derek/TheRock
1
0 Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
Files
1a182e2dac58879f215c0fad0f5f78c76dcafe56
TheRock/compiler/amd-llvm/clang/test/CodeGen/AArch64/neon-ldst-one-rcpc3.c
T
derek.holloway 7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
Details
CodeQL / Analyze (python) (push) Canceled after 0s
Details
pre-commit / pre-commit (push) Canceled after 0s
Details
Multi-Arch CI / setup (push) Canceled after 0s
Details
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Details
Setup (Multi-Arch) / setup (push) Canceled after 0s
Details
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Details
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
Details
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Details
Multi-Arch CI / CI Summary (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Details
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Details
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
Details
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

208 lines
8.8 KiB
C
Raw Blame History

// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
// RUN: %clang_cc1 -triple aarch64 -target-feature +neon \
// RUN: -target-feature +rcpc3 -disable-O0-optnone -emit-llvm -o - %s \
// RUN: | opt -S -passes=mem2reg,sroa | FileCheck %s
// REQUIRES: aarch64-registered-target
#include <arm_neon.h>
// CHECK-LABEL: @test_vldap1q_lane_u64(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = bitcast <2 x i64> [[B:%.*]] to <16 x i8>
// CHECK-NEXT: [[TMP1:%.*]] = bitcast <16 x i8> [[TMP0]] to <2 x i64>
// CHECK-NEXT: [[TMP2:%.*]] = load atomic i64, ptr [[A:%.*]] acquire, align 8
// CHECK-NEXT: [[VLDAP1_LANE:%.*]] = insertelement <2 x i64> [[TMP1]], i64 [[TMP2]], i32 1
// CHECK-NEXT: ret <2 x i64> [[VLDAP1_LANE]]
//
uint64x2_t test_vldap1q_lane_u64(uint64_t *a, uint64x2_t b) {
return vldap1q_lane_u64(a, b, 1);
}
// CHECK-LABEL: @test_vldap1q_lane_s64(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = bitcast <2 x i64> [[B:%.*]] to <16 x i8>
// CHECK-NEXT: [[TMP1:%.*]] = bitcast <16 x i8> [[TMP0]] to <2 x i64>
// CHECK-NEXT: [[TMP2:%.*]] = load atomic i64, ptr [[A:%.*]] acquire, align 8
// CHECK-NEXT: [[VLDAP1_LANE:%.*]] = insertelement <2 x i64> [[TMP1]], i64 [[TMP2]], i32 1
// CHECK-NEXT: ret <2 x i64> [[VLDAP1_LANE]]
//
int64x2_t test_vldap1q_lane_s64(int64_t *a, int64x2_t b) {
return vldap1q_lane_s64(a, b, 1);
}
// CHECK-LABEL: @test_vldap1q_lane_f64(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = bitcast <2 x double> [[B:%.*]] to <2 x i64>
// CHECK-NEXT: [[TMP1:%.*]] = bitcast <2 x i64> [[TMP0]] to <16 x i8>
// CHECK-NEXT: [[TMP2:%.*]] = bitcast <16 x i8> [[TMP1]] to <2 x double>
// CHECK-NEXT: [[TMP3:%.*]] = load atomic double, ptr [[A:%.*]] acquire, align 8
// CHECK-NEXT: [[VLDAP1_LANE:%.*]] = insertelement <2 x double> [[TMP2]], double [[TMP3]], i32 1
// CHECK-NEXT: ret <2 x double> [[VLDAP1_LANE]]
//
float64x2_t test_vldap1q_lane_f64(float64_t *a, float64x2_t b) {
return vldap1q_lane_f64(a, b, 1);
}
// CHECK-LABEL: @test_vldap1q_lane_p64(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = bitcast <2 x i64> [[B:%.*]] to <16 x i8>
// CHECK-NEXT: [[TMP1:%.*]] = bitcast <16 x i8> [[TMP0]] to <2 x i64>
// CHECK-NEXT: [[TMP2:%.*]] = load atomic i64, ptr [[A:%.*]] acquire, align 8
