derek/TheRock
1
0 Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
Files
1a182e2dac58879f215c0fad0f5f78c76dcafe56
TheRock/compiler/amd-llvm/llvm/test/Transforms/InstCombine/2006-10-26-VectorReassoc.ll
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

144 lines
8.6 KiB
LLVM
Raw Blame History

; RUN: opt < %s -passes=instcombine -S | FileCheck %s
; (V * C1) * C2 => V * (C1 * C2)
; Verify this doesn't fold when no fast-math-flags are specified
define <4 x float> @test_fmul(<4 x float> %V) {
; CHECK-LABEL: @test_fmul(
; CHECK-NEXT: [[TMP1:%.*]] = fmul <4 x float> [[V:%.*]], <float 1.000000e+00, float 2.000000e+00, float 3.000000e+00, float 4.000000e+00>
; CHECK-NEXT: [[TMP2:%.*]] = fmul <4 x float> [[TMP1]], <float 1.000000e+00, float 2.000000e+05, float -3.000000e+00, float 4.000000e+00>
; CHECK-NEXT: ret <4 x float> [[TMP2]]
%Y = fmul <4 x float> %V, < float 1.000000e+00, float 2.000000e+00, float 3.000000e+00, float 4.000000e+00 >
%Z = fmul <4 x float> %Y, < float 1.000000e+00, float 2.000000e+05, float -3.000000e+00, float 4.000000e+00 >
ret <4 x float> %Z
}
; (V * C1) * C2 => V * (C1 * C2)
; Verify this folds with 'fast'
define <4 x float> @test_fmul_fast(<4 x float> %V) {
; CHECK-LABEL: @test_fmul_fast(
; CHECK-NEXT: [[TMP1:%.*]] = fmul fast <4 x float> [[V:%.*]], <float 1.000000e+00, float 4.000000e+05, float -9.000000e+00, float 1.600000e+01>
; CHECK-NEXT: ret <4 x float> [[TMP1]]
%Y = fmul fast <4 x float> %V, < float 1.000000e+00, float 2.000000e+00, float 3.000000e+00, float 4.000000e+00 >
%Z = fmul fast <4 x float> %Y, < float 1.000000e+00, float 2.000000e+05, float -3.000000e+00, float 4.000000e+00 >
ret <4 x float> %Z
}
; (V * C1) * C2 => V * (C1 * C2)
; Verify this folds with 'reassoc' and 'nsz' ('nsz' not technically required)
define <4 x float> @test_fmul_reassoc_nsz(<4 x float> %V) {
; CHECK-LABEL: @test_fmul_reassoc_nsz(
; CHECK-NEXT: [[TMP1:%.*]] = fmul reassoc nsz <4 x float> [[V:%.*]], <float 1.000000e+00, float 4.000000e+05, float -9.000000e+00, float 1.600000e+01>
; CHECK-NEXT: ret <4 x float> [[TMP1]]
%Y = fmul reassoc nsz <4 x float> %V, < float 1.000000e+00, float 2.000000e+00, float 3.000000e+00, float 4.000000e+00 >
%Z = fmul reassoc nsz <4 x float> %Y, < float 1.000000e+00, float 2.000000e+05, float -3.000000e+00, float 4.000000e+00 >
ret <4 x float> %Z
}
; (V * C1) * C2 => V * (C1 * C2)
define <4 x float> @test_fmul_reassoc(<4 x float> %V) {
; CHECK-LABEL: @test_fmul_reassoc(
; CHECK: [[TMP1:%.*]] = fmul reassoc <4 x float> %V, <float 1.000000e+00, float 4.000000e+05, float -9.000000e+00, float 1.600000e+01>
; CHECK-NEXT: ret <4 x float> [[TMP1]]
%Y = fmul reassoc <4 x float> %V, < float 1.000000e+00, float 2.000000e+00, float 3.000000e+00, float 4.000000e+00 >
%Z = fmul reassoc <4 x float> %Y, < float 1.000000e+00, float 2.000000e+05, float -3.000000e+00, float 4.000000e+00 >
ret <4 x float> %Z
}
; (V + C1) + C2 => V + (C1 + C2)
