diff --git a/libc/benchmarks/gpu/timing/amdgpu/timing.h b/libc/benchmarks/gpu/timing/amdgpu/timing.h
index b4a174f729817..8b92584b39230 100644
--- a/libc/benchmarks/gpu/timing/amdgpu/timing.h
+++ b/libc/benchmarks/gpu/timing/amdgpu/timing.h
@@ -117,6 +117,8 @@ throughput_baseline(const cpp::array<T, N> &inputs) {
   asm("" ::"s"(start));
 
   T result{};
+
+#pragma clang loop unroll(disable)
   for (auto input : inputs) {
     asm("" ::"v"(input));
     result = input;
@@ -146,6 +148,8 @@ static LIBC_INLINE uint64_t throughput(F f, const cpp::array<T, N> &inputs) {
   asm("" ::"s"(start));
 
   T result{};
+
+#pragma clang loop unroll(disable)
   for (auto input : inputs) {
     asm("" ::"v"(input));
     result = f(input);
@@ -174,6 +178,8 @@ static LIBC_INLINE uint64_t throughput_baseline(
   asm("" ::"s"(start));
 
   T result{};
+
+#pragma clang loop unroll(disable)
   for (size_t i = 0; i < N; i++) {
     T x = inputs1[i];
     T y = inputs2[i];
@@ -206,6 +212,8 @@ static LIBC_INLINE uint64_t throughput(F f, const cpp::array<T, N> &inputs1,
   asm("" ::"s"(start));
 
   T result{};
+
+#pragma clang loop unroll(disable)
   for (size_t i = 0; i < N; i++) {
     T x = inputs1[i];
     T y = inputs2[i];
diff --git a/libc/benchmarks/gpu/timing/nvptx/timing.h b/libc/benchmarks/gpu/timing/nvptx/timing.h
index 0c93a67129b8d..944d3732eae65 100644
--- a/libc/benchmarks/gpu/timing/nvptx/timing.h
+++ b/libc/benchmarks/gpu/timing/nvptx/timing.h
@@ -106,6 +106,8 @@ throughput_baseline(const cpp::array<T, N> &inputs) {
   asm("" ::"llr"(start));
 
   T result{};
+
+#pragma clang loop unroll(disable)
   for (auto input : inputs) {
     asm("" ::"r"(input));
     result = input;
@@ -135,6 +137,8 @@ static LIBC_INLINE uint64_t throughput(F f, const cpp::array<T, N> &inputs) {
   asm("" ::"llr"(start));
 
   T result{};
+
+#pragma clang loop unroll(disable)
   for (auto input : inputs) {
     asm("" ::"r"(input));
     result = f(input);
@@ -163,6 +167,8 @@ static LIBC_INLINE uint64_t throughput_baseline(
   asm("" ::"llr"(start));
 
   T result{};
+
+#pragma clang loop unroll(disable)
   for (size_t i = 0; i < N; i++) {
     T x = inputs1[i];
     T y = inputs2[i];
@@ -195,6 +201,8 @@ static LIBC_INLINE uint64_t throughput(F f, const cpp::array<T, N> &inputs1,
   asm("" ::"llr"(start));
 
   T result{};
+
+#pragma clang loop unroll(disable)
   for (size_t i = 0; i < N; i++) {
     T x = inputs1[i];
     T y = inputs2[i];