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
143 lines
5.3 KiB
LLVM
143 lines
5.3 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt < %s -passes=instcombine -S | FileCheck %s
|
|
|
|
define double @x(i32 %a, i32 %b) {
|
|
; CHECK-LABEL: @x(
|
|
; CHECK-NEXT: [[M:%.*]] = lshr i32 [[A:%.*]], 24
|
|
; CHECK-NEXT: [[N:%.*]] = and i32 [[M]], [[B:%.*]]
|
|
; CHECK-NEXT: [[TMP1:%.*]] = add nuw nsw i32 [[N]], 1
|
|
; CHECK-NEXT: [[P:%.*]] = uitofp nneg i32 [[TMP1]] to double
|
|
; CHECK-NEXT: ret double [[P]]
|
|
;
|
|
%m = lshr i32 %a, 24
|
|
%n = and i32 %m, %b
|
|
%o = sitofp i32 %n to double
|
|
%p = fadd double %o, 1.0
|
|
ret double %p
|
|
}
|
|
|
|
define double @test(i32 %a) {
|
|
; CHECK-LABEL: @test(
|
|
; CHECK-NEXT: [[A_AND:%.*]] = and i32 [[A:%.*]], 1073741823
|
|
; CHECK-NEXT: [[TMP1:%.*]] = add nuw nsw i32 [[A_AND]], 1
|
|
; CHECK-NEXT: [[RES:%.*]] = uitofp nneg i32 [[TMP1]] to double
|
|
; CHECK-NEXT: ret double [[RES]]
|
|
;
|
|
; Drop two highest bits to guarantee that %a + 1 doesn't overflow
|
|
%a_and = and i32 %a, 1073741823
|
|
%a_and_fp = sitofp i32 %a_and to double
|
|
%res = fadd double %a_and_fp, 1.0
|
|
ret double %res
|
|
}
|
|
|
|
define float @test_neg(i32 %a) {
|
|
; CHECK-LABEL: @test_neg(
|
|
; CHECK-NEXT: [[A_AND:%.*]] = and i32 [[A:%.*]], 1073741823
|
|
; CHECK-NEXT: [[A_AND_FP:%.*]] = uitofp nneg i32 [[A_AND]] to float
|
|
; CHECK-NEXT: [[RES:%.*]] = fadd float [[A_AND_FP]], 1.000000e+00
|
|
; CHECK-NEXT: ret float [[RES]]
|
|
;
|
|
; Drop two highest bits to guarantee that %a + 1 doesn't overflow
|
|
%a_and = and i32 %a, 1073741823
|
|
%a_and_fp = sitofp i32 %a_and to float
|
|
%res = fadd float %a_and_fp, 1.0
|
|
ret float %res
|
|
}
|
|
|
|
define double @test_2(i32 %a, i32 %b) {
|
|
; CHECK-LABEL: @test_2(
|
|
; CHECK-NEXT: [[A_AND:%.*]] = and i32 [[A:%.*]], 1073741823
|
|
; CHECK-NEXT: [[B_AND:%.*]] = and i32 [[B:%.*]], 1073741823
|
|
; CHECK-NEXT: [[TMP1:%.*]] = add nuw nsw i32 [[A_AND]], [[B_AND]]
|
|
; CHECK-NEXT: [[RES:%.*]] = uitofp nneg i32 [[TMP1]] to double
|
|
; CHECK-NEXT: ret double [[RES]]
|
|
;
|
|
; Drop two highest bits to guarantee that %a + %b doesn't overflow
|
|
%a_and = and i32 %a, 1073741823
|
|
%b_and = and i32 %b, 1073741823
|
|
|
|
%a_and_fp = sitofp i32 %a_and to double
|
|
%b_and_fp = sitofp i32 %b_and to double
|
|
|
|
%res = fadd double %a_and_fp, %b_and_fp
|
|
ret double %res
|
|
}
|
|
|
|
define float @test_2_neg(i32 %a, i32 %b) {
|
|
; CHECK-LABEL: @test_2_neg(
|
|
; CHECK-NEXT: [[A_AND:%.*]] = and i32 [[A:%.*]], 1073741823
|
|
; CHECK-NEXT: [[B_AND:%.*]] = and i32 [[B:%.*]], 1073741823
|
|
; CHECK-NEXT: [[A_AND_FP:%.*]] = uitofp nneg i32 [[A_AND]] to float
|
|
; CHECK-NEXT: [[B_AND_FP:%.*]] = uitofp nneg i32 [[B_AND]] to float
|
|
; CHECK-NEXT: [[RES:%.*]] = fadd float [[A_AND_FP]], [[B_AND_FP]]
|
|
; CHECK-NEXT: ret float [[RES]]
|
|
;
|
|
; Drop two highest bits to guarantee that %a + %b doesn't overflow
|
|
%a_and = and i32 %a, 1073741823
|
|
%b_and = and i32 %b, 1073741823
|
|
|
|
%a_and_fp = sitofp i32 %a_and to float
|
|
%b_and_fp = sitofp i32 %b_and to float
|
|
|
|
%res = fadd float %a_and_fp, %b_and_fp
|
|
ret float %res
|
|
}
|
|
|
|
; can be represented in float.