// CHECK-NEXT: [[VLDAP1_LANE:%.*]] = insertelement <2 x i64> [[TMP1]], i64 [[TMP2]], i32 1
// CHECK-NEXT: ret <2 x i64> [[VLDAP1_LANE]]
//
poly64x2_t test_vldap1q_lane_p64(poly64_t *a, poly64x2_t b) {
return vldap1q_lane_p64(a, b, 1);
}
// CHECK-LABEL: @test_vldap1_lane_u64(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = bitcast <1 x i64> [[B:%.*]] to <8 x i8>
// CHECK-NEXT: [[TMP1:%.*]] = bitcast <8 x i8> [[TMP0]] to <1 x i64>
// CHECK-NEXT: [[TMP2:%.*]] = load atomic i64, ptr [[A:%.*]] acquire, align 8
// CHECK-NEXT: [[VLDAP1_LANE:%.*]] = insertelement <1 x i64> [[TMP1]], i64 [[TMP2]], i32 0
// CHECK-NEXT: ret <1 x i64> [[VLDAP1_LANE]]
//
uint64x1_t test_vldap1_lane_u64(uint64_t *a, uint64x1_t b) {
return vldap1_lane_u64(a, b, 0);
}
// CHECK-LABEL: @test_vldap1_lane_s64(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = bitcast <1 x i64> [[B:%.*]] to <8 x i8>
// CHECK-NEXT: [[TMP1:%.*]] = bitcast <8 x i8> [[TMP0]] to <1 x i64>
// CHECK-NEXT: [[TMP2:%.*]] = load atomic i64, ptr [[A:%.*]] acquire, align 8
// CHECK-NEXT: [[VLDAP1_LANE:%.*]] = insertelement <1 x i64> [[TMP1]], i64 [[TMP2]], i32 0
// CHECK-NEXT: ret <1 x i64> [[VLDAP1_LANE]]
//
int64x1_t test_vldap1_lane_s64(int64_t *a, int64x1_t b) {
return vldap1_lane_s64(a, b, 0);
}
// CHECK-LABEL: @test_vldap1_lane_f64(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = bitcast <1 x double> [[B:%.*]] to i64
// CHECK-NEXT: [[__S1_SROA_0_0_VEC_INSERT:%.*]] = insertelement <1 x i64> undef, i64 [[TMP0]], i32 0
// CHECK-NEXT: [[TMP1:%.*]] = bitcast <1 x i64> [[__S1_SROA_0_0_VEC_INSERT]] to <8 x i8>
// CHECK-NEXT: [[TMP2:%.*]] = bitcast <8 x i8> [[TMP1]] to <1 x double>
// CHECK-NEXT: [[TMP3:%.*]] = load atomic double, ptr [[A:%.*]] acquire, align 8
// CHECK-NEXT: [[VLDAP1_LANE:%.*]] = insertelement <1 x double> [[TMP2]], double [[TMP3]], i32 0
// CHECK-NEXT: ret <1 x double> [[VLDAP1_LANE]]
//
float64x1_t test_vldap1_lane_f64(float64_t *a, float64x1_t b) {
return vldap1_lane_f64(a, b, 0);
}
// CHECK-LABEL: @test_vldap1_lane_p64(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = bitcast <1 x i64> [[B:%.*]] to <8 x i8>
// CHECK-NEXT: [[TMP1:%.*]] = bitcast <8 x i8> [[TMP0]] to <1 x i64>
// CHECK-NEXT: [[TMP2:%.*]] = load atomic i64, ptr [[A:%.*]] acquire, align 8
// CHECK-NEXT: [[VLDAP1_LANE:%.*]] = insertelement <1 x i64> [[TMP1]], i64 [[TMP2]], i32 0
// CHECK-NEXT: ret <1 x i64> [[VLDAP1_LANE]]
//
poly64x1_t test_vldap1_lane_p64(poly64_t *a, poly64x1_t b) {
return vldap1_lane_p64(a, b, 0);
}
// CHECK-LABEL: @test_vstl1q_lane_u64(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = bitcast <2 x i64> [[B:%.*]] to <16 x i8>
// CHECK-NEXT: [[TMP1:%.*]] = bitcast <16 x i8> [[TMP0]] to <2 x i64>
// CHECK-NEXT: [[TMP2:%.*]] = extractelement <2 x i64> [[TMP1]], i32 1
// CHECK-NEXT: store atomic i64 [[TMP2]], ptr [[A:%.*]] release, align 8
// CHECK-NEXT: ret void
//
void test_vstl1q_lane_u64(uint64_t *a, uint64x2_t b) {
vstl1q_lane_u64(a, b, 1);
}
// CHECK-LABEL: @test_vstl1q_lane_s64(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = bitcast <2 x i64> [[B:%.*]] to <16 x i8>
// CHECK-NEXT: [[TMP1:%.*]] = bitcast <16 x i8> [[TMP0]] to <2 x i64>
// CHECK-NEXT: [[TMP2:%.*]] = extractelement <2 x i64> [[TMP1]], i32 1
