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
63 lines
3.2 KiB
C++
63 lines
3.2 KiB
C++
// Test frontend handling of nontemporal builtins.
|
|
// RUN: %clang_cc1 -triple x86_64-apple-darwin -emit-llvm %s -o - | FileCheck %s
|
|
|
|
signed char sc;
|
|
unsigned char uc;
|
|
signed short ss;
|
|
unsigned short us;
|
|
signed int si;
|
|
unsigned int ui;
|
|
signed long long sll;
|
|
unsigned long long ull;
|
|
float f1, f2;
|
|
double d1, d2;
|
|
float __attribute__((vector_size(16))) vf1, vf2;
|
|
char __attribute__((vector_size(8))) vc1, vc2;
|
|
bool b1, b2;
|
|
|
|
void test_all_sizes(void) // CHECK-LABEL: test_all_sizes
|
|
{
|
|
__builtin_nontemporal_store(true, &b1); // CHECK: store i8 1, ptr @b1, align 1, !nontemporal
|
|
__builtin_nontemporal_store(b1, &b2); // CHECK: store i8{{.*}}, align 1, !nontemporal
|
|
__builtin_nontemporal_store(1, &uc); // CHECK: store i8{{.*}}align 1, !nontemporal
|
|
__builtin_nontemporal_store(1, &sc); // CHECK: store i8{{.*}}align 1, !nontemporal
|
|
__builtin_nontemporal_store(1, &us); // CHECK: store i16{{.*}}align 2, !nontemporal
|
|
__builtin_nontemporal_store(1, &ss); // CHECK: store i16{{.*}}align 2, !nontemporal
|
|
__builtin_nontemporal_store(1, &ui); // CHECK: store i32{{.*}}align 4, !nontemporal
|
|
__builtin_nontemporal_store(1, &si); // CHECK: store i32{{.*}}align 4, !nontemporal
|
|
__builtin_nontemporal_store(1, &ull); // CHECK: store i64{{.*}}align 8, !nontemporal
|
|
__builtin_nontemporal_store(1, &sll); // CHECK: store i64{{.*}}align 8, !nontemporal
|
|
__builtin_nontemporal_store(1.0, &f1); // CHECK: store float{{.*}}align 4, !nontemporal
|
|
__builtin_nontemporal_store(1.0, &d1); // CHECK: store double{{.*}}align 8, !nontemporal
|
|
__builtin_nontemporal_store(vf1, &vf2); // CHECK: store <4 x float>{{.*}}align 16, !nontemporal
|
|
__builtin_nontemporal_store(vc1, &vc2); // CHECK: store <8 x i8>{{.*}}align 8, !nontemporal
|
|
|
|
b1 = __builtin_nontemporal_load(&b2); // CHECK: load i8{{.*}}align 1, !nontemporal
|
|
uc = __builtin_nontemporal_load(&sc); // CHECK: load i8{{.*}}align 1, !nontemporal
|
|
sc = __builtin_nontemporal_load(&uc); // CHECK: load i8{{.*}}align 1, !nontemporal
|
|
us = __builtin_nontemporal_load(&ss); // CHECK: load i16{{.*}}align 2, !nontemporal
|
|
ss = __builtin_nontemporal_load(&us); // CHECK: load i16{{.*}}align 2, !nontemporal
|
|
ui = __builtin_nontemporal_load(&si); // CHECK: load i32{{.*}}align 4, !nontemporal
|
|
si = __builtin_nontemporal_load(&ui); // CHECK: load i32{{.*}}align 4, !nontemporal
|
|
ull = __builtin_nontemporal_load(&sll); // CHECK: load i64{{.*}}align 8, !nontemporal
|
|
sll = __builtin_nontemporal_load(&ull); // CHECK: load i64{{.*}}align 8, !nontemporal
|
|
f1 = __builtin_nontemporal_load(&f2); // CHECK: load float{{.*}}align 4, !nontemporal
|
|
d1 = __builtin_nontemporal_load(&d2); // CHECK: load double{{.*}}align 8, !nontemporal
|
|
vf2 = __builtin_nontemporal_load(&vf1); // CHECK: load <4 x float>{{.*}}align 16, !nontemporal
|
|
vc2 = __builtin_nontemporal_load(&vc1); // CHECK: load <8 x i8>{{.*}}align 8, !nontemporal
|
|
}
|
|
|
|
struct S { char c[16]; };
|
|
S x;
|
|
|
|
typedef int v4si __attribute__ ((vector_size(16)));
|
|
|
|
// CHECK-LABEL: define void @_Z14test_alignmentv()
|
|
// CHECK: load <4 x i32>, ptr @x, align 1, !nontemporal
|
|
// CHECK: store <4 x i32> %1, ptr @x, align 1, !nontemporal
|
|
|
|
void test_alignment() {
|
|
auto t = __builtin_nontemporal_load((v4si*)x.c);
|
|
__builtin_nontemporal_store(t, (v4si*)x.c);
|
|
}
|