Files
TheRock/compiler/amd-llvm/clang/test/CodeGenCUDA/shuffle_long_long.cu
T
derek.holloway 7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

62 lines
1.9 KiB
Plaintext

// REQUIRES: nvptx-registered-target
// RUN: %clang_cc1 -triple nvptx64-nvidia-cuda -fcuda-is-device -emit-llvm -target-cpu sm_30 %s -o - | FileCheck %s --check-prefix=NO_SYNC
// RUN: %clang_cc1 -triple nvptx64-nvidia-cuda -fcuda-is-device -emit-llvm -target-cpu sm_30 -target-feature +ptx70 -DSYNC -DCUDA_VERSION=9000 %s -o - | FileCheck %s --check-prefix=SYNC
#include "Inputs/cuda.h"
__device__ void *memcpy(void *dest, const void *src, size_t n);
#define warpSize 32
#include <__clang_cuda_intrinsics.h>
__device__ void use(unsigned long long, long long);
// Test function, 4 shfl calls.
// NO_SYNC: define{{.*}} @_Z14test_long_longv
// NO_SYNC: call noundef i64 @_Z6__shflyii(
// NO_SYNC: call noundef i64 @_Z6__shflxii(
// SYNC: define{{.*}} @_Z14test_long_longv
// SYNC: call noundef i64 @_Z11__shfl_syncjyii(
// SYNC: call noundef i64 @_Z11__shfl_syncjxii(
// unsigned long long -> long long
// NO_SYNC: define{{.*}} @_Z6__shflyii
// NO_SYNC: call noundef i64 @_Z6__shflxii(
// long long -> int + int
// NO_SYNC: define{{.*}} @_Z6__shflxii
// NO_SYNC: call noundef i32 @_Z6__shfliii(
// NO_SYNC: call noundef i32 @_Z6__shfliii(
// NO_SYNC: define{{.*}} @_Z6__shfliii
// NO_SYNC: call i32 @llvm.nvvm.shfl.idx.i32
// unsigned long long -> long long
// SYNC: _Z11__shfl_syncjyii
// SYNC: call noundef i64 @_Z11__shfl_syncjxii(
// long long -> int + int
// SYNC: define{{.*}} @_Z11__shfl_syncjxii
// SYNC: call noundef i32 @_Z11__shfl_syncjiii(
// SYNC: call noundef i32 @_Z11__shfl_syncjiii(
// SYNC: define{{.*}} @_Z11__shfl_syncjiii
// SYNC: call i32 @llvm.nvvm.shfl.sync.idx.i32
__device__ void test_long_long() {
unsigned long long ull = 13;
long long ll = 17;
#ifndef SYNC
ull = __shfl(ull, 7, 32);
ll = __shfl(ll, 7, 32);
use(ull, ll);
#else
ull = __shfl_sync(0x11, ull, 7, 32);
ll = __shfl_sync(0x11, ll, 7, 32);
use(ull, ll);
#endif
}