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
125 lines
7.0 KiB
LLVM
125 lines
7.0 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt < %s -passes=instcombine -S | FileCheck %s
|
|
|
|
; llvm.vector.insert canonicalizes to shufflevector in the fixed case. In the
|
|
; scalable case, we lower to the INSERT_SUBVECTOR ISD node.
|
|
|
|
declare <8 x i32> @llvm.vector.insert.v8i32.v2i32(<8 x i32> %vec, <2 x i32> %subvec, i64 %idx)
|
|
declare <8 x i32> @llvm.vector.insert.v8i32.v3i32(<8 x i32> %vec, <3 x i32> %subvec, i64 %idx)
|
|
declare <8 x i32> @llvm.vector.insert.v8i32.v4i32(<8 x i32> %vec, <4 x i32> %subvec, i64 %idx)
|
|
declare <8 x i32> @llvm.vector.insert.v8i32.v8i32(<8 x i32> %vec, <8 x i32> %subvec, i64 %idx)
|
|
declare <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v4i32(<vscale x 4 x i32> %vec, <4 x i32> %subvec, i64 %idx)
|
|
|
|
; ============================================================================ ;
|
|
; Trivial cases
|
|
; ============================================================================ ;
|
|
|
|
; An insert that entirely overwrites an <n x ty> with another <n x ty> is a
|
|
; nop.
|
|
define <8 x i32> @trivial_nop(<8 x i32> %vec, <8 x i32> %subvec) {
|
|
; CHECK-LABEL: @trivial_nop(
|
|
; CHECK-NEXT: ret <8 x i32> [[SUBVEC:%.*]]
|
|
;
|
|
%1 = call <8 x i32> @llvm.vector.insert.v8i32.v8i32(<8 x i32> %vec, <8 x i32> %subvec, i64 0)
|
|
ret <8 x i32> %1
|
|
}
|
|
|
|
; ============================================================================ ;
|
|
; Valid canonicalizations
|
|
; ============================================================================ ;
|
|
|
|
define <8 x i32> @valid_insertion_a(<8 x i32> %vec, <2 x i32> %subvec) {
|
|
; CHECK-LABEL: @valid_insertion_a(
|
|
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <2 x i32> [[SUBVEC:%.*]], <2 x i32> poison, <8 x i32> <i32 0, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
|
|
; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <8 x i32> [[TMP1]], <8 x i32> [[VEC:%.*]], <8 x i32> <i32 0, i32 1, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
|
|
; CHECK-NEXT: ret <8 x i32> [[TMP2]]
|
|
;
|
|
%1 = call <8 x i32> @llvm.vector.insert.v8i32.v2i32(<8 x i32> %vec, <2 x i32> %subvec, i64 0)
|
|
ret <8 x i32> %1
|
|
}
|
|
|
|
define <8 x i32> @valid_insertion_b(<8 x i32> %vec, <2 x i32> %subvec) {
|
|
; CHECK-LABEL: @valid_insertion_b(
|
|
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <2 x i32> [[SUBVEC:%.*]], <2 x i32> poison, <8 x i32> <i32 0, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
|
|
; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <8 x i32> [[VEC:%.*]], <8 x i32> [[TMP1]], <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
|
|
; CHECK-NEXT: ret <8 x i32> [[TMP2]]
|
|
;
|
|
%1 = call <8 x i32> @llvm.vector.insert.v8i32.v2i32(<8 x i32> %vec, <2 x i32> %subvec, i64 2)
|
|
ret <8 x i32> %1
|
|
}
|
|
|
|
define <8 x i32> @valid_insertion_c(<8 x i32> %vec, <2 x i32> %subvec) {
|
|
; CHECK-LABEL: @valid_insertion_c(
|
|
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <2 x i32> [[SUBVEC:%.*]], <2 x i32> poison, <8 x i32> <i32 0, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
|
|
; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <8 x i32> [[VEC:%.*]], <8 x i32> [[TMP1]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
|
|
; CHECK-NEXT: ret <8 x i32> [[TMP2]]
|
|
;
|
|
%1 = call <8 x i32> @llvm.vector.insert.v8i32.v2i32(<8 x i32> %vec, <2 x i32> %subvec, i64 4)
|
|
ret <8 x i32> %1
|
|
}
|
|
|
|
define <8 x i32> @valid_insertion_d(<8 x i32> %vec, <2 x i32> %subvec) {
|
|
; CHECK-LABEL: @valid_insertion_d(
|
|
