Skip to content

[SLP]Initial support for non-power-of-2 vectorization #151530

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 3 commits into
base: main
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
447 changes: 267 additions & 180 deletions llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp

Large diffs are not rendered by default.

Original file line number Diff line number Diff line change
Expand Up @@ -7,18 +7,20 @@ target triple = "aarch64-unknown-linux-gnu"
define void @foo(ptr %0) {
; CHECK-LABEL: @foo(
; CHECK-NEXT: vector.scevcheck:
; CHECK-NEXT: [[TMP1:%.*]] = insertelement <2 x ptr> <ptr poison, ptr null>, ptr [[TMP0:%.*]], i32 0
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr i8, <2 x ptr> [[TMP1]], <2 x i64> splat (i64 4)
; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <2 x ptr> [[TMP2]], <2 x ptr> poison, <4 x i32> <i32 0, i32 0, i32 0, i32 1>
; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr i8, ptr [[TMP0:%.*]], i64 4
; CHECK-NEXT: [[SCEVGEP3:%.*]] = getelementptr i8, ptr null, i64 4
; CHECK-NEXT: [[TMP1:%.*]] = insertelement <4 x ptr> poison, ptr [[TMP0]], i32 1
; CHECK-NEXT: [[TMP2:%.*]] = insertelement <4 x ptr> [[TMP1]], ptr [[SCEVGEP]], i32 0
; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <4 x ptr> [[TMP2]], <4 x ptr> poison, <4 x i32> <i32 0, i32 0, i32 0, i32 1>
; CHECK-NEXT: [[TMP4:%.*]] = icmp ult <4 x ptr> [[TMP3]], zeroinitializer
; CHECK-NEXT: [[TMP5:%.*]] = and <4 x i1> [[TMP4]], zeroinitializer
; CHECK-NEXT: [[TMP6:%.*]] = insertelement <4 x ptr> poison, ptr [[TMP0]], i32 0
; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <4 x ptr> [[TMP6]], <4 x ptr> poison, <4 x i32> zeroinitializer
; CHECK-NEXT: [[TMP7:%.*]] = shufflevector <4 x ptr> [[TMP3]], <4 x ptr> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP11:%.*]] = shufflevector <4 x ptr> [[TMP5]], <4 x ptr> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP12:%.*]] = shufflevector <4 x ptr> [[TMP3]], <4 x ptr> [[TMP5]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; CHECK-NEXT: [[TMP8:%.*]] = shufflevector <8 x ptr> [[TMP12]], <8 x ptr> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 4, i32 5, i32 6, i32 7, i32 3>
; CHECK-NEXT: [[TMP9:%.*]] = icmp ult <8 x ptr> [[TMP8]], zeroinitializer
; CHECK-NEXT: [[TMP10:%.*]] = and <8 x i1> [[TMP9]], zeroinitializer
; CHECK-NEXT: [[OP_RDX:%.*]] = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> [[TMP10]])
; CHECK-NEXT: [[TMP7:%.*]] = insertelement <4 x ptr> [[TMP6]], ptr [[SCEVGEP3]], i32 1
; CHECK-NEXT: [[TMP8:%.*]] = shufflevector <4 x ptr> [[TMP7]], <4 x ptr> poison, <4 x i32> <i32 0, i32 0, i32 0, i32 1>
; CHECK-NEXT: [[TMP9:%.*]] = icmp ult <4 x ptr> [[TMP8]], zeroinitializer
; CHECK-NEXT: [[TMP10:%.*]] = and <4 x i1> [[TMP9]], zeroinitializer
; CHECK-NEXT: [[RDX_OP:%.*]] = or <4 x i1> [[TMP5]], [[TMP10]]
; CHECK-NEXT: [[OP_RDX:%.*]] = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> [[RDX_OP]])
; CHECK-NEXT: br i1 [[OP_RDX]], label [[DOTLR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: ret void
Expand Down
8 changes: 4 additions & 4 deletions llvm/test/Transforms/SLPVectorizer/AArch64/PR38339.ll
