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
157 lines
6.0 KiB
YAML
157 lines
6.0 KiB
YAML
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
|
|
# RUN: llc -mtriple=x86_64-linux-gnu -run-pass=instruction-select -verify-machineinstrs %s -o - | FileCheck %s --check-prefix=SSE
|
|
# RUN: llc -mtriple=x86_64-linux-gnu -mattr=+avx -run-pass=instruction-select -verify-machineinstrs %s -o - | FileCheck %s --check-prefix=AVX
|
|
# RUN: llc -mtriple=x86_64-linux-gnu -mattr=+avx512f -run-pass=instruction-select -verify-machineinstrs %s -o - | FileCheck %s --check-prefix=AVX512F
|
|
# RUN: llc -mtriple=x86_64-linux-gnu -mattr=+avx512f -mattr=+avx512vl -run-pass=instruction-select -verify-machineinstrs %s -o - | FileCheck %s --check-prefix=AVX512VL
|
|
--- |
|
|
|
|
define float @test_fmul_float(float %arg1, float %arg2) {
|
|
%ret = fmul float %arg1, %arg2
|
|
ret float %ret
|
|
}
|
|
|
|
define double @test_fmul_double(double %arg1, double %arg2) {
|
|
%ret = fmul double %arg1, %arg2
|
|
ret double %ret
|
|
}
|
|
|
|
...
|
|
---
|
|
name: test_fmul_float
|
|
alignment: 16
|
|
legalized: true
|
|
regBankSelected: true
|
|
#
|
|
registers:
|
|
- { id: 0, class: vecr, preferred-register: '' }
|
|
- { id: 1, class: vecr, preferred-register: '' }
|
|
- { id: 2, class: vecr, preferred-register: '' }
|
|
- { id: 3, class: vecr, preferred-register: '' }
|
|
- { id: 4, class: vecr, preferred-register: '' }
|
|
- { id: 5, class: vecr, preferred-register: '' }
|
|
liveins:
|
|
fixedStack:
|
|
stack:
|
|
constants:
|
|
#
|
|
#
|
|
body: |
|
|
bb.1 (%ir-block.0):
|
|
liveins: $xmm0, $xmm1
|
|
|
|
; SSE-LABEL: name: test_fmul_float
|
|
; SSE: [[COPY:%[0-9]+]]:vr128 = COPY $xmm0
|
|
; SSE: [[COPY1:%[0-9]+]]:fr32 = COPY [[COPY]]
|
|
; SSE: [[COPY2:%[0-9]+]]:vr128 = COPY $xmm1
|
|
; SSE: [[COPY3:%[0-9]+]]:fr32 = COPY [[COPY2]]
|
|
; SSE: %4:fr32 = nofpexcept MULSSrr [[COPY1]], [[COPY3]], implicit $mxcsr
|
|
; SSE: [[COPY4:%[0-9]+]]:vr128 = COPY %4
|
|
; SSE: $xmm0 = COPY [[COPY4]]
|
|
; SSE: RET 0, implicit $xmm0
|
|
; AVX-LABEL: name: test_fmul_float
|
|
; AVX: [[COPY:%[0-9]+]]:vr128 = COPY $xmm0
|
|
; AVX: [[COPY1:%[0-9]+]]:fr32 = COPY [[COPY]]
|
|
; AVX: [[COPY2:%[0-9]+]]:vr128 = COPY $xmm1
|
|
; AVX: [[COPY3:%[0-9]+]]:fr32 = COPY [[COPY2]]
|
|
; AVX: %4:fr32 = nofpexcept VMULSSrr [[COPY1]], [[COPY3]], implicit $mxcsr
|
|
; AVX: [[COPY4:%[0-9]+]]:vr128 = COPY %4
|
|
; AVX: $xmm0 = COPY [[COPY4]]
|
|
; AVX: RET 0, implicit $xmm0
|
|
; AVX512F-LABEL: name: test_fmul_float
|
|
; AVX512F: [[COPY:%[0-9]+]]:vr128x = COPY $xmm0
|
|
; AVX512F: [[COPY1:%[0-9]+]]:fr32x = COPY [[COPY]]
|
|
; AVX512F: [[COPY2:%[0-9]+]]:vr128x = COPY $xmm1
|
|
; AVX512F: [[COPY3:%[0-9]+]]:fr32x = COPY [[COPY2]]
|
|
; AVX512F: %4:fr32x = nofpexcept VMULSSZrr [[COPY1]], [[COPY3]], implicit $mxcsr
|
|
; AVX512F: [[COPY4:%[0-9]+]]:vr128x = COPY %4
|
|
; AVX512F: $xmm0 = COPY [[COPY4]]
|
|
; AVX512F: RET 0, implicit $xmm0
|
|
; AVX512VL-LABEL: name: test_fmul_float
|
|
; AVX512VL: [[COPY:%[0-9]+]]:vr128x = COPY $xmm0
|
|
; AVX512VL: [[COPY1:%[0-9]+]]:fr32x = COPY [[COPY]]
|
|
; AVX512VL: [[COPY2:%[0-9]+]]:vr128x = COPY $xmm1
|
|
; AVX512VL: [[COPY3:%[0-9]+]]:fr32x = COPY [[COPY2]]
|
|
; AVX512VL: %4:fr32x = nofpexcept VMULSSZrr [[COPY1]], [[COPY3]], implicit $mxcsr
|
|
; AVX512VL: [[COPY4:%[0-9]+]]:vr128x = COPY %4
|
|
; AVX512VL: $xmm0 = COPY [[COPY4]]
|
|
; AVX512VL: RET 0, implicit $xmm0
|
|
%2:vecr(s128) = COPY $xmm0
|
|
%0:vecr(s32) = G_TRUNC %2(s128)
|
|
%3:vecr(s128) = COPY $xmm1
|
|
%1:vecr(s32) = G_TRUNC %3(s128)
|
|
%4:vecr(s32) = G_FMUL %0, %1
|
|
%5:vecr(s128) = G_ANYEXT %4(s32)
|
|
$xmm0 = COPY %5(s128)
|
|
RET 0, implicit $xmm0
|
|
|
|
...
