[llvm-branch-commits] [llvm] [TBAA] Use !tbaa for first accessed field, even if there are others. (PR #81313)
Florian Hahn via llvm-branch-commits
llvm-branch-commits at lists.llvm.org
Fri Feb 9 12:13:47 PST 2024
https://github.com/fhahn created https://github.com/llvm/llvm-project/pull/81313
Motivation for this and follow-on patches is to improve codegen for libc++, where using memcpy limits optimizations, like vectorization for code iteration over std::vector<std::complex<float>>: https://godbolt.org/z/f3vqYos3c
Depends on https://github.com/llvm/llvm-project/pull/81289.
>From e879ab07a6b39d7cf47fbc3c17ff25918cdee628 Mon Sep 17 00:00:00 2001
From: Florian Hahn <flo at fhahn.com>
Date: Fri, 9 Feb 2024 16:48:26 +0000
Subject: [PATCH] [TBAA] Use !tbaa for first accessed field, even if there are
others.
Motivation for this and follow-on patches is to improve codegen for
libc++, where using memcpy limits optimizations, like vectorization for
code iteration over std::vector<std::complex<float>>:
https://godbolt.org/z/f3vqYos3c
Depends on https://github.com/llvm/llvm-project/pull/81289.
---
llvm/lib/Analysis/TypeBasedAliasAnalysis.cpp | 3 +--
llvm/test/Transforms/SROA/tbaa-struct2.ll | 21 +++++++--------
llvm/test/Transforms/SROA/tbaa-struct3.ll | 28 ++++++++++----------
3 files changed, 25 insertions(+), 27 deletions(-)
diff --git a/llvm/lib/Analysis/TypeBasedAliasAnalysis.cpp b/llvm/lib/Analysis/TypeBasedAliasAnalysis.cpp
index b2dc451d581939..25ac01db7633ee 100644
--- a/llvm/lib/Analysis/TypeBasedAliasAnalysis.cpp
+++ b/llvm/lib/Analysis/TypeBasedAliasAnalysis.cpp
@@ -821,8 +821,7 @@ MDNode *AAMDNodes::extendToTBAA(MDNode *MD, ssize_t Len) {
AAMDNodes AAMDNodes::adjustForAccess(unsigned AccessSize) {
AAMDNodes New = *this;
MDNode *M = New.TBAAStruct;
- if (M && M->getNumOperands() == 3 && M->getOperand(0) &&
- mdconst::hasa<ConstantInt>(M->getOperand(0)) &&
+ if (M && M->getOperand(0) && mdconst::hasa<ConstantInt>(M->getOperand(0)) &&
mdconst::extract<ConstantInt>(M->getOperand(0))->isZero() &&
M->getOperand(1) && mdconst::hasa<ConstantInt>(M->getOperand(1)) &&
mdconst::extract<ConstantInt>(M->getOperand(1))->getValue() ==
diff --git a/llvm/test/Transforms/SROA/tbaa-struct2.ll b/llvm/test/Transforms/SROA/tbaa-struct2.ll
index 02c99a2b329457..545fa47eecb2ce 100644
--- a/llvm/test/Transforms/SROA/tbaa-struct2.ll
+++ b/llvm/test/Transforms/SROA/tbaa-struct2.ll
@@ -11,11 +11,11 @@ declare double @subcall(double %g, i32 %m)
define double @bar(ptr %wishart) {
; CHECK-LABEL: @bar(
; CHECK-NEXT: [[TMP_SROA_3:%.*]] = alloca [4 x i8], align 4
-; CHECK-NEXT: [[TMP_SROA_0_0_COPYLOAD:%.*]] = load double, ptr [[WISHART:%.*]], align 8, !tbaa.struct [[TBAA_STRUCT0:![0-9]+]]
+; CHECK-NEXT: [[TMP_SROA_0_0_COPYLOAD:%.*]] = load double, ptr [[WISHART:%.*]], align 8, !tbaa [[TBAA0:![0-9]+]]
; CHECK-NEXT: [[TMP_SROA_2_0_WISHART_SROA_IDX:%.*]] = getelementptr inbounds i8, ptr [[WISHART]], i64 8
-; CHECK-NEXT: [[TMP_SROA_2_0_COPYLOAD:%.*]] = load i32, ptr [[TMP_SROA_2_0_WISHART_SROA_IDX]], align 8, !tbaa [[TBAA5:![0-9]+]]
+; CHECK-NEXT: [[TMP_SROA_2_0_COPYLOAD:%.*]] = load i32, ptr [[TMP_SROA_2_0_WISHART_SROA_IDX]], align 8, !tbaa [[TBAA4:![0-9]+]]
; CHECK-NEXT: [[TMP_SROA_3_0_WISHART_SROA_IDX:%.*]] = getelementptr inbounds i8, ptr [[WISHART]], i64 12
-; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 4 [[TMP_SROA_3]], ptr align 4 [[TMP_SROA_3_0_WISHART_SROA_IDX]], i64 4, i1 false), !tbaa.struct [[TBAA_STRUCT7:![0-9]+]]
+; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 4 [[TMP_SROA_3]], ptr align 4 [[TMP_SROA_3_0_WISHART_SROA_IDX]], i64 4, i1 false), !tbaa.struct [[TBAA_STRUCT6:![0-9]+]]
; CHECK-NEXT: [[CALL:%.*]] = call double @subcall(double [[TMP_SROA_0_0_COPYLOAD]], i32 [[TMP_SROA_2_0_COPYLOAD]])
; CHECK-NEXT: ret double [[CALL]]
;
@@ -38,14 +38,13 @@ define double @bar(ptr %wishart) {
;.
