Disable loop unrolling in the throughput benchmark loop by default

Author: leandrolcampos

libc/benchmarks/gpu/CMakeLists.txt

@@ -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"
@@ -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
@@ -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__)

libc/benchmarks/gpu/timing/amdgpu/timing.h

@@ -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;
@@ -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);
@@ -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];
@@ -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];

libc/benchmarks/gpu/timing/nvptx/timing.h

@@ -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;
@@ -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);
@@ -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];
@@ -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];