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
130 lines
6.3 KiB
C
130 lines
6.3 KiB
C
// RUN: %clang_cc1 -flax-vector-conversions=none -ffreestanding %s -triple=x86_64-unknown-linux -target-feature +avx512vl -target-feature +avx512fp16 -fclangir -emit-cir -o %t.cir -Wall -Werror
|
|
// RUN: FileCheck --check-prefix=CIR --input-file=%t.cir %s
|
|
// RUN: %clang_cc1 -flax-vector-conversions=none -ffreestanding %s -triple=x86_64-unknown-linux -target-feature +avx512vl -target-feature +avx512fp16 -fclangir -emit-llvm -o %t.ll -Wall -Werror
|
|
// RUN: FileCheck --check-prefixes=LLVM --input-file=%t.ll %s
|
|
|
|
// RUN: %clang_cc1 -x c -flax-vector-conversions=none -ffreestanding %s -triple=x86_64-unknown-linux -target-feature +avx512vl -target-feature +avx512fp16 -emit-llvm -o - -Wall -Werror | FileCheck %s -check-prefix=OGCG
|
|
// RUN: %clang_cc1 -x c++ -flax-vector-conversions=none -ffreestanding %s -triple=x86_64-unknown-linux -target-feature +avx512vl -target-feature +avx512fp16 -emit-llvm -o - -Wall -Werror | FileCheck %s -check-prefix=OGCG
|
|
#include <immintrin.h>
|
|
|
|
_Float16 test_mm256_reduce_add_ph(__m256h __W) {
|
|
// CIR-LABEL: _mm256_reduce_add_ph
|
|
// CIR: cir.call_llvm_intrinsic "vector.reduce.fadd" %[[R:.*]], %[[V:.*]] : (!cir.f16{{.*}}, !cir.vector<16 x !cir.f16>{{.*}}) -> !cir.f16
|
|
|
|
// CIR-LABEL: test_mm256_reduce_add_ph
|
|
// CIR: cir.call @_mm256_reduce_add_ph(%[[VEC:.*]]) {nobuiltin, nobuiltins = [{{.*}}]} : (!cir.vector<16 x !cir.f16>{{.*}}) -> !cir.f16
|
|
|
|
// LLVM-LABEL: test_mm256_reduce_add_ph
|
|
// LLVM: call half @llvm.vector.reduce.fadd.v16f16(half -0.000000e+00, <16 x half> %{{.*}})
|
|
|
|
// OGCG-LABEL: test_mm256_reduce_add_ph
|
|
// OGCG: call reassoc {{.*}}@llvm.vector.reduce.fadd.v16f16(half -0.000000e+00, <16 x half> %{{.*}})
|
|
return _mm256_reduce_add_ph(__W);
|
|
}
|
|
|
|
_Float16 test_mm256_reduce_mul_ph(__m256h __W) {
|
|
// CIR-LABEL: _mm256_reduce_mul_ph
|
|
// CIR: cir.call_llvm_intrinsic "vector.reduce.fmul" %[[R:.*]], %[[V:.*]] : (!cir.f16{{.*}}, !cir.vector<16 x !cir.f16>{{.*}}) -> !cir.f16
|
|
|
|
// CIR-LABEL: test_mm256_reduce_mul_ph
|
|
// CIR: cir.call @_mm256_reduce_mul_ph(%[[VEC:.*]]) {nobuiltin, nobuiltins = [{{.*}}]} : (!cir.vector<16 x !cir.f16>{{.*}}) -> !cir.f16
|
|
|
|
// LLVM-LABEL: test_mm256_reduce_mul_ph
|
|
// LLVM: call half @llvm.vector.reduce.fmul.v16f16(half 1.000000e+00, <16 x half> %{{.*}})
|
|
|
|
// OGCG-LABEL: test_mm256_reduce_mul_ph
|
|
// OGCG: call reassoc {{.*}}@llvm.vector.reduce.fmul.v16f16(half 1.000000e+00, <16 x half> %{{.*}})
|
|
return _mm256_reduce_mul_ph(__W);
|
|
}
|
|
|
|
_Float16 test_mm256_reduce_max_ph(__m256h __W) {
|
|
// CIR-LABEL: _mm256_reduce_max_ph
|
|
// CIR: cir.call_llvm_intrinsic "vector.reduce.fmax" %[[V:.*]] (!cir.vector<16 x !cir.f16>{{.*}}) -> !cir.f16
|
|
|
|
// CIR-LABEL: test_mm256_reduce_max_ph
|
|
// CIR: cir.call @_mm256_reduce_max_ph(%[[VEC:.*]]) {nobuiltin, nobuiltins = [{{.*}}]} : (!cir.vector<16 x !cir.f16>{{.*}}) -> !cir.f16
|
|
|
|
// LLVM-LABEL: test_mm256_reduce_max_ph
|
|
// LLVM: call half @llvm.vector.reduce.fmax.v16f16(<16 x half> %{{.*}})
|
|
|
|
// OGCG-LABEL: test_mm256_reduce_max_ph
|
|
// OGCG: call nnan {{.*}}@llvm.vector.reduce.fmax.v16f16(<16 x half> %{{.*}})
|
|
return _mm256_reduce_max_ph(__W);
|
|
}
|
|
|
|
_Float16 test_mm256_reduce_min_ph(__m256h __W) {
|
|
// CIR-LABEL: _mm256_reduce_min_ph
|