|
|
define float @test_3(i32 %a, i32 %b) {
|
|
; CHECK-LABEL: @test_3(
|
|
; CHECK-NEXT: [[M:%.*]] = lshr i32 [[A:%.*]], 24
|
|
; CHECK-NEXT: [[N:%.*]] = and i32 [[M]], [[B:%.*]]
|
|
; CHECK-NEXT: [[TMP1:%.*]] = add nuw nsw i32 [[N]], 1
|
|
; CHECK-NEXT: [[P:%.*]] = uitofp nneg i32 [[TMP1]] to float
|
|
; CHECK-NEXT: ret float [[P]]
|
|
;
|
|
%m = lshr i32 %a, 24
|
|
%n = and i32 %m, %b
|
|
%o = sitofp i32 %n to float
|
|
%p = fadd float %o, 1.0
|
|
ret float %p
|
|
}
|
|
|
|
; Don't perform the fold on vector operations, as the integer op may be
|
|
; much more expensive than the float op in that case.
|
|
define <4 x double> @test_4(<4 x i32> %a, <4 x i32> %b) {
|
|
; CHECK-LABEL: @test_4(
|
|
; CHECK-NEXT: [[A_AND:%.*]] = and <4 x i32> [[A:%.*]], splat (i32 1073741823)
|
|
; CHECK-NEXT: [[B_AND:%.*]] = and <4 x i32> [[B:%.*]], splat (i32 1073741823)
|
|
; CHECK-NEXT: [[A_AND_FP:%.*]] = uitofp nneg <4 x i32> [[A_AND]] to <4 x double>
|
|
; CHECK-NEXT: [[B_AND_FP:%.*]] = uitofp nneg <4 x i32> [[B_AND]] to <4 x double>
|
|
; CHECK-NEXT: [[RES:%.*]] = fadd <4 x double> [[A_AND_FP]], [[B_AND_FP]]
|
|
; CHECK-NEXT: ret <4 x double> [[RES]]
|
|
;
|
|
; Drop two highest bits to guarantee that %a + %b doesn't overflow
|
|
%a_and = and <4 x i32> %a, <i32 1073741823, i32 1073741823, i32 1073741823, i32 1073741823>
|
|
%b_and = and <4 x i32> %b, <i32 1073741823, i32 1073741823, i32 1073741823, i32 1073741823>
|
|
|
|
%a_and_fp = sitofp <4 x i32> %a_and to <4 x double>
|
|
%b_and_fp = sitofp <4 x i32> %b_and to <4 x double>
|
|
|
|
%res = fadd <4 x double> %a_and_fp, %b_and_fp
|
|
ret <4 x double> %res
|
|
}
|
|
|
|
define <4 x float> @test_4_neg(<4 x i32> %a, <4 x i32> %b) {
|
|
; CHECK-LABEL: @test_4_neg(
|
|
; CHECK-NEXT: [[A_AND:%.*]] = and <4 x i32> [[A:%.*]], splat (i32 1073741823)
|
|
; CHECK-NEXT: [[B_AND:%.*]] = and <4 x i32> [[B:%.*]], splat (i32 1073741823)
|
|
; CHECK-NEXT: [[A_AND_FP:%.*]] = uitofp nneg <4 x i32> [[A_AND]] to <4 x float>
|
|
; CHECK-NEXT: [[B_AND_FP:%.*]] = uitofp nneg <4 x i32> [[B_AND]] to <4 x float>
|
|
; CHECK-NEXT: [[RES:%.*]] = fadd <4 x float> [[A_AND_FP]], [[B_AND_FP]]
|
|
; CHECK-NEXT: ret <4 x float> [[RES]]
|
|
;
|
|
; Drop two highest bits to guarantee that %a + %b doesn't overflow
|
|
%a_and = and <4 x i32> %a, <i32 1073741823, i32 1073741823, i32 1073741823, i32 1073741823>
|
|
%b_and = and <4 x i32> %b, <i32 1073741823, i32 1073741823, i32 1073741823, i32 1073741823>
|
|
|
|
%a_and_fp = sitofp <4 x i32> %a_and to <4 x float>
|
|
%b_and_fp = sitofp <4 x i32> %b_and to <4 x float>
|
|
|
|
%res = fadd <4 x float> %a_and_fp, %b_and_fp
|
|
ret <4 x float> %res
|
|
}
|