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
72 lines
3.0 KiB
LLVM
72 lines
3.0 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt < %s -passes=instcombine -S | FileCheck %s
|
|
|
|
declare <4 x float> @llvm.x86.vcvtph2ps.128(<8 x i16>)
|
|
declare <8 x float> @llvm.x86.vcvtph2ps.256(<8 x i16>)
|
|
|
|
;
|
|
; Vector Demanded Elts
|
|
;
|
|
|
|
; Only bottom 4 elements required.
|
|
define <4 x float> @demand_vcvtph2ps_128(<8 x i16> %A) {
|
|
; CHECK-LABEL: @demand_vcvtph2ps_128(
|
|
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <8 x i16> [[A:%.*]], <8 x i16> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
|
; CHECK-NEXT: [[TMP2:%.*]] = bitcast <4 x i16> [[TMP1]] to <4 x half>
|
|
; CHECK-NEXT: [[CVTPH2PS:%.*]] = fpext <4 x half> [[TMP2]] to <4 x float>
|
|
; CHECK-NEXT: ret <4 x float> [[CVTPH2PS]]
|
|
;
|
|
%1 = shufflevector <8 x i16> %A, <8 x i16> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3>
|
|
%2 = tail call <4 x float> @llvm.x86.vcvtph2ps.128(<8 x i16> %1)
|
|
ret <4 x float> %2
|
|
}
|
|
|
|
; All 8 elements required.
|
|
define <8 x float> @demand_vcvtph2ps_256(<8 x i16> %A) {
|
|
; CHECK-LABEL: @demand_vcvtph2ps_256(
|
|
; CHECK-NEXT: [[TMP1:%.*]] = bitcast <8 x i16> [[A:%.*]] to <8 x half>
|
|
; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <8 x half> [[TMP1]], <8 x half> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3>
|
|
; CHECK-NEXT: [[CVTPH2PS:%.*]] = fpext <8 x half> [[TMP2]] to <8 x float>
|
|
; CHECK-NEXT: ret <8 x float> [[CVTPH2PS]]
|
|
;
|
|
%1 = shufflevector <8 x i16> %A, <8 x i16> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3>
|
|
%2 = tail call <8 x float> @llvm.x86.vcvtph2ps.256(<8 x i16> %1)
|
|
ret <8 x float> %2
|
|
}
|
|
|
|
;
|
|
; Constant Folding
|
|
;
|
|
|
|
define <4 x float> @fold_vcvtph2ps_128() {
|
|
; CHECK-LABEL: @fold_vcvtph2ps_128(
|
|
; CHECK-NEXT: ret <4 x float> <float 0.000000e+00, float 5.000000e-01, float 1.000000e+00, float -0.000000e+00>
|
|
;
|
|
%1 = tail call <4 x float> @llvm.x86.vcvtph2ps.128(<8 x i16> <i16 0, i16 14336, i16 15360, i16 32768, i16 16384, i16 31743, i16 48128, i16 49152>)
|
|
ret <4 x float> %1
|
|
}
|
|
|
|
define <8 x float> @fold_vcvtph2ps_256() {
|
|
; CHECK-LABEL: @fold_vcvtph2ps_256(
|
|
; CHECK-NEXT: ret <8 x float> <float 0.000000e+00, float 5.000000e-01, float 1.000000e+00, float -0.000000e+00, float 2.000000e+00, float 6.550400e+04, float -1.000000e+00, float -2.000000e+00>
|
|
;
|
|
%1 = tail call <8 x float> @llvm.x86.vcvtph2ps.256(<8 x i16> <i16 0, i16 14336, i16 15360, i16 32768, i16 16384, i16 31743, i16 48128, i16 49152>)
|
|
ret <8 x float> %1
|
|
}
|
|
|
|
define <4 x float> @fold_vcvtph2ps_128_zero() {
|
|
; CHECK-LABEL: @fold_vcvtph2ps_128_zero(
|
|
; CHECK-NEXT: ret <4 x float> zeroinitializer
|
|
;
|
|
%1 = tail call <4 x float> @llvm.x86.vcvtph2ps.128(<8 x i16> <i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0>)
|
|
ret <4 x float> %1
|
|
}
|
|
|
|
define <8 x float> @fold_vcvtph2ps_256_zero() {
|
|
; CHECK-LABEL: @fold_vcvtph2ps_256_zero(
|
|
; CHECK-NEXT: ret <8 x float> zeroinitializer
|
|
;
|
|
%1 = tail call <8 x float> @llvm.x86.vcvtph2ps.256(<8 x i16> <i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0>)
|
|
ret <8 x float> %1
|
|
}
|