|
|
---
|
|
name: test_fmul_double
|
|
alignment: 16
|
|
legalized: true
|
|
regBankSelected: true
|
|
#
|
|
registers:
|
|
- { id: 0, class: vecr, preferred-register: '' }
|
|
- { id: 1, class: vecr, preferred-register: '' }
|
|
- { id: 2, class: vecr, preferred-register: '' }
|
|
- { id: 3, class: vecr, preferred-register: '' }
|
|
- { id: 4, class: vecr, preferred-register: '' }
|
|
- { id: 5, class: vecr, preferred-register: '' }
|
|
liveins:
|
|
fixedStack:
|
|
stack:
|
|
constants:
|
|
#
|
|
#
|
|
body: |
|
|
bb.1 (%ir-block.0):
|
|
liveins: $xmm0, $xmm1
|
|
|
|
; SSE-LABEL: name: test_fmul_double
|
|
; SSE: [[COPY:%[0-9]+]]:vr128 = COPY $xmm0
|
|
; SSE: [[COPY1:%[0-9]+]]:fr64 = COPY [[COPY]]
|
|
; SSE: [[COPY2:%[0-9]+]]:vr128 = COPY $xmm1
|
|
; SSE: [[COPY3:%[0-9]+]]:fr64 = COPY [[COPY2]]
|
|
; SSE: %4:fr64 = nofpexcept MULSDrr [[COPY1]], [[COPY3]], implicit $mxcsr
|
|
; SSE: [[COPY4:%[0-9]+]]:vr128 = COPY %4
|
|
; SSE: $xmm0 = COPY [[COPY4]]
|
|
; SSE: RET 0, implicit $xmm0
|
|
; AVX-LABEL: name: test_fmul_double
|
|
; AVX: [[COPY:%[0-9]+]]:vr128 = COPY $xmm0
|
|
; AVX: [[COPY1:%[0-9]+]]:fr64 = COPY [[COPY]]
|
|
; AVX: [[COPY2:%[0-9]+]]:vr128 = COPY $xmm1
|
|
; AVX: [[COPY3:%[0-9]+]]:fr64 = COPY [[COPY2]]
|
|
; AVX: %4:fr64 = nofpexcept VMULSDrr [[COPY1]], [[COPY3]], implicit $mxcsr
|
|
; AVX: [[COPY4:%[0-9]+]]:vr128 = COPY %4
|
|
; AVX: $xmm0 = COPY [[COPY4]]
|
|
; AVX: RET 0, implicit $xmm0
|
|
; AVX512F-LABEL: name: test_fmul_double
|
|
; AVX512F: [[COPY:%[0-9]+]]:vr128x = COPY $xmm0
|
|
; AVX512F: [[COPY1:%[0-9]+]]:fr64x = COPY [[COPY]]
|
|
; AVX512F: [[COPY2:%[0-9]+]]:vr128x = COPY $xmm1
|
|
; AVX512F: [[COPY3:%[0-9]+]]:fr64x = COPY [[COPY2]]
|
|
; AVX512F: %4:fr64x = nofpexcept VMULSDZrr [[COPY1]], [[COPY3]], implicit $mxcsr
|
|
; AVX512F: [[COPY4:%[0-9]+]]:vr128x = COPY %4
|
|
; AVX512F: $xmm0 = COPY [[COPY4]]
|
|
; AVX512F: RET 0, implicit $xmm0
|
|
; AVX512VL-LABEL: name: test_fmul_double
|
|
; AVX512VL: [[COPY:%[0-9]+]]:vr128x = COPY $xmm0
|
|
; AVX512VL: [[COPY1:%[0-9]+]]:fr64x = COPY [[COPY]]
|
|
; AVX512VL: [[COPY2:%[0-9]+]]:vr128x = COPY $xmm1
|
|
; AVX512VL: [[COPY3:%[0-9]+]]:fr64x = COPY [[COPY2]]
|
|
; AVX512VL: %4:fr64x = nofpexcept VMULSDZrr [[COPY1]], [[COPY3]], implicit $mxcsr
|
|
; AVX512VL: [[COPY4:%[0-9]+]]:vr128x = COPY %4
|
|
; AVX512VL: $xmm0 = COPY [[COPY4]]
|
|
; AVX512VL: RET 0, implicit $xmm0
|
|
%2:vecr(s128) = COPY $xmm0
|
|
%0:vecr(s64) = G_TRUNC %2(s128)
|
|
%3:vecr(s128) = COPY $xmm1
|
|
%1:vecr(s64) = G_TRUNC %3(s128)
|
|
%4:vecr(s64) = G_FMUL %0, %1
|
|
%5:vecr(s128) = G_ANYEXT %4(s64)
|
|
$xmm0 = COPY %5(s128)
|
|
RET 0, implicit $xmm0
|
|
|
|
...
|