Original file line number Diff line number Diff line change
Expand Up @@ -3,9 +3,9 @@

define void @f1(<2 x i16> %x, ptr %a) {
; CHECK-LABEL: @f1(
; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <2 x i16> [[X:%.*]], <2 x i16> poison, <4 x i32> <i32 0, i32 1, i32 1, i32 0>
; CHECK-NEXT: [[TMP1:%.*]] = extractelement <2 x i16> [[X]], i32 0
; CHECK-NEXT: [[TMP1:%.*]] = extractelement <2 x i16> [[X:%.*]], i32 0
; CHECK-NEXT: store i16 [[TMP1]], ptr [[A:%.*]], align 2
; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <2 x i16> [[X]], <2 x i16> poison, <4 x i32> <i32 0, i32 1, i32 1, i32 0>
; CHECK-NEXT: store <4 x i16> [[SHUFFLE]], ptr undef, align 2
; CHECK-NEXT: ret void
;
Expand All @@ -29,9 +29,9 @@ define void @f2(<2 x i16> %x, ptr %a) {
; CHECK: cont:
; CHECK-NEXT: [[XX:%.*]] = phi <2 x i16> [ [[X:%.*]], [[ENTRY:%.*]] ], [ undef, [[CONT]] ]
; CHECK-NEXT: [[AA:%.*]] = phi ptr [ [[A:%.*]], [[ENTRY]] ], [ undef, [[CONT]] ]
; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <2 x i16> [[XX]], <2 x i16> poison, <4 x i32> <i32 0, i32 1, i32 1, i32 0>
; CHECK-NEXT: [[TMP0:%.*]] = extractelement <2 x i16> [[XX]], i32 0
; CHECK-NEXT: store i16 [[TMP0]], ptr [[A]], align 2
; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <2 x i16> [[XX]], <2 x i16> poison, <4 x i32> <i32 0, i32 1, i32 1, i32 0>
; CHECK-NEXT: store <4 x i16> [[SHUFFLE]], ptr undef, align 2
; CHECK-NEXT: [[A_VAL:%.*]] = load i16, ptr [[A]], align 2
; CHECK-NEXT: [[CMP:%.*]] = icmp eq i16 [[A_VAL]], 0
Expand Down Expand Up @@ -70,9 +70,9 @@ define void @f3(<2 x i16> %x, ptr %a) {
; CHECK: cont:
; CHECK-NEXT: [[XX:%.*]] = phi <2 x i16> [ [[X:%.*]], [[ENTRY:%.*]] ], [ undef, [[CONT]] ]
; CHECK-NEXT: [[AA:%.*]] = phi ptr [ [[A:%.*]], [[ENTRY]] ], [ undef, [[CONT]] ]
; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <2 x i16> [[XX]], <2 x i16> poison, <4 x i32> <i32 1, i32 0, i32 0, i32 1>
; CHECK-NEXT: [[TMP0:%.*]] = extractelement <2 x i16> [[XX]], i32 1
; CHECK-NEXT: store i16 [[TMP0]], ptr [[A]], align 2
; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <2 x i16> [[XX]], <2 x i16> poison, <4 x i32> <i32 1, i32 0, i32 0, i32 1>
; CHECK-NEXT: store <4 x i16> [[SHUFFLE]], ptr undef, align 2
; CHECK-NEXT: [[A_VAL:%.*]] = load i16, ptr [[A]], align 2
; CHECK-NEXT: [[CMP:%.*]] = icmp eq i16 [[A_VAL]], 0
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -10,9 +10,11 @@ define i32 @test(ptr %c) {
; CHECK-NEXT: [[TMP0:%.*]] = load <2 x i64>, ptr [[BITLEN]], align 8
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <2 x i64> [[TMP0]], <2 x i64> poison, <6 x i32> <i32 1, i32 1, i32 1, i32 1, i32 0, i32 0>
; CHECK-NEXT: [[TMP2:%.*]] = lshr <6 x i64> [[TMP1]], zeroinitializer
; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <2 x i64> [[TMP0]], <2 x i64> poison, <8 x i32> <i32 poison, i32 poison, i32 poison, i32 poison, i32 1, i32 0, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <2 x i64> [[TMP0]], <2 x i64> poison, <2 x i32> <i32 1, i32 0>
; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <6 x i64> [[TMP2]], <6 x i64> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <8 x i64> [[TMP4]], <8 x i64> [[TMP3]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 12, i32 13, i32 4, i32 5>