; Verify this doesn't fold when no fast-math-flags are specified
define <4 x float> @test_fadd(<4 x float> %V) {
; CHECK-LABEL: @test_fadd(
; CHECK-NEXT: [[TMP1:%.*]] = fadd <4 x float> [[V:%.*]], <float 1.000000e+00, float 2.000000e+00, float 3.000000e+00, float 4.000000e+00>
; CHECK-NEXT: [[TMP2:%.*]] = fadd <4 x float> [[TMP1]], <float 1.000000e+00, float 2.000000e+00, float -3.000000e+00, float 4.000000e+00>
; CHECK-NEXT: ret <4 x float> [[TMP2]]
%Y = fadd <4 x float> %V, < float 1.000000e+00, float 2.000000e+00, float 3.000000e+00, float 4.000000e+00 >
%Z = fadd <4 x float> %Y, < float 1.000000e+00, float 2.000000e+00, float -3.000000e+00, float 4.000000e+00 >
ret <4 x float> %Z
}
; (V + C1) + C2 => V + (C1 + C2)
; Verify this folds with 'fast'
define <4 x float> @test_fadd_fast(<4 x float> %V) {
; CHECK-LABEL: @test_fadd_fast(
; CHECK-NEXT: [[TMP1:%.*]] = fadd fast <4 x float> [[V:%.*]], <float 2.000000e+00, float 4.000000e+00, float 0.000000e+00, float 8.000000e+00>
; CHECK-NEXT: ret <4 x float> [[TMP1]]
%Y = fadd fast <4 x float> %V, < float 1.000000e+00, float 2.000000e+00, float 3.000000e+00, float 4.000000e+00 >
%Z = fadd fast <4 x float> %Y, < float 1.000000e+00, float 2.000000e+00, float -3.000000e+00, float 4.000000e+00 >
ret <4 x float> %Z
}
; (V + C1) + C2 => V + (C1 + C2)
; Verify this folds with 'reassoc' and 'nsz' ('nsz' not technically required)
define <4 x float> @test_fadd_reassoc_nsz(<4 x float> %V) {
; CHECK-LABEL: @test_fadd_reassoc_nsz(
; CHECK-NEXT: [[TMP1:%.*]] = fadd reassoc nsz <4 x float> [[V:%.*]], <float 2.000000e+00, float 4.000000e+00, float 0.000000e+00, float 8.000000e+00>
; CHECK-NEXT: ret <4 x float> [[TMP1]]
%Y = fadd reassoc nsz <4 x float> %V, < float 1.000000e+00, float 2.000000e+00, float 3.000000e+00, float 4.000000e+00 >
%Z = fadd reassoc nsz <4 x float> %Y, < float 1.000000e+00, float 2.000000e+00, float -3.000000e+00, float 4.000000e+00 >
ret <4 x float> %Z
}
; (V + C1) + C2 => V + (C1 + C2)
; TODO: This doesn't require 'nsz'. It should fold to V + { 2.0, 4.0, 0.0, 8.0 }
define <4 x float> @test_fadd_reassoc(<4 x float> %V) {
; CHECK-LABEL: @test_fadd_reassoc(
; CHECK-NEXT: [[TMP1:%.*]] = fadd reassoc <4 x float> [[V:%.*]], <float 1.000000e+00, float 2.000000e+00, float 3.000000e+00, float 4.000000e+00>
; CHECK-NEXT: [[TMP2:%.*]] = fadd reassoc <4 x float> [[TMP1]], <float 1.000000e+00, float 2.000000e+00, float -3.000000e+00, float 4.000000e+00>
; CHECK-NEXT: ret <4 x float> [[TMP2]]
%Y = fadd reassoc <4 x float> %V, < float 1.000000e+00, float 2.000000e+00, float 3.000000e+00, float 4.000000e+00 >
%Z = fadd reassoc <4 x float> %Y, < float 1.000000e+00, float 2.000000e+00, float -3.000000e+00, float 4.000000e+00 >
ret <4 x float> %Z
}
; ( A + C1 ) + ( B + -C1 )
; Verify this doesn't fold when no fast-math-flags are specified
define <4 x float> @test_fadds_cancel_(<4 x float> %A, <4 x float> %B) {
