Files
TheRock/compiler/amd-llvm/llvm/test/Transforms/LoopVectorize/widen-gep-all-indices-invariant.ll
T
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
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

180 lines
8.2 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 2
; RUN: opt -passes=loop-vectorize -force-vector-width=4 -force-vector-interleave=1 -S %s | FileCheck %s
define void @pr63340(ptr %A, ptr %B) {
; CHECK-LABEL: define void @pr63340
; CHECK-SAME: (ptr [[A:%.*]], ptr [[B:%.*]]) {
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: [[TMP0:%.*]] = getelementptr i8, ptr [[A]], i64 1
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x ptr> poison, ptr [[TMP0]], i64 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x ptr> [[BROADCAST_SPLATINSERT]], <4 x ptr> poison, <4 x i32> zeroinitializer
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[OFFSET_IDX:%.*]] = trunc i32 [[INDEX]] to i8
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds ptr, ptr [[B]], i8 [[OFFSET_IDX]]
; CHECK-NEXT: store <4 x ptr> [[BROADCAST_SPLAT]], ptr [[TMP1]], align 8
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 4
; CHECK-NEXT: [[TMP2:%.*]] = icmp eq i32 [[INDEX_NEXT]], 128
; CHECK-NEXT: br i1 [[TMP2]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: br label [[EXIT:%.*]]
; CHECK: exit:
; CHECK-NEXT: ret void
;
entry:
br label %loop.header
loop.header:
%iv = phi i8 [ 0, %entry ], [ %iv.next, %loop.latch ]
br label %loop.latch
loop.latch:
%f.0.i = phi ptr [ %A, %loop.header ]
%gep = getelementptr i8, ptr %f.0.i, i64 1
%gep.B = getelementptr inbounds ptr, ptr %B, i8 %iv
store ptr %gep, ptr %gep.B
%iv.next = add i8 %iv, 1
%ec = icmp eq i8 %iv.next, 128
br i1 %ec, label %exit, label %loop.header
exit:
ret void
}
; FIXME: Redundant broadcast in vector.ph only feeds an extract only.
define void @wide_gep_index_invariant(ptr noalias %dst, ptr noalias %src, i64 %n) {
; CHECK-LABEL: define void @wide_gep_index_invariant
; CHECK-SAME: (ptr noalias [[DST:%.*]], ptr noalias [[SRC:%.*]], i64 [[N:%.*]]) {
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[SRC]], align 8
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr float, ptr [[TMP0]], i64 [[N]]
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x ptr> poison, ptr [[TMP1]], i64 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x ptr> [[BROADCAST_SPLATINSERT]], <4 x ptr> poison, <4 x i32> zeroinitializer
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr ptr, ptr [[DST]], i64 [[INDEX]]
; CHECK-NEXT: store <4 x ptr> [[BROADCAST_SPLAT]], ptr [[TMP2]], align 8
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT: [[TMP3:%.*]] = icmp eq i64 [[INDEX_NEXT]], 100
; CHECK-NEXT: br i1 [[TMP3]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: br label [[EXIT:%.*]]
; CHECK: exit:
; CHECK-NEXT: ret void
;
entry:
br label %loop
loop:
%iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
%l = load ptr, ptr %src, align 8
%gep.l = getelementptr float, ptr %l, i64 %n
%gep.dst = getelementptr ptr, ptr %dst, i64 %iv
store ptr %gep.l, ptr %gep.dst, align 8
%iv.next = add nuw nsw i64 %iv, 1
%ec = icmp eq i64 %iv.next, 100
br i1 %ec, label %exit, label %loop
exit:
ret void
}
define void @wide_gep_multiple_indices_some_invariant(ptr noalias %dst, ptr noalias %src, i32 %x) {
; CHECK-LABEL: define void @wide_gep_multiple_indices_some_invariant
; CHECK-SAME: (ptr noalias [[DST:%.*]], ptr noalias [[SRC:%.*]], i32 [[X:%.*]]) {