; CHECK-NEXT: [[TMP7:%.*]] = shufflevector <2 x i64> [[TMP3]], <2 x i64> poison, <8 x i32> <i32 0, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP8:%.*]] = shufflevector <8 x i64> [[TMP4]], <8 x i64> [[TMP7]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <8 x i64> [[TMP8]], <8 x i64> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 6, i32 7, i32 4, i32 5>
; CHECK-NEXT: [[TMP6:%.*]] = trunc <8 x i64> [[TMP5]] to <8 x i8>
; CHECK-NEXT: store <8 x i8> [[TMP6]], ptr [[INCDEC_PTR_3_1]], align 1
; CHECK-NEXT: ret i32 0
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -124,16 +124,16 @@ define <4 x i32> @build_vec_v4i32_reuse_0(<2 x i32> %v0, <2 x i32> %v1) {

define <4 x i32> @build_vec_v4i32_reuse_1(<2 x i32> %v0, <2 x i32> %v1) {
; CHECK-LABEL: @build_vec_v4i32_reuse_1(
; CHECK-NEXT: [[TMP6:%.*]] = shufflevector <2 x i32> [[V0:%.*]], <2 x i32> poison, <4 x i32> <i32 0, i32 0, i32 0, i32 1>
; CHECK-NEXT: [[TMP7:%.*]] = shufflevector <2 x i32> [[V1:%.*]], <2 x i32> poison, <4 x i32> <i32 0, i32 0, i32 0, i32 1>
; CHECK-NEXT: [[TMP3:%.*]] = add <4 x i32> [[TMP6]], [[TMP7]]
; CHECK-NEXT: [[TMP4:%.*]] = xor <4 x i32> [[TMP6]], [[TMP7]]
; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <4 x i32> [[TMP3]], <4 x i32> [[TMP4]], <4 x i32> <i32 0, i32 1, i32 6, i32 7>
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <2 x i32> [[V0]], <2 x i32> poison, <4 x i32> <i32 1, i32 1, i32 1, i32 0>
; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <2 x i32> [[V1]], <2 x i32> poison, <4 x i32> <i32 1, i32 1, i32 1, i32 0>
; CHECK-NEXT: [[TMP8:%.*]] = add <4 x i32> [[TMP1]], [[TMP2]]
; CHECK-NEXT: [[TMP11:%.*]] = xor <4 x i32> [[TMP1]], [[TMP2]]
; CHECK-NEXT: [[TMP10:%.*]] = shufflevector <4 x i32> [[TMP8]], <4 x i32> [[TMP11]], <4 x i32> <i32 0, i32 1, i32 6, i32 7>
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <2 x i32> [[V0:%.*]], <2 x i32> poison, <3 x i32> <i32 0, i32 0, i32 1>
; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <2 x i32> [[V1:%.*]], <2 x i32> poison, <3 x i32> <i32 0, i32 0, i32 1>
; CHECK-NEXT: [[TMP3:%.*]] = add <3 x i32> [[TMP1]], [[TMP2]]
; CHECK-NEXT: [[TMP4:%.*]] = xor <3 x i32> [[TMP1]], [[TMP2]]
; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <3 x i32> [[TMP3]], <3 x i32> [[TMP4]], <4 x i32> <i32 0, i32 0, i32 4, i32 5>
; CHECK-NEXT: [[TMP6:%.*]] = shufflevector <2 x i32> [[V0]], <2 x i32> poison, <3 x i32> <i32 1, i32 1, i32 0>
; CHECK-NEXT: [[TMP7:%.*]] = shufflevector <2 x i32> [[V1]], <2 x i32> poison, <3 x i32> <i32 1, i32 1, i32 0>
; CHECK-NEXT: [[TMP8:%.*]] = add <3 x i32> [[TMP6]], [[TMP7]]
; CHECK-NEXT: [[TMP11:%.*]] = xor <3 x i32> [[TMP6]], [[TMP7]]
; CHECK-NEXT: [[TMP10:%.*]] = shufflevector <3 x i32> [[TMP8]], <3 x i32> [[TMP11]], <4 x i32> <i32 0, i32 0, i32 4, i32 5>
; CHECK-NEXT: [[TMP9:%.*]] = sub <4 x i32> [[TMP5]], [[TMP10]]
; CHECK-NEXT: ret <4 x i32> [[TMP9]]
;
Expand Down
20 changes: 10 additions & 10 deletions llvm/test/Transforms/SLPVectorizer/AArch64/transpose.ll
Original file line number Diff line number Diff line change