// CHECK-NEXT: store atomic i64 [[TMP2]], ptr [[A:%.*]] release, align 8
// CHECK-NEXT: ret void
//
void test_vstl1q_lane_s64(int64_t *a, int64x2_t b) {
vstl1q_lane_s64(a, b, 1);
}
// CHECK-LABEL: @test_vstl1q_lane_f64(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = bitcast <2 x double> [[B:%.*]] to <2 x i64>
// CHECK-NEXT: [[TMP1:%.*]] = bitcast <2 x i64> [[TMP0]] to <16 x i8>
// CHECK-NEXT: [[TMP2:%.*]] = bitcast <16 x i8> [[TMP1]] to <2 x double>
// CHECK-NEXT: [[TMP3:%.*]] = extractelement <2 x double> [[TMP2]], i32 1
// CHECK-NEXT: store atomic double [[TMP3]], ptr [[A:%.*]] release, align 8
// CHECK-NEXT: ret void
//
void test_vstl1q_lane_f64(float64_t *a, float64x2_t b) {
vstl1q_lane_f64(a, b, 1);
}
// CHECK-LABEL: @test_vstl1q_lane_p64(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = bitcast <2 x i64> [[B:%.*]] to <16 x i8>
// CHECK-NEXT: [[TMP1:%.*]] = bitcast <16 x i8> [[TMP0]] to <2 x i64>
// CHECK-NEXT: [[TMP2:%.*]] = extractelement <2 x i64> [[TMP1]], i32 1
// CHECK-NEXT: store atomic i64 [[TMP2]], ptr [[A:%.*]] release, align 8
// CHECK-NEXT: ret void
//
void test_vstl1q_lane_p64(poly64_t *a, poly64x2_t b) {
vstl1q_lane_p64(a, b, 1);
}
// CHECK-LABEL: @test_vstl1_lane_u64(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = bitcast <1 x i64> [[B:%.*]] to <8 x i8>
// CHECK-NEXT: [[TMP1:%.*]] = bitcast <8 x i8> [[TMP0]] to <1 x i64>
// CHECK-NEXT: [[TMP2:%.*]] = extractelement <1 x i64> [[TMP1]], i32 0
// CHECK-NEXT: store atomic i64 [[TMP2]], ptr [[A:%.*]] release, align 8
// CHECK-NEXT: ret void
//
void test_vstl1_lane_u64(uint64_t *a, uint64x1_t b) {
vstl1_lane_u64(a, b, 0);
}
// CHECK-LABEL: @test_vstl1_lane_s64(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = bitcast <1 x i64> [[B:%.*]] to <8 x i8>
// CHECK-NEXT: [[TMP1:%.*]] = bitcast <8 x i8> [[TMP0]] to <1 x i64>
// CHECK-NEXT: [[TMP2:%.*]] = extractelement <1 x i64> [[TMP1]], i32 0
// CHECK-NEXT: store atomic i64 [[TMP2]], ptr [[A:%.*]] release, align 8
// CHECK-NEXT: ret void
//
void test_vstl1_lane_s64(int64_t *a, int64x1_t b) {
vstl1_lane_s64(a, b, 0);
}
// CHECK-LABEL: @test_vstl1_lane_f64(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = bitcast <1 x double> [[B:%.*]] to i64
// CHECK-NEXT: [[__S1_SROA_0_0_VEC_INSERT:%.*]] = insertelement <1 x i64> undef, i64 [[TMP0]], i32 0
// CHECK-NEXT: [[TMP1:%.*]] = bitcast <1 x i64> [[__S1_SROA_0_0_VEC_INSERT]] to <8 x i8>
// CHECK-NEXT: [[TMP2:%.*]] = bitcast <8 x i8> [[TMP1]] to <1 x double>
// CHECK-NEXT: [[TMP3:%.*]] = extractelement <1 x double> [[TMP2]], i32 0
// CHECK-NEXT: store atomic double [[TMP3]], ptr [[A:%.*]] release, align 8
// CHECK-NEXT: ret void
//
void test_vstl1_lane_f64(float64_t *a, float64x1_t b) {
vstl1_lane_f64(a, b, 0);
}
// CHECK-LABEL: @test_vstl1_lane_p64(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = bitcast <1 x i64> [[B:%.*]] to <8 x i8>
// CHECK-NEXT: [[TMP1:%.*]] = bitcast <8 x i8> [[TMP0]] to <1 x i64>
// CHECK-NEXT: [[TMP2:%.*]] = extractelement <1 x i64> [[TMP1]], i32 0
// CHECK-NEXT: store atomic i64 [[TMP2]], ptr [[A:%.*]] release, align 8
// CHECK-NEXT: ret void
//
void test_vstl1_lane_p64(poly64_t *a, poly64x1_t b) {
vstl1_lane_p64(a, b, 0);
}
Reference in new issue View Git Blame Copy Permalink