committed
changed the max length per warp and cta per row WG size

root
authored and
liligwu
committed
added DPP and changed max length per warp to 16k

kudomcho
authored and
liligwu
committed
guard max segment warp based on emb dim

kudomcho
authored and
liligwu
committed
added guarding opt of max segment for the case batch size list=1

kudomcho
authored and
liligwu
committed
opt for grad_indice_weights kernel

root
authored and
liligwu
committed
added store row per warp on emb 192 and added accuracy test functionality

kudomcho
authored and
liligwu
committed
workgroup tuning and loop unrolled

shbiswas834
authored and
liligwu
committed
specialize

Hardcode84
authored and
liligwu
committed
explicitly link to tbb
liligwu
committed

Commits on Sep 25, 2025

added warpReduceAllSum with rocm guards
shbiswas834
committed