Expand Up @@ -124,16 +124,16 @@ define <4 x i32> @build_vec_v4i32_reuse_0(<2 x i32> %v0, <2 x i32> %v1) {

define <4 x i32> @build_vec_v4i32_reuse_1(<2 x i32> %v0, <2 x i32> %v1) {
; CHECK-LABEL: @build_vec_v4i32_reuse_1(
; CHECK-NEXT: [[TMP6:%.*]] = shufflevector <2 x i32> [[V0:%.*]], <2 x i32> poison, <4 x i32> <i32 0, i32 0, i32 0, i32 1>
; CHECK-NEXT: [[TMP7:%.*]] = shufflevector <2 x i32> [[V1:%.*]], <2 x i32> poison, <4 x i32> <i32 0, i32 0, i32 0, i32 1>
; CHECK-NEXT: [[TMP3:%.*]] = add <4 x i32> [[TMP6]], [[TMP7]]
; CHECK-NEXT: [[TMP4:%.*]] = xor <4 x i32> [[TMP6]], [[TMP7]]
; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <4 x i32> [[TMP3]], <4 x i32> [[TMP4]], <4 x i32> <i32 0, i32 1, i32 6, i32 7>
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <2 x i32> [[V0]], <2 x i32> poison, <4 x i32> <i32 1, i32 1, i32 1, i32 0>
; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <2 x i32> [[V1]], <2 x i32> poison, <4 x i32> <i32 1, i32 1, i32 1, i32 0>
; CHECK-NEXT: [[TMP8:%.*]] = add <4 x i32> [[TMP1]], [[TMP2]]
; CHECK-NEXT: [[TMP11:%.*]] = xor <4 x i32> [[TMP1]], [[TMP2]]
; CHECK-NEXT: [[TMP10:%.*]] = shufflevector <4 x i32> [[TMP8]], <4 x i32> [[TMP11]], <4 x i32> <i32 0, i32 1, i32 6, i32 7>
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <2 x i32> [[V0:%.*]], <2 x i32> poison, <3 x i32> <i32 0, i32 0, i32 1>
; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <2 x i32> [[V1:%.*]], <2 x i32> poison, <3 x i32> <i32 0, i32 0, i32 1>
; CHECK-NEXT: [[TMP3:%.*]] = add <3 x i32> [[TMP1]], [[TMP2]]
; CHECK-NEXT: [[TMP4:%.*]] = xor <3 x i32> [[TMP1]], [[TMP2]]
; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <3 x i32> [[TMP3]], <3 x i32> [[TMP4]], <4 x i32> <i32 0, i32 0, i32 4, i32 5>
; CHECK-NEXT: [[TMP6:%.*]] = shufflevector <2 x i32> [[V0]], <2 x i32> poison, <3 x i32> <i32 1, i32 1, i32 0>
; CHECK-NEXT: [[TMP7:%.*]] = shufflevector <2 x i32> [[V1]], <2 x i32> poison, <3 x i32> <i32 1, i32 1, i32 0>
; CHECK-NEXT: [[TMP8:%.*]] = add <3 x i32> [[TMP6]], [[TMP7]]
; CHECK-NEXT: [[TMP11:%.*]] = xor <3 x i32> [[TMP6]], [[TMP7]]
; CHECK-NEXT: [[TMP10:%.*]] = shufflevector <3 x i32> [[TMP8]], <3 x i32> [[TMP11]], <4 x i32> <i32 0, i32 0, i32 4, i32 5>
; CHECK-NEXT: [[TMP9:%.*]] = sub <4 x i32> [[TMP5]], [[TMP10]]
; CHECK-NEXT: ret <4 x i32> [[TMP9]]
;
Expand Down
11 changes: 7 additions & 4 deletions llvm/test/Transforms/SLPVectorizer/AArch64/tsc-s116.ll
Original file line number Diff line number Diff line change
Expand Up @@ -17,12 +17,15 @@

define void @s116_modified(ptr %a) {
; CHECK-LABEL: @s116_modified(
; CHECK-NEXT: [[A:%.*]] = getelementptr inbounds float, ptr [[GEP1:%.*]], i64 4
; CHECK-NEXT: [[GEP2:%.*]] = getelementptr inbounds float, ptr [[GEP1:%.*]], i64 1
; CHECK-NEXT: [[A:%.*]] = getelementptr inbounds float, ptr [[GEP1]], i64 4
; CHECK-NEXT: [[LD1:%.*]] = load float, ptr [[GEP1]], align 4
; CHECK-NEXT: [[LD0:%.*]] = load float, ptr [[A]], align 4
; CHECK-NEXT: [[TMP1:%.*]] = load <4 x float>, ptr [[GEP1]], align 4
; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <4 x float> [[TMP1]], <4 x float> poison, <4 x i32> <i32 0, i32 2, i32 3, i32 poison>
