Skip to content

[libc][gpu] Disable loop unrolling in the throughput benchmark loop #153971

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Aug 16, 2025
Merged

[libc][gpu] Disable loop unrolling in the throughput benchmark loop #153971

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
c227a4b
Disable loop unrolling in the throughput benchmark loop by default
leandrolcampos Aug 16, 2025
4da8053
Remove unroll toggle; make `throughput` loop non-unrolled uncondition…
leandrolcampos Aug 16, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 9 additions & 0 deletions libc/benchmarks/gpu/CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,8 @@ add_subdirectory(timing)

add_custom_target(gpu-benchmark)

option(LIBC_GPU_BENCHMARKS_ALLOW_UNROLL "Allow compiler loop unrolling in throughput loops" OFF)

function(add_benchmark benchmark_name)
cmake_parse_arguments(
"BENCHMARK"
Expand All @@ -14,6 +16,12 @@ function(add_benchmark benchmark_name)
if(NOT libc.src.time.clock IN_LIST TARGET_LLVMLIBC_ENTRYPOINTS)
message(FATAL_ERROR "target does not support clock")
endif()

set(benchmark_extra_flags "")
if(NOT LIBC_GPU_BENCHMARKS_ALLOW_UNROLL)
list(APPEND benchmark_extra_flags "-DLIBC_GPU_BENCHMARKS_DISABLE_UNROLL=1")
endif()

add_libc_hermetic(
${benchmark_name}
IS_GPU_BENCHMARK
Expand All @@ -26,6 +34,7 @@ function(add_benchmark benchmark_name)
${BENCHMARK_UNPARSED_ARGUMENTS}
COMPILE_OPTIONS
-flto
${benchmark_extra_flags}
)
get_fq_target_name(${benchmark_name} fq_target_name)
set(fq_build_target_name ${fq_target_name}.__build__)
Expand Down
16 changes: 16 additions & 0 deletions libc/benchmarks/gpu/timing/amdgpu/timing.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -117,6 +117,10 @@ throughput_baseline(const cpp::array<T, N> &inputs) {
asm("" ::"s"(start));

T result{};

#if defined(LIBC_GPU_BENCHMARKS_DISABLE_UNROLL)
#pragma clang loop unroll(disable)
#endif
for (auto input : inputs) {
asm("" ::"v"(input));
result = input;
Expand Down Expand Up @@ -146,6 +150,10 @@ static LIBC_INLINE uint64_t throughput(F f, const cpp::array<T, N> &inputs) {
asm("" ::"s"(start));

T result{};

#if defined(LIBC_GPU_BENCHMARKS_DISABLE_UNROLL)
#pragma clang loop unroll(disable)
#endif
for (auto input : inputs) {
asm("" ::"v"(input));
result = f(input);
Expand Down Expand Up @@ -174,6 +182,10 @@ static LIBC_INLINE uint64_t throughput_baseline(
asm("" ::"s"(start));

T result{};

#if defined(LIBC_GPU_BENCHMARKS_DISABLE_UNROLL)
#pragma clang loop unroll(disable)
#endif
for (size_t i = 0; i < N; i++) {
T x = inputs1[i];
T y = inputs2[i];
Expand Down Expand Up @@ -206,6 +218,10 @@ static LIBC_INLINE uint64_t throughput(F f, const cpp::array<T, N> &inputs1,
asm("" ::"s"(start));

T result{};

#if defined(LIBC_GPU_BENCHMARKS_DISABLE_UNROLL)
#pragma clang loop unroll(disable)
#endif
for (size_t i = 0; i < N; i++) {
T x = inputs1[i];
T y = inputs2[i];
Expand Down
16 changes: 16 additions & 0 deletions libc/benchmarks/gpu/timing/nvptx/timing.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -106,6 +106,10 @@ throughput_baseline(const cpp::array<T, N> &inputs) {
asm("" ::"llr"(start));

T result{};

#if defined(LIBC_GPU_BENCHMARKS_DISABLE_UNROLL)
#pragma clang loop unroll(disable)
#endif
for (auto input : inputs) {
asm("" ::"r"(input));
result = input;
Expand Down Expand Up @@ -135,6 +139,10 @@ static LIBC_INLINE uint64_t throughput(F f, const cpp::array<T, N> &inputs) {
asm("" ::"llr"(start));

T result{};

#if defined(LIBC_GPU_BENCHMARKS_DISABLE_UNROLL)
#pragma clang loop unroll(disable)
#endif
for (auto input : inputs) {
asm("" ::"r"(input));
result = f(input);
Expand Down Expand Up @@ -163,6 +171,10 @@ static LIBC_INLINE uint64_t throughput_baseline(
asm("" ::"llr"(start));

T result{};

#if defined(LIBC_GPU_BENCHMARKS_DISABLE_UNROLL)
#pragma clang loop unroll(disable)
#endif
for (size_t i = 0; i < N; i++) {
T x = inputs1[i];
T y = inputs2[i];
Expand Down Expand Up @@ -195,6 +207,10 @@ static LIBC_INLINE uint64_t throughput(F f, const cpp::array<T, N> &inputs1,
asm("" ::"llr"(start));

T result{};

#if defined(LIBC_GPU_BENCHMARKS_DISABLE_UNROLL)
#pragma clang loop unroll(disable)
#endif
for (size_t i = 0; i < N; i++) {
T x = inputs1[i];
T y = inputs2[i];
Expand Down
Loading