Lixun Zhang 8351f49fc7 [Tuning] Gemm tuning v3 (#457) ...

* Add gemm tuning script v3

* Introduce --jobs to control the number of files to generate

* Switch to trans convention used by Tensile

* Rerun rocprof if it crashes

* update README

* Remove peak perf and efficiency

2024-01-17 10:09:34 -06:00

..

gemm

[Tuning] Gemm tuning v3 (#457)

2024-01-17 10:09:34 -06:00

benchmark_flash_attention.py

Benchmark FA on 2 GCDs (#393)

2023-11-08 12:42:54 -06:00

build_dbg_llvm.sh

[ROCM][scripts] Add script to build debug LLVM installation.

2023-01-13 00:41:57 +01:00

build.sh

assume ROCM device

2023-05-04 16:46:59 -05:00

cache_print.sh

update scripts

2022-12-22 18:47:42 -06:00

check_llvm_src.sh

Replace hard coded ROCM paths with ROCM_PATH env var.

2023-03-06 03:20:38 +00:00

clean.sh

update scripts

2022-12-22 18:47:42 -06:00

collect_rocm_kernels.sh

add scripts

2022-12-21 13:13:24 -06:00

debug.sh

add scripts

2022-12-21 13:13:24 -06:00

delete_hip_files.sh

add scripts

2022-12-21 13:13:24 -06:00

deps.sh

add scripts

2022-12-21 13:13:24 -06:00

docker_build.sh

add scripts

2022-12-21 13:13:24 -06:00

docker_run.sh

Initial commit to resolve merge conflicts

2023-10-03 04:04:26 +00:00

find_lib.sh

add scripts

2022-12-21 13:13:24 -06:00

fix_so.sh

Update hip_backend to use libhsa-runtime for arch info, (#411)

2023-12-21 15:40:57 +00:00

git_checkout_all.sh

add scripts

2022-12-21 13:13:24 -06:00

git_commit_amend.sh

add scripts

2022-12-21 13:13:24 -06:00

git_config_user.sh

add scripts

2022-12-21 13:13:24 -06:00

git_submodule_add.sh

add scripts

2022-12-21 13:13:24 -06:00

git_submodule_rm.sh

add scripts

2022-12-21 13:13:24 -06:00

git_submodule_update.sh

add scripts

2022-12-21 13:13:24 -06:00

grep_for_symbol.sh

add scripts

2022-12-21 13:13:24 -06:00

hip_kernel.cpp

add scripts

2022-12-21 13:13:24 -06:00

hipify.sh

add scripts

2022-12-21 13:13:24 -06:00

lit.sh

fix workflow

2023-05-01 12:49:29 -05:00

lld.sh

Replace hard coded ROCM paths with ROCM_PATH env var.

2023-03-06 03:20:38 +00:00

occ.sh

Added a script to print occupancy info (#450)

2024-01-10 14:01:13 -06:00

plot_layout.py

Add a cute tool to plot blocked, dotOperand, and mfma layout (#407)

2023-11-29 09:35:33 -06:00

post.sh

add scripts

2022-12-21 13:13:24 -06:00

pytorch.sh

assume ROCM device

2023-05-04 16:46:59 -05:00

run_2gcd.sh

Benchmark FA on 2 GCDs (#393)

2023-11-08 12:42:54 -06:00

run.sh

ROCM IFU: remove ref to test_elementwise

2023-12-07 13:31:59 -06:00

setup_rocm_libs.sh

Update hip_backend to use libhsa-runtime for arch info, (#411)

2023-12-21 15:40:57 +00:00

test_fptrunc.py

add scripts

2022-12-21 13:13:24 -06:00

test_hip_kernel.sh

add scripts

2022-12-21 13:13:24 -06:00

test.sh

ROCM IFU: remove ref to test_elementwise

2023-12-07 13:31:59 -06:00

tikzplot.tex

Add a cute tool to plot blocked, dotOperand, and mfma layout (#407)

2023-11-29 09:35:33 -06:00