; CHECK-NEXT: [[TMP1:%.*]] = load <3 x float>, ptr [[GEP2]], align 4
; CHECK-NEXT: [[TMP7:%.*]] = shufflevector <3 x float> [[TMP1]], <3 x float> poison, <4 x i32> <i32 0, i32 0, i32 1, i32 2>
; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <3 x float> [[TMP1]], <3 x float> poison, <4 x i32> <i32 poison, i32 1, i32 2, i32 poison>
; CHECK-NEXT: [[TMP2:%.*]] = insertelement <4 x float> [[TMP3]], float [[LD1]], i32 0
; CHECK-NEXT: [[TMP6:%.*]] = insertelement <4 x float> [[TMP2]], float [[LD0]], i32 3
; CHECK-NEXT: [[TMP7:%.*]] = shufflevector <4 x float> [[TMP1]], <4 x float> poison, <4 x i32> <i32 1, i32 1, i32 2, i32 3>
; CHECK-NEXT: [[TMP8:%.*]] = fmul fast <4 x float> [[TMP6]], [[TMP7]]
; CHECK-NEXT: store <4 x float> [[TMP8]], ptr [[GEP1]], align 4
; CHECK-NEXT: ret void
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -245,26 +245,17 @@ define void @select_uniform_ugt_16xi8(ptr %ptr, i8 %x) {
; CHECK-NEXT: [[L_8:%.*]] = load i8, ptr [[GEP_8]], align 1
; CHECK-NEXT: [[CMP_8:%.*]] = icmp ugt i8 [[L_8]], -1
; CHECK-NEXT: [[GEP_9:%.*]] = getelementptr inbounds i8, ptr [[PTR]], i8 9
; CHECK-NEXT: [[GEP_11:%.*]] = getelementptr inbounds i8, ptr [[PTR]], i8 11
; CHECK-NEXT: [[L_11:%.*]] = load i8, ptr [[GEP_11]], align 1
; CHECK-NEXT: [[GEP_12:%.*]] = getelementptr inbounds i8, ptr [[PTR]], i8 12
; CHECK-NEXT: [[TMP0:%.*]] = load <8 x i8>, ptr [[PTR]], align 1
; CHECK-NEXT: [[TMP1:%.*]] = load i8, ptr [[PTR]], align 1
; CHECK-NEXT: [[S_8:%.*]] = select i1 [[CMP_8]], i8 [[TMP1]], i8 [[X:%.*]]
; CHECK-NEXT: [[TMP2:%.*]] = load <2 x i8>, ptr [[GEP_9]], align 1
; CHECK-NEXT: [[TMP3:%.*]] = load <4 x i8>, ptr [[GEP_12]], align 1
; CHECK-NEXT: [[TMP7:%.*]] = shufflevector <8 x i8> [[TMP0]], <8 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP11:%.*]] = shufflevector <2 x i8> [[TMP2]], <2 x i8> poison, <16 x i32> <i32 0, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <2 x i8> [[TMP2]], <2 x i8> poison, <8 x i32> <i32 0, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <8 x i8> [[TMP0]], <8 x i8> [[TMP4]], <16 x i32> <i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 0, i32 8, i32 9, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP6:%.*]] = insertelement <16 x i8> [[TMP5]], i8 [[L_11]], i32 11
; CHECK-NEXT: [[TMP15:%.*]] = shufflevector <16 x i8> [[TMP6]], <16 x i8> [[TMP7]], <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; CHECK-NEXT: [[TMP10:%.*]] = shufflevector <4 x i8> [[TMP3]], <4 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP8:%.*]] = shufflevector <16 x i8> [[TMP15]], <16 x i8> [[TMP10]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 18, i32 19>
; CHECK-NEXT: [[TMP9:%.*]] = icmp ugt <16 x i8> [[TMP8]], splat (i8 -1)
; CHECK-NEXT: [[TMP12:%.*]] = insertelement <16 x i8> poison, i8 [[X]], i32 0
; CHECK-NEXT: [[TMP13:%.*]] = shufflevector <16 x i8> [[TMP12]], <16 x i8> poison, <16 x i32> zeroinitializer
; CHECK-NEXT: [[TMP14:%.*]] = select <16 x i1> [[TMP9]], <16 x i8> [[TMP8]], <16 x i8> [[TMP13]]
; CHECK-NEXT: [[TMP3:%.*]] = load <7 x i8>, ptr [[GEP_9]], align 1
; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <7 x i8> [[TMP3]], <7 x i8> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 poison>
; CHECK-NEXT: [[TMP7:%.*]] = shufflevector <8 x i8> [[TMP0]], <8 x i8> [[TMP2]], <15 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14>
; CHECK-NEXT: [[TMP8:%.*]] = icmp ugt <15 x i8> [[TMP7]], splat (i8 -1)
; CHECK-NEXT: [[TMP9:%.*]] = insertelement <15 x i8> poison, i8 [[X]], i32 0
; CHECK-NEXT: [[TMP10:%.*]] = shufflevector <15 x i8> [[TMP9]], <15 x i8> poison, <15 x i32> zeroinitializer
; CHECK-NEXT: [[TMP11:%.*]] = select <15 x i1> [[TMP8]], <15 x i8> [[TMP7]], <15 x i8> [[TMP10]]
; CHECK-NEXT: [[TMP14:%.*]] = shufflevector <15 x i8> [[TMP11]], <15 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 0, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14>
; CHECK-NEXT: store <16 x i8> [[TMP14]], ptr [[PTR]], align 2
; CHECK-NEXT: ret void
;
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -252,7 +252,6 @@ define void @const_stride_2_with_reordering(ptr %pl, ptr %ps) {
; CHECK-NEXT: [[GEP_L0:%.*]] = getelementptr inbounds i8, ptr [[PL]], i64 0
; CHECK-NEXT: [[GEP_S0:%.*]] = getelementptr inbounds i8, ptr [[PS]], i64 0
; CHECK-NEXT: [[TMP1:%.*]] = call <31 x i8> @llvm.masked.load.v31i8.p0(ptr [[GEP_L0]], i32 16, <31 x i1> <i1 true, i1 false, i1 true, i1 false, i1 true, i1 false, i1 true, i1 false, i1 true, i1 false, i1 true, i1 false, i1 true, i1 false, i1 true, i1 false, i1 true, i1 false, i1 true, i1 false, i1 true, i1 false, i1 true, i1 false, i1 true, i1 false, i1 true, i1 false, i1 true, i1 false, i1 true>, <31 x i8> poison)
; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <31 x i8> [[TMP1]], <31 x i8> poison, <16 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26, i32 28, i32 30>
; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <31 x i8> [[TMP1]], <31 x i8> poison, <16 x i32> <i32 2, i32 0, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26, i32 28, i32 30>
; CHECK-NEXT: store <16 x i8> [[TMP2]], ptr [[GEP_S0]], align 16
; CHECK-NEXT: ret void
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -5,10 +5,9 @@ define i16 @test(ptr %i) {
; CHECK-LABEL: define i16 @test(
; CHECK-SAME: ptr [[I:%.*]]) #[[ATTR0:[0-9]+]] {
; CHECK-NEXT: [[ENTRY:.*:]]
; CHECK-NEXT: [[TMP0:%.*]] = insertelement <2 x ptr> poison, ptr [[I]], i32 0
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <2 x ptr> [[TMP0]], <2 x ptr> poison, <2 x i32> zeroinitializer
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr i8, <2 x ptr> [[TMP1]], <2 x i64> <i64 132860, i64 137774>
; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <2 x ptr> [[TMP2]], <2 x ptr> poison, <4 x i32> <i32 0, i32 1, i32 0, i32 1>
; CHECK-NEXT: [[TMP0:%.*]] = insertelement <4 x ptr> poison, ptr [[I]], i32 0
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <4 x ptr> [[TMP0]], <4 x ptr> poison, <4 x i32> zeroinitializer
; CHECK-NEXT: [[TMP3:%.*]] = getelementptr i8, <4 x ptr> [[TMP1]], <4 x i64> <i64 132860, i64 137774, i64 132860, i64 137774>
; CHECK-NEXT: [[GEP_US154_2:%.*]] = getelementptr i8, ptr [[I]], i64 142688
; CHECK-NEXT: br label %[[FOR_COND5_US:.*]]
; CHECK: [[FOR_COND5_US]]:
Expand Down
Loading