[PATCH] D149240: [InstCombine] Combine const GEP chains
Yingwei Zheng via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Wed Apr 26 00:07:30 PDT 2023
dtcxzyw created this revision.
dtcxzyw added reviewers: nikic, StephenFan.
dtcxzyw added a project: LLVM.
Herald added a subscriber: hiraditya.
Herald added a project: All.
dtcxzyw requested review of this revision.
Herald added subscribers: llvm-commits, pcwang-thead.
This patch reverts rGae739aefd7473517d3f08b5c8d08a66c7f469198 <https://reviews.llvm.org/rGae739aefd7473517d3f08b5c8d08a66c7f469198> to address performance regressions reported by our CI <https://github.com/dtcxzyw/llvm-ci/issues/137> after rG2ec1d0f427c7822540352c0c14d057e7bfe4f77b <https://reviews.llvm.org/rG2ec1d0f427c7822540352c0c14d057e7bfe4f77b>.
For example:
define ptr @const_gep_chain(ptr %p, i64 %a) {
%p1 = getelementptr inbounds i8, ptr %p, i64 %a
%p2 = getelementptr inbounds i8, ptr %p1, i64 1
%p3 = getelementptr inbounds i8, ptr %p2, i64 2
%p4 = getelementptr inbounds i8, ptr %p3, i64 3
ret ptr %p4
}
The last three GEPs will not be folded since rG2ec1d0f427c7822540352c0c14d057e7bfe4f77b <https://reviews.llvm.org/rG2ec1d0f427c7822540352c0c14d057e7bfe4f77b>.
I think it is appropriate to remove this code because there is no compile-time regression reported in our benchmarks.
Repository:
rG LLVM Github Monorepo
https://reviews.llvm.org/D149240
Files:
llvm/lib/Transforms/InstCombine/InstructionCombining.cpp
llvm/test/Transforms/InstCombine/getelementptr.ll
llvm/test/Transforms/LoopVectorize/interleaved-accesses.ll
Index: llvm/test/Transforms/LoopVectorize/interleaved-accesses.ll
===================================================================
--- llvm/test/Transforms/LoopVectorize/interleaved-accesses.ll
+++ llvm/test/Transforms/LoopVectorize/interleaved-accesses.ll
@@ -745,18 +745,16 @@
; CHECK-NEXT: [[STRIDED_VEC2:%.*]] = shufflevector <12 x i32> [[WIDE_VEC]], <12 x i32> poison, <4 x i32> <i32 1, i32 4, i32 7, i32 10>
; CHECK-NEXT: [[STRIDED_VEC3:%.*]] = shufflevector <12 x i32> [[WIDE_VEC]], <12 x i32> poison, <4 x i32> <i32 2, i32 5, i32 8, i32 11>
; CHECK-NEXT: [[TMP1:%.*]] = add <4 x i32> [[STRIDED_VEC]], [[VEC_IND]]
-; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i32, ptr [[NEXT_GEP]], i64 2
-; CHECK-NEXT: [[TMP3:%.*]] = add <4 x i32> [[STRIDED_VEC2]], [[VEC_IND]]
-; CHECK-NEXT: [[TMP4:%.*]] = add <4 x i32> [[STRIDED_VEC3]], [[VEC_IND]]
-; CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds i32, ptr [[TMP2]], i64 -2
-; CHECK-NEXT: [[TMP6:%.*]] = shufflevector <4 x i32> [[TMP1]], <4 x i32> [[TMP3]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; CHECK-NEXT: [[TMP7:%.*]] = shufflevector <4 x i32> [[TMP4]], <4 x i32> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
-; CHECK-NEXT: [[INTERLEAVED_VEC:%.*]] = shufflevector <8 x i32> [[TMP6]], <8 x i32> [[TMP7]], <12 x i32> <i32 0, i32 4, i32 8, i32 1, i32 5, i32 9, i32 2, i32 6, i32 10, i32 3, i32 7, i32 11>
-; CHECK-NEXT: store <12 x i32> [[INTERLEAVED_VEC]], ptr [[TMP5]], align 4
+; CHECK-NEXT: [[TMP2:%.*]] = add <4 x i32> [[STRIDED_VEC2]], [[VEC_IND]]
+; CHECK-NEXT: [[TMP3:%.*]] = add <4 x i32> [[STRIDED_VEC3]], [[VEC_IND]]
+; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <4 x i32> [[TMP1]], <4 x i32> [[TMP2]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <4 x i32> [[TMP3]], <4 x i32> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
+; CHECK-NEXT: [[INTERLEAVED_VEC:%.*]] = shufflevector <8 x i32> [[TMP4]], <8 x i32> [[TMP5]], <12 x i32> <i32 0, i32 4, i32 8, i32 1, i32 5, i32 9, i32 2, i32 6, i32 10, i32 3, i32 7, i32 11>
+; CHECK-NEXT: store <12 x i32> [[INTERLEAVED_VEC]], ptr [[NEXT_GEP]], align 4
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT: [[VEC_IND_NEXT]] = add <4 x i32> [[VEC_IND]], <i32 4, i32 4, i32 4, i32 4>
-; CHECK-NEXT: [[TMP8:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1024
-; CHECK-NEXT: br i1 [[TMP8]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP20:![0-9]+]]
+; CHECK-NEXT: [[TMP6:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1024
+; CHECK-NEXT: br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP20:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: br i1 true, label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
Index: llvm/test/Transforms/InstCombine/getelementptr.ll
===================================================================
--- llvm/test/Transforms/InstCombine/getelementptr.ll
+++ llvm/test/Transforms/InstCombine/getelementptr.ll
@@ -1389,4 +1389,17 @@
ret ptr getelementptr ([0 x i8], ptr @g_0xi8_e, i64 0, i64 10)
}
+define ptr @const_gep_chain(ptr %p, i64 %a) {
+; CHECK-LABEL: @const_gep_chain(
+; CHECK-NEXT: [[P1:%.*]] = getelementptr inbounds i8, ptr [[P:%.*]], i64 [[A:%.*]]
+; CHECK-NEXT: [[P4:%.*]] = getelementptr inbounds i8, ptr [[P1]], i64 6
+; CHECK-NEXT: ret ptr [[P4]]
+;
+ %p1 = getelementptr inbounds i8, ptr %p, i64 %a
+ %p2 = getelementptr inbounds i8, ptr %p1, i64 1
+ %p3 = getelementptr inbounds i8, ptr %p2, i64 2
+ %p4 = getelementptr inbounds i8, ptr %p3, i64 3
+ ret ptr %p4
+}
+
!0 = !{!"branch_weights", i32 2, i32 10}
Index: llvm/lib/Transforms/InstCombine/InstructionCombining.cpp
===================================================================
--- llvm/lib/Transforms/InstCombine/InstructionCombining.cpp
+++ llvm/lib/Transforms/InstCombine/InstructionCombining.cpp
@@ -1945,13 +1945,6 @@
if (!shouldMergeGEPs(*cast<GEPOperator>(&GEP), *Src))
return nullptr;
- // Note that if our source is a gep chain itself then we wait for that
- // chain to be resolved before we perform this transformation. This
- // avoids us creating a TON of code in some cases.
- if (auto *SrcGEP = dyn_cast<GEPOperator>(Src->getOperand(0)))
- if (SrcGEP->getNumOperands() == 2 && shouldMergeGEPs(*Src, *SrcGEP))
- return nullptr; // Wait until our source is folded to completion.
-
// For constant GEPs, use a more general offset-based folding approach.
Type *PtrTy = Src->getType()->getScalarType();
if (GEP.hasAllConstantIndices() &&
-------------- next part --------------
A non-text attachment was scrubbed...
Name: D149240.517074.patch
Type: text/x-patch
Size: 4770 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20230426/80ad2ace/attachment.bin>
More information about the llvm-commits
mailing list