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
175 lines
12 KiB
LLVM
175 lines
12 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt -S -passes=instcombine < %s | FileCheck %s
|
|
|
|
target triple = "aarch64-unknown-linux-gnu"
|
|
|
|
define <vscale x 4 x i1> @try_combine_svbool_binop_and_0(<vscale x 4 x i1> %a, <vscale x 16 x i1> %b, <vscale x 16 x i1> %c) {
|
|
; CHECK-LABEL: @try_combine_svbool_binop_and_0(
|
|
; CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[B:%.*]])
|
|
; CHECK-NEXT: [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[C:%.*]])
|
|
; CHECK-NEXT: [[TMP3:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.and.z.nxv4i1(<vscale x 4 x i1> [[A:%.*]], <vscale x 4 x i1> [[TMP1]], <vscale x 4 x i1> [[TMP2]])
|
|
; CHECK-NEXT: ret <vscale x 4 x i1> [[TMP3]]
|
|
;
|
|
%t1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> %a)
|
|
%t2 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.and.z.nxv16i1(<vscale x 16 x i1> %t1, <vscale x 16 x i1> %b, <vscale x 16 x i1> %c)
|
|
%t3 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> %t2)
|
|
ret <vscale x 4 x i1> %t3
|
|
}
|
|
|
|
define <vscale x 8 x i1> @try_combine_svbool_binop_and_1(<vscale x 8 x i1> %a, <vscale x 16 x i1> %b) {
|
|
; CHECK-LABEL: @try_combine_svbool_binop_and_1(
|
|
; CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[B:%.*]])
|
|
; CHECK-NEXT: [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.and.z.nxv8i1(<vscale x 8 x i1> [[A:%.*]], <vscale x 8 x i1> [[TMP1]], <vscale x 8 x i1> [[TMP1]])
|
|
; CHECK-NEXT: ret <vscale x 8 x i1> [[TMP2]]
|
|
;
|
|
%t1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> %a)
|
|
%t2 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.and.z.nxv16i1(<vscale x 16 x i1> %t1, <vscale x 16 x i1> %b, <vscale x 16 x i1> %b)
|
|
%t3 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> %t2)
|
|
ret <vscale x 8 x i1> %t3
|
|
}
|
|
|
|
define <vscale x 4 x i1> @try_combine_svbool_binop_and_2(<vscale x 4 x i1> %a, <vscale x 16 x i1> %b) {
|
|
; CHECK-LABEL: @try_combine_svbool_binop_and_2(
|
|
; CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[B:%.*]])
|
|
; CHECK-NEXT: [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.and.z.nxv4i1(<vscale x 4 x i1> [[A:%.*]], <vscale x 4 x i1> [[TMP1]], <vscale x 4 x i1> [[TMP1]])
|
|
; CHECK-NEXT: ret <vscale x 4 x i1> [[TMP2]]
|
|
;
|
|
%t1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> %a)
|
|
%t2 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.and.z.nxv16i1(<vscale x 16 x i1> %t1, <vscale x 16 x i1> %b, <vscale x 16 x i1> %b)
|
|
%t3 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> %t2)
|
|
ret <vscale x 4 x i1> %t3
|
|
}
|
|
|
|
define <vscale x 2 x i1> @try_combine_svbool_binop_and_3(<vscale x 2 x i1> %a, <vscale x 16 x i1> %b) {
|
|
; CHECK-LABEL: @try_combine_svbool_binop_and_3(
|
|
; CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[B:%.*]])
|
|
; CHECK-NEXT: [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.and.z.nxv2i1(<vscale x 2 x i1> [[A:%.*]], <vscale x 2 x i1> [[TMP1]], <vscale x 2 x i1> [[TMP1]])
|
|
; CHECK-NEXT: ret <vscale x 2 x i1> [[TMP2]]
|
|
;
|
|
%t1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> %a)
|
|
%t2 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.and.z.nxv16i1(<vscale x 16 x i1> %t1, <vscale x 16 x i1> %b, <vscale x 16 x i1> %b)
|
|
%t3 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> %t2)
|
|
ret <vscale x 2 x i1> %t3
|
|
}
|
|
|
|
define <vscale x 8 x i1> @try_combine_svbool_binop_bic(<vscale x 8 x i1> %a, <vscale x 16 x i1> %b) {
|
|
; CHECK-LABEL: @try_combine_svbool_binop_bic(
|
|
; CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[B:%.*]])
|
|
; CHECK-NEXT: [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.bic.z.nxv8i1(<vscale x 8 x i1> [[A:%.*]], <vscale x 8 x i1> [[TMP1]], <vscale x 8 x i1> [[TMP1]])
|
|
; CHECK-NEXT: ret <vscale x 8 x i1> [[TMP2]]
|
|
;
|
|
%t1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> %a)
|
|
%t2 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.bic.z.nxv16i1(<vscale x 16 x i1> %t1, <vscale x 16 x i1> %b, <vscale x 16 x i1> %b)