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[VEC_IND:%.*]] = phi <4 x i64> [ <i64 0, i64 1, i64 2, i64 3>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[SRC]], align 8
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x ptr> poison, ptr [[TMP0]], i64 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x ptr> [[BROADCAST_SPLATINSERT]], <4 x ptr> poison, <4 x i32> zeroinitializer
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr [10 x float], <4 x ptr> [[BROADCAST_SPLAT]], i32 [[X]], <4 x i64> [[VEC_IND]]
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr ptr, ptr [[DST]], i64 [[INDEX]]
; CHECK-NEXT: store <4 x ptr> [[TMP1]], ptr [[TMP2]], align 8
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT: [[VEC_IND_NEXT]] = add nuw nsw <4 x i64> [[VEC_IND]], splat (i64 4)
; CHECK-NEXT: [[TMP3:%.*]] = icmp eq i64 [[INDEX_NEXT]], 100
; CHECK-NEXT: br i1 [[TMP3]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: br label [[EXIT:%.*]]
; CHECK: exit:
; CHECK-NEXT: ret void
;
entry:
br label %loop
loop:
%iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
%l = load ptr, ptr %src, align 8
%gep.l = getelementptr [10 x float], ptr %l, i32 %x, i64 %iv
%gep.dst = getelementptr ptr, ptr %dst, i64 %iv
store ptr %gep.l, ptr %gep.dst, align 8
%iv.next = add nuw nsw i64 %iv, 1
%ec = icmp eq i64 %iv.next, 100
br i1 %ec, label %exit, label %loop
exit:
ret void
}
define void @pr173761(i8 %c, ptr %p, ptr noalias %q, ptr noalias %r) {
; CHECK-LABEL: define void @pr173761
; CHECK-SAME: (i8 [[C:%.*]], ptr [[P:%.*]], ptr noalias [[Q:%.*]], ptr noalias [[R:%.*]]) {
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i8> poison, i8 [[C]], i64 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i8> [[BROADCAST_SPLATINSERT]], <4 x i8> poison, <4 x i32> zeroinitializer
; CHECK-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <4 x ptr> poison, ptr [[P]], i64 0
; CHECK-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <4 x ptr> [[BROADCAST_SPLATINSERT1]], <4 x ptr> poison, <4 x i32> zeroinitializer
; CHECK-NEXT: [[TMP0:%.*]] = getelementptr inbounds nuw i8, ptr [[P]], i64 16
; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <4 x ptr> poison, ptr [[TMP0]], i64 0
; CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <4 x ptr> [[DOTSPLATINSERT]], <4 x ptr> poison, <4 x i32> zeroinitializer
; CHECK-NEXT: [[TMP1:%.*]] = trunc <4 x i8> [[BROADCAST_SPLAT]] to <4 x i1>
; CHECK-NEXT: [[TMP2:%.*]] = select <4 x i1> [[TMP1]], <4 x ptr> [[DOTSPLAT]], <4 x ptr> [[BROADCAST_SPLAT2]]
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP3:%.*]] = load i8, ptr [[P]], align 1
; CHECK-NEXT: store i8 [[TMP3]], ptr [[R]], align 1
; CHECK-NEXT: [[TMP4:%.*]] = extractelement <4 x ptr> [[TMP2]], i64 3
; CHECK-NEXT: [[TMP5:%.*]] = load i8, ptr [[TMP4]], align 1
; CHECK-NEXT: store i8 [[TMP5]], ptr [[Q]], align 1
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 4
; CHECK-NEXT: [[TMP6:%.*]] = icmp eq i32 [[INDEX_NEXT]], 1024
; CHECK-NEXT: br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: br label [[EXIT:%.*]]
; CHECK: exit:
; CHECK-NEXT: ret void
;
entry:
br label %loop
loop:
%iv = phi i16 [ 0, %entry ], [ %iv.next, %loop ]
%ld.p = load i8, ptr %p
store i8 %ld.p, ptr %r
%gep.inv = getelementptr inbounds nuw i8, ptr %p, i64 16
%c.trunc = trunc i8 %c to i1
%sel.inv = select i1 %c.trunc, ptr %gep.inv, ptr %p
%ld.sel.inv = load i8, ptr %sel.inv
store i8 %ld.sel.inv, ptr %q
%iv.next = add i16 %iv, 1
%ec = icmp ne i16 %iv.next, 1024
br i1 %ec, label %loop, label %exit
exit:
ret void
}