|
// CIR: cir.call_llvm_intrinsic "vector.reduce.fmin" %[[V:.*]] : (!cir.vector<16 x !cir.f16>{{.*}}) -> !cir.f16
|
|
|
|
// CIR-LABEL: test_mm256_reduce_min_ph
|
|
// CIR: cir.call @_mm256_reduce_min_ph(%[[VEC:.*]]) {nobuiltin, nobuiltins = [{{.*}}]} : (!cir.vector<16 x !cir.f16>{{.*}}) -> !cir.f16
|
|
|
|
// LLVM-LABEL: test_mm256_reduce_min_ph
|
|
// LLVM: call half @llvm.vector.reduce.fmin.v16f16(<16 x half> %{{.*}})
|
|
|
|
// OGCG-LABEL: test_mm256_reduce_min_ph
|
|
// OGCG: call nnan {{.*}}@llvm.vector.reduce.fmin.v16f16(<16 x half> %{{.*}})
|
|
return _mm256_reduce_min_ph(__W);
|
|
}
|
|
|
|
_Float16 test_mm_reduce_add_ph(__m128h __W) {
|
|
// CIR-LABEL: _mm_reduce_add_ph
|
|
// CIR: cir.call_llvm_intrinsic "vector.reduce.fadd" %[[R:.*]], %[[V:.*]] : (!cir.f16{{.*}}, !cir.vector<8 x !cir.f16>{{.*}}) -> !cir.f16
|
|
|
|
// CIR-LABEL: test_mm_reduce_add_ph
|
|
// CIR: cir.call @_mm_reduce_add_ph(%[[VEC:.*]]) {nobuiltin, nobuiltins = [{{.*}}]} : (!cir.vector<8 x !cir.f16>{{.*}}) -> !cir.f16
|
|
|
|
// LLVM-LABEL: test_mm_reduce_add_ph
|
|
// LLVM: call half @llvm.vector.reduce.fadd.v8f16(half -0.000000e+00, <8 x half> %{{.*}})
|
|
|
|
// OGCG-LABEL: test_mm_reduce_add_ph
|
|
// OGCG: call reassoc {{.*}}@llvm.vector.reduce.fadd.v8f16(half -0.000000e+00, <8 x half> %{{.*}})
|
|
return _mm_reduce_add_ph(__W);
|
|
}
|
|
|
|
_Float16 test_mm_reduce_mul_ph(__m128h __W) {
|
|
// CIR-LABEL: _mm_reduce_mul_ph
|
|
// CIR: cir.call_llvm_intrinsic "vector.reduce.fmul" %[[R:.*]], %[[V:.*]] : (!cir.f16{{.*}}, !cir.vector<8 x !cir.f16>{{.*}}) -> !cir.f16
|
|
|
|
// CIR-LABEL: test_mm_reduce_mul_ph
|
|
// CIR: cir.call @_mm_reduce_mul_ph(%[[VEC:.*]]) {nobuiltin, nobuiltins = [{{.*}}]} : (!cir.vector<8 x !cir.f16>{{.*}}) -> !cir.f16
|
|
|
|
// LLVM-LABEL: test_mm_reduce_mul_ph
|
|
// LLVM: call half @llvm.vector.reduce.fmul.v8f16(half 1.000000e+00, <8 x half> %{{.*}})
|
|
|
|
// OGCG-LABEL: test_mm_reduce_mul_ph
|
|
// OGCG: call reassoc {{.*}}@llvm.vector.reduce.fmul.v8f16(half 1.000000e+00, <8 x half> %{{.*}})
|
|
return _mm_reduce_mul_ph(__W);
|
|
}
|
|
|
|
_Float16 test_mm_reduce_max_ph(__m128h __W) {
|
|
// CIR-LABEL: _mm_reduce_max_ph
|
|
// CIR: cir.call_llvm_intrinsic "vector.reduce.fmax" %[[V:.*]] (!cir.vector<8 x !cir.f16>{{.*}}) -> !cir.f16
|
|
|
|
// CIR-LABEL: test_mm_reduce_max_ph
|
|
// CIR: cir.call @_mm_reduce_max_ph(%[[VEC:.*]]) {nobuiltin, nobuiltins = [{{.*}}]} : (!cir.vector<8 x !cir.f16>{{.*}}) -> !cir.f16
|
|
|
|
// LLVM-LABEL: test_mm_reduce_max_ph
|
|
// LLVM: call half @llvm.vector.reduce.fmax.v8f16(<8 x half> %{{.*}})
|
|
|
|
// OGCG-LABEL: test_mm_reduce_max_ph
|
|
// OGCG: call nnan {{.*}}@llvm.vector.reduce.fmax.v8f16(<8 x half> %{{.*}})
|
|
return _mm_reduce_max_ph(__W);
|
|
}
|
|
|
|
_Float16 test_mm_reduce_min_ph(__m128h __W) {
|
|
// CIR-LABEL: _mm_reduce_min_ph
|
|
// CIR: cir.call_llvm_intrinsic "vector.reduce.fmin" %[[V:.*]] : (!cir.vector<8 x !cir.f16>{{.*}}) -> !cir.f16
|
|
|
|
// CIR-LABEL: test_mm_reduce_min_ph
|
|
// CIR: cir.call @_mm_reduce_min_ph(%[[VEC:.*]]) {nobuiltin, nobuiltins = [{{.*}}]} : (!cir.vector<8 x !cir.f16>{{.*}}) -> !cir.f16
|
|
|
|
// LLVM-LABEL: test_mm_reduce_min_ph
|
|
// LLVM: call half @llvm.vector.reduce.fmin.v8f16(<8 x half> %{{.*}})
|
|
|
|
// OGCG-LABEL: test_mm_reduce_min_ph
|
|
// OGCG: call nnan {{.*}}@llvm.vector.reduce.fmin.v8f16(<8 x half> %{{.*}})
|
|
return _mm_reduce_min_ph(__W);
|
|
}
|
|
|