|
|
%t3 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> %t2)
|
|
ret <vscale x 8 x i1> %t3
|
|
}
|
|
|
|
define <vscale x 8 x i1> @try_combine_svbool_binop_eor(<vscale x 8 x i1> %a, <vscale x 16 x i1> %b) {
|
|
; CHECK-LABEL: @try_combine_svbool_binop_eor(
|
|
; CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[B:%.*]])
|
|
; CHECK-NEXT: [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.eor.z.nxv8i1(<vscale x 8 x i1> [[A:%.*]], <vscale x 8 x i1> [[TMP1]], <vscale x 8 x i1> [[TMP1]])
|
|
; CHECK-NEXT: ret <vscale x 8 x i1> [[TMP2]]
|
|
;
|
|
%t1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> %a)
|
|
%t2 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.eor.z.nxv16i1(<vscale x 16 x i1> %t1, <vscale x 16 x i1> %b, <vscale x 16 x i1> %b)
|
|
%t3 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> %t2)
|
|
ret <vscale x 8 x i1> %t3
|
|
}
|
|
|
|
define <vscale x 8 x i1> @try_combine_svbool_binop_nand(<vscale x 8 x i1> %a, <vscale x 16 x i1> %b) {
|
|
; CHECK-LABEL: @try_combine_svbool_binop_nand(
|
|
; CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[B:%.*]])
|
|
; CHECK-NEXT: [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.nand.z.nxv8i1(<vscale x 8 x i1> [[A:%.*]], <vscale x 8 x i1> [[TMP1]], <vscale x 8 x i1> [[TMP1]])
|
|
; CHECK-NEXT: ret <vscale x 8 x i1> [[TMP2]]
|
|
;
|
|
%t1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> %a)
|
|
%t2 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.nand.z.nxv16i1(<vscale x 16 x i1> %t1, <vscale x 16 x i1> %b, <vscale x 16 x i1> %b)
|
|
%t3 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> %t2)
|
|
ret <vscale x 8 x i1> %t3
|
|
}
|
|
|
|
define <vscale x 8 x i1> @try_combine_svbool_binop_nor(<vscale x 8 x i1> %a, <vscale x 16 x i1> %b) {
|
|
; CHECK-LABEL: @try_combine_svbool_binop_nor(
|
|
; CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[B:%.*]])
|
|
; CHECK-NEXT: [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.nor.z.nxv8i1(<vscale x 8 x i1> [[A:%.*]], <vscale x 8 x i1> [[TMP1]], <vscale x 8 x i1> [[TMP1]])
|
|
; CHECK-NEXT: ret <vscale x 8 x i1> [[TMP2]]
|
|
;
|
|
%t1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> %a)
|
|
%t2 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.nor.z.nxv16i1(<vscale x 16 x i1> %t1, <vscale x 16 x i1> %b, <vscale x 16 x i1> %b)
|
|
%t3 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> %t2)
|
|
ret <vscale x 8 x i1> %t3
|
|
}
|
|
|
|
define <vscale x 8 x i1> @try_combine_svbool_binop_orn(<vscale x 8 x i1> %a, <vscale x 16 x i1> %b) {
|
|
; CHECK-LABEL: @try_combine_svbool_binop_orn(
|
|
; CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[B:%.*]])
|
|
; CHECK-NEXT: [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.orn.z.nxv8i1(<vscale x 8 x i1> [[A:%.*]], <vscale x 8 x i1> [[TMP1]], <vscale x 8 x i1> [[TMP1]])
|
|
; CHECK-NEXT: ret <vscale x 8 x i1> [[TMP2]]
|
|
;
|
|
%t1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> %a)
|
|
%t2 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.orn.z.nxv16i1(<vscale x 16 x i1> %t1, <vscale x 16 x i1> %b, <vscale x 16 x i1> %b)
|
|
%t3 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> %t2)
|
|
ret <vscale x 8 x i1> %t3
|
|
}
|
|
|
|
define <vscale x 8 x i1> @try_combine_svbool_binop_orr(<vscale x 8 x i1> %a, <vscale x 16 x i1> %b) {
|
|
; CHECK-LABEL: @try_combine_svbool_binop_orr(
|
|
; CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[B:%.*]])
|
|
; CHECK-NEXT: [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.orr.z.nxv8i1(<vscale x 8 x i1> [[A:%.*]], <vscale x 8 x i1> [[TMP1]], <vscale x 8 x i1> [[TMP1]])
|
|
; CHECK-NEXT: ret <vscale x 8 x i1> [[TMP2]]
|
|
;
|
|
%t1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> %a)
|
|
%t2 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.orr.z.nxv16i1(<vscale x 16 x i1> %t1, <vscale x 16 x i1> %b, <vscale x 16 x i1> %b)
|
|
%t3 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> %t2)
|
|
ret <vscale x 8 x i1> %t3
|
|
}
|
|
|
|
; Verify predicate cast does not hinder "isAllActive" knowledge.