; CHECK-LABEL: @test_fadds_cancel_(
; CHECK-NEXT: [[TMP1:%.*]] = fadd <4 x float> [[A:%.*]], <float 1.000000e+00, float 2.000000e+00, float 3.000000e+00, float 4.000000e+00>
; CHECK-NEXT: [[TMP2:%.*]] = fadd <4 x float> [[B:%.*]], <float -1.000000e+00, float -2.000000e+00, float -3.000000e+00, float -4.000000e+00>
; CHECK-NEXT: [[TMP3:%.*]] = fadd <4 x float> [[TMP1]], [[TMP2]]
; CHECK-NEXT: ret <4 x float> [[TMP3]]
%X = fadd <4 x float> %A, < float 1.000000e+00, float 2.000000e+00, float 3.000000e+00, float 4.000000e+00 >
%Y = fadd <4 x float> %B, < float -1.000000e+00, float -2.000000e+00, float -3.000000e+00, float -4.000000e+00 >
%Z = fadd <4 x float> %X, %Y
ret <4 x float> %Z
}
; ( A + C1 ) + ( B + -C1 )
; Verify this folds to 'A + B' with 'fast'
define <4 x float> @test_fadds_cancel_fast(<4 x float> %A, <4 x float> %B) {
; CHECK-LABEL: @test_fadds_cancel_fast(
; CHECK-NEXT: [[TMP1:%.*]] = fadd fast <4 x float> [[A:%.*]], [[B:%.*]]
; CHECK-NEXT: ret <4 x float> [[TMP1]]
%X = fadd fast <4 x float> %A, < float 1.000000e+00, float 2.000000e+00, float 3.000000e+00, float 4.000000e+00 >
%Y = fadd fast <4 x float> %B, < float -1.000000e+00, float -2.000000e+00, float -3.000000e+00, float -4.000000e+00 >
%Z = fadd fast <4 x float> %X, %Y
ret <4 x float> %Z
}
; ( A + C1 ) + ( B + -C1 )
; Verify this folds to 'A + B' with 'reassoc' and 'nsz' ('nsz' is required)
define <4 x float> @test_fadds_cancel_reassoc_nsz(<4 x float> %A, <4 x float> %B) {
; CHECK-LABEL: @test_fadds_cancel_reassoc_nsz(
; CHECK-NEXT: [[TMP1:%.*]] = fadd reassoc nsz <4 x float> [[A:%.*]], [[B:%.*]]
; CHECK-NEXT: ret <4 x float> [[TMP1]]
%X = fadd reassoc nsz <4 x float> %A, < float 1.000000e+00, float 2.000000e+00, float 3.000000e+00, float 4.000000e+00 >
%Y = fadd reassoc nsz <4 x float> %B, < float -1.000000e+00, float -2.000000e+00, float -3.000000e+00, float -4.000000e+00 >
%Z = fadd reassoc nsz <4 x float> %X, %Y
ret <4 x float> %Z
}
; ( A + C1 ) + ( B + -C1 )
; Verify the fold is not done with only 'reassoc' ('nsz' is required).
define <4 x float> @test_fadds_cancel_reassoc(<4 x float> %A, <4 x float> %B) {
; CHECK-LABEL: @test_fadds_cancel_reassoc(
; CHECK-NEXT: [[TMP1:%.*]] = fadd reassoc <4 x float> [[A:%.*]], <float 1.000000e+00, float 2.000000e+00, float 3.000000e+00, float 4.000000e+00>
; CHECK-NEXT: [[TMP2:%.*]] = fadd reassoc <4 x float> [[B:%.*]], <float -1.000000e+00, float -2.000000e+00, float -3.000000e+00, float -4.000000e+00>
; CHECK-NEXT: [[TMP3:%.*]] = fadd reassoc <4 x float> [[TMP1]], [[TMP2]]
; CHECK-NEXT: ret <4 x float> [[TMP3]]
%X = fadd reassoc <4 x float> %A, < float 1.000000e+00, float 2.000000e+00, float 3.000000e+00, float 4.000000e+00 >
%Y = fadd reassoc <4 x float> %B, < float -1.000000e+00, float -2.000000e+00, float -3.000000e+00, float -4.000000e+00 >
%Z = fadd reassoc <4 x float> %X, %Y
ret <4 x float> %Z
}
Reference in new issue View Git Blame Copy Permalink