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <2 x i32> [[SUBVEC:%.*]], <2 x i32> poison, <8 x i32> <i32 0, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
|
|
; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <8 x i32> [[VEC:%.*]], <8 x i32> [[TMP1]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
|
|
; CHECK-NEXT: ret <8 x i32> [[TMP2]]
|
|
;
|
|
%1 = call <8 x i32> @llvm.vector.insert.v8i32.v2i32(<8 x i32> %vec, <2 x i32> %subvec, i64 6)
|
|
ret <8 x i32> %1
|
|
}
|
|
|
|
define <8 x i32> @valid_insertion_e(<8 x i32> %vec, <4 x i32> %subvec) {
|
|
; CHECK-LABEL: @valid_insertion_e(
|
|
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <4 x i32> [[SUBVEC:%.*]], <4 x i32> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison>
|
|
; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <8 x i32> [[TMP1]], <8 x i32> [[VEC:%.*]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 12, i32 13, i32 14, i32 15>
|
|
; CHECK-NEXT: ret <8 x i32> [[TMP2]]
|
|
;
|
|
%1 = call <8 x i32> @llvm.vector.insert.v8i32.v4i32(<8 x i32> %vec, <4 x i32> %subvec, i64 0)
|
|
ret <8 x i32> %1
|
|
}
|
|
|
|
define <8 x i32> @valid_insertion_f(<8 x i32> %vec, <4 x i32> %subvec) {
|
|
; CHECK-LABEL: @valid_insertion_f(
|
|
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <4 x i32> [[SUBVEC:%.*]], <4 x i32> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison>
|
|
; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <8 x i32> [[VEC:%.*]], <8 x i32> [[TMP1]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
|
|
; CHECK-NEXT: ret <8 x i32> [[TMP2]]
|
|
;
|
|
%1 = call <8 x i32> @llvm.vector.insert.v8i32.v4i32(<8 x i32> %vec, <4 x i32> %subvec, i64 4)
|
|
ret <8 x i32> %1
|
|
}
|
|
|
|
define <8 x i32> @valid_insertion_g(<8 x i32> %vec, <3 x i32> %subvec) {
|
|
; CHECK-LABEL: @valid_insertion_g(
|
|
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <3 x i32> [[SUBVEC:%.*]], <3 x i32> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
|
|
; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <8 x i32> [[TMP1]], <8 x i32> [[VEC:%.*]], <8 x i32> <i32 0, i32 1, i32 2, i32 11, i32 12, i32 13, i32 14, i32 15>
|
|
; CHECK-NEXT: ret <8 x i32> [[TMP2]]
|
|
;
|
|
%1 = call <8 x i32> @llvm.vector.insert.v8i32.v3i32(<8 x i32> %vec, <3 x i32> %subvec, i64 0)
|
|
ret <8 x i32> %1
|
|
}
|
|
|
|
define <8 x i32> @valid_insertion_h(<8 x i32> %vec, <3 x i32> %subvec) {
|
|
; CHECK-LABEL: @valid_insertion_h(
|
|
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <3 x i32> [[SUBVEC:%.*]], <3 x i32> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
|
|
; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <8 x i32> [[VEC:%.*]], <8 x i32> [[TMP1]], <8 x i32> <i32 0, i32 1, i32 2, i32 8, i32 9, i32 10, i32 6, i32 7>
|
|
; CHECK-NEXT: ret <8 x i32> [[TMP2]]
|
|
;
|
|
%1 = call <8 x i32> @llvm.vector.insert.v8i32.v3i32(<8 x i32> %vec, <3 x i32> %subvec, i64 3)
|
|
ret <8 x i32> %1
|
|
}
|
|
|
|
; ============================================================================ ;
|
|
; Scalable cases
|
|
; ============================================================================ ;
|
|
|
|
; Scalable insertions should not be canonicalized. This will be lowered to the
|
|
; INSERT_SUBVECTOR ISD node later.
|
|
define <vscale x 4 x i32> @scalable_insert(<vscale x 4 x i32> %vec, <4 x i32> %subvec) {
|
|
; CHECK-LABEL: @scalable_insert(
|
|
; CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v4i32(<vscale x 4 x i32> [[VEC:%.*]], <4 x i32> [[SUBVEC:%.*]], i64 0)
|
|
; CHECK-NEXT: ret <vscale x 4 x i32> [[TMP1]]
|
|
;
|
|
%1 = call <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v4i32(<vscale x 4 x i32> %vec, <4 x i32> %subvec, i64 0)
|
|
ret <vscale x 4 x i32> %1
|
|
}
|