|
|
define <vscale x 8 x half> @try_combine_svbool_binop_fadd(<vscale x 8 x half> %a, <vscale x 8 x half> %b) {
|
|
; CHECK-LABEL: @try_combine_svbool_binop_fadd(
|
|
; CHECK-NEXT: [[T2:%.*]] = fadd <vscale x 8 x half> [[A:%.*]], [[B:%.*]]
|
|
; CHECK-NEXT: ret <vscale x 8 x half> [[T2]]
|
|
;
|
|
%t1 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> splat (i1 true))
|
|
%t2 = tail call <vscale x 8 x half> @llvm.aarch64.sve.fadd.nxv8f16(<vscale x 8 x i1> %t1, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
|
|
ret <vscale x 8 x half> %t2
|
|
}
|
|
|
|
; Verify predicate cast does not hinder "isAllActive" knowledge.
|
|
define <vscale x 4 x float> @try_combine_svbool_binop_fmul(<vscale x 4 x float> %a, <vscale x 4 x float> %b) {
|
|
; CHECK-LABEL: @try_combine_svbool_binop_fmul(
|
|
; CHECK-NEXT: [[T2:%.*]] = fmul <vscale x 4 x float> [[A:%.*]], [[B:%.*]]
|
|
; CHECK-NEXT: ret <vscale x 4 x float> [[T2]]
|
|
;
|
|
%t1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> splat (i1 true))
|
|
%t2 = tail call <vscale x 4 x float> @llvm.aarch64.sve.fmul.nxv4f32(<vscale x 4 x i1> %t1, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
|
|
ret <vscale x 4 x float> %t2
|
|
}
|
|
|
|
; Verify predicate cast does not hinder "isAllActive" knowledge.
|
|
define <vscale x 2 x double> @try_combine_svbool_binop_fsub(<vscale x 2 x double> %a, <vscale x 2 x double> %b) {
|
|
; CHECK-LABEL: @try_combine_svbool_binop_fsub(
|
|
; CHECK-NEXT: [[T2:%.*]] = fsub <vscale x 2 x double> [[A:%.*]], [[B:%.*]]
|
|
; CHECK-NEXT: ret <vscale x 2 x double> [[T2]]
|
|
;
|
|
%t1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> splat (i1 true))
|
|
%t2 = tail call <vscale x 2 x double> @llvm.aarch64.sve.fsub.nxv2f64(<vscale x 2 x i1> %t1, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
|
|
ret <vscale x 2 x double> %t2
|
|
}
|
|
|
|
declare <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1>)
|
|
declare <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1>)
|
|
declare <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1>)
|
|
declare <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1>)
|
|
declare <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1>)
|
|
declare <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1>)
|
|
declare <vscale x 16 x i1> @llvm.aarch64.sve.and.z.nxv16i1(<vscale x 16 x i1>, <vscale x 16 x i1>, <vscale x 16 x i1>)
|
|
declare <vscale x 16 x i1> @llvm.aarch64.sve.bic.z.nxv16i1(<vscale x 16 x i1>, <vscale x 16 x i1>, <vscale x 16 x i1>)
|
|
declare <vscale x 16 x i1> @llvm.aarch64.sve.eor.z.nxv16i1(<vscale x 16 x i1>, <vscale x 16 x i1>, <vscale x 16 x i1>)
|
|
declare <vscale x 16 x i1> @llvm.aarch64.sve.nand.z.nxv16i1(<vscale x 16 x i1>, <vscale x 16 x i1>, <vscale x 16 x i1>)
|
|
declare <vscale x 16 x i1> @llvm.aarch64.sve.nor.z.nxv16i1(<vscale x 16 x i1>, <vscale x 16 x i1>, <vscale x 16 x i1>)
|
|
declare <vscale x 16 x i1> @llvm.aarch64.sve.orn.z.nxv16i1(<vscale x 16 x i1>, <vscale x 16 x i1>, <vscale x 16 x i1>)
|
|
declare <vscale x 16 x i1> @llvm.aarch64.sve.orr.z.nxv16i1(<vscale x 16 x i1>, <vscale x 16 x i1>, <vscale x 16 x i1>)
|
|
|
|
attributes #0 = { "target-features"="+sve" }
|