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
87 lines
3.1 KiB
C
87 lines
3.1 KiB
C
// REQUIRES: arm-registered-target
|
|
// RUN: %clang_cc1 -triple armv8.2a-arm-none-eabi \
|
|
// RUN: -target-feature +neon \
|
|
// RUN: -mfloat-abi hard \
|
|
// RUN: -disable-O0-optnone -emit-llvm -o - %s | opt -S -passes=mem2reg,sroa \
|
|
// RUN: | FileCheck %s
|
|
|
|
#include <arm_neon.h>
|
|
|
|
// CHECK-LABEL: @test_vadd_p8(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = xor <8 x i8> [[A:%.*]], [[B:%.*]]
|
|
// CHECK-NEXT: ret <8 x i8> [[TMP0]]
|
|
//
|
|
poly8x8_t test_vadd_p8(poly8x8_t a, poly8x8_t b) {
|
|
return vadd_p8 (a, b);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vadd_p16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast <4 x i16> [[A:%.*]] to <8 x i8>
|
|
// CHECK-NEXT: [[TMP1:%.*]] = bitcast <4 x i16> [[B:%.*]] to <8 x i8>
|
|
// CHECK-NEXT: [[TMP2:%.*]] = xor <8 x i8> [[TMP0]], [[TMP1]]
|
|
// CHECK-NEXT: [[TMP3:%.*]] = bitcast <8 x i8> [[TMP2]] to <4 x i16>
|
|
// CHECK-NEXT: ret <4 x i16> [[TMP3]]
|
|
//
|
|
poly16x4_t test_vadd_p16(poly16x4_t a, poly16x4_t b) {
|
|
return vadd_p16 (a, b);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vadd_p64(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast <1 x i64> [[A:%.*]] to <8 x i8>
|
|
// CHECK-NEXT: [[TMP1:%.*]] = bitcast <1 x i64> [[B:%.*]] to <8 x i8>
|
|
// CHECK-NEXT: [[TMP2:%.*]] = xor <8 x i8> [[TMP0]], [[TMP1]]
|
|
// CHECK-NEXT: [[TMP3:%.*]] = bitcast <8 x i8> [[TMP2]] to <1 x i64>
|
|
// CHECK-NEXT: ret <1 x i64> [[TMP3]]
|
|
//
|
|
poly64x1_t test_vadd_p64(poly64x1_t a, poly64x1_t b) {
|
|
return vadd_p64(a, b);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vaddq_p8(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = xor <16 x i8> [[A:%.*]], [[B:%.*]]
|
|
// CHECK-NEXT: ret <16 x i8> [[TMP0]]
|
|
//
|
|
poly8x16_t test_vaddq_p8(poly8x16_t a, poly8x16_t b){
|
|
return vaddq_p8(a, b);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vaddq_p16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast <8 x i16> [[A:%.*]] to <16 x i8>
|
|
// CHECK-NEXT: [[TMP1:%.*]] = bitcast <8 x i16> [[B:%.*]] to <16 x i8>
|
|
// CHECK-NEXT: [[TMP2:%.*]] = xor <16 x i8> [[TMP0]], [[TMP1]]
|
|
// CHECK-NEXT: [[TMP3:%.*]] = bitcast <16 x i8> [[TMP2]] to <8 x i16>
|
|
// CHECK-NEXT: ret <8 x i16> [[TMP3]]
|
|
//
|
|
poly16x8_t test_vaddq_p16(poly16x8_t a, poly16x8_t b){
|
|
return vaddq_p16(a, b);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vaddq_p64(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast <2 x i64> [[A:%.*]] to <16 x i8>
|
|
// CHECK-NEXT: [[TMP1:%.*]] = bitcast <2 x i64> [[B:%.*]] to <16 x i8>
|
|
// CHECK-NEXT: [[TMP2:%.*]] = xor <16 x i8> [[TMP0]], [[TMP1]]
|
|
// CHECK-NEXT: [[TMP3:%.*]] = bitcast <16 x i8> [[TMP2]] to <2 x i64>
|
|
// CHECK-NEXT: ret <2 x i64> [[TMP3]]
|
|
//
|
|
poly64x2_t test_vaddq_p64(poly64x2_t a, poly64x2_t b){
|
|
return vaddq_p64(a, b);
|
|
}
|
|
|
|
// TODO: poly128_t not implemented on aarch32
|
|
// CHCK-LABEL: @test_vaddq_p128(
|
|
// CHCK-NEXT: entry:
|
|
// CHCK-NEXT: [[TMP0:%.*]] = bitcast i128 [[A:%.*]] to <16 x i8>
|
|
// CHCK-NEXT: [[TMP1:%.*]] = bitcast i128 [[B:%.*]] to <16 x i8>
|
|
// CHCK-NEXT: [[TMP2:%.*]] = xor <16 x i8> [[TMP0]], [[TMP1]]
|
|
// CHCK-NEXT: [[TMP3:%.*]] = bitcast <16 x i8> [[TMP2]] to i128
|
|
// CHCK-NEXT: ret i128 [[TMP3]]
|
|
//
|
|
//poly128_t test_vaddq_p128 (poly128_t a, poly128_t b){
|
|
// return vaddq_p128(a, b);
|