; CHECK: attributes #[[ATTR0:[0-9]+]] = { nocallback nofree nounwind willreturn memory(argmem: readwrite) }
;.
-; CHECK: [[TBAA_STRUCT0]] = !{i64 0, i64 8, [[META1:![0-9]+]], i64 8, i64 4, [[TBAA5]]}
-; CHECK: [[META1]] = !{[[META2:![0-9]+]], [[META2]], i64 0}
-; CHECK: [[META2]] = !{!"double", [[META3:![0-9]+]], i64 0}
-; CHECK: [[META3]] = !{!"omnipotent char", [[META4:![0-9]+]], i64 0}
-; CHECK: [[META4]] = !{!"Simple C++ TBAA"}
-; CHECK: [[TBAA5]] = !{[[META6:![0-9]+]], [[META6]], i64 0}
-; CHECK: [[META6]] = !{!"int", [[META3]], i64 0}
-; CHECK: [[TBAA_STRUCT7]] = !{}
+; CHECK: [[TBAA0]] = !{[[META1:![0-9]+]], [[META1]], i64 0}
+; CHECK: [[META1]] = !{!"double", [[META2:![0-9]+]], i64 0}
+; CHECK: [[META2]] = !{!"omnipotent char", [[META3:![0-9]+]], i64 0}
+; CHECK: [[META3]] = !{!"Simple C++ TBAA"}
+; CHECK: [[TBAA4]] = !{[[META5:![0-9]+]], [[META5]], i64 0}
+; CHECK: [[META5]] = !{!"int", [[META2]], i64 0}
+; CHECK: [[TBAA_STRUCT6]] = !{}
;.
;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
; CHECK-MODIFY-CFG: {{.*}}
diff --git a/llvm/test/Transforms/SROA/tbaa-struct3.ll b/llvm/test/Transforms/SROA/tbaa-struct3.ll
index 603e7d708647fc..68553d9b1a270b 100644
--- a/llvm/test/Transforms/SROA/tbaa-struct3.ll
+++ b/llvm/test/Transforms/SROA/tbaa-struct3.ll
@@ -7,9 +7,9 @@ define void @load_store_transfer_split_struct_tbaa_2_float(ptr dereferenceable(2
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = bitcast float [[A]] to i32
; CHECK-NEXT: [[TMP1:%.*]] = bitcast float [[B]] to i32
-; CHECK-NEXT: store i32 [[TMP0]], ptr [[RES]], align 4, !tbaa.struct [[TBAA_STRUCT0:![0-9]+]]
+; CHECK-NEXT: store i32 [[TMP0]], ptr [[RES]], align 4, !tbaa [[TBAA0:![0-9]+]]
; CHECK-NEXT: [[RES_SROA_IDX:%.*]] = getelementptr inbounds i8, ptr [[RES]], i64 4
-; CHECK-NEXT: store i32 [[TMP1]], ptr [[RES_SROA_IDX]], align 4, !tbaa [[TBAA1:![0-9]+]]
+; CHECK-NEXT: store i32 [[TMP1]], ptr [[RES_SROA_IDX]], align 4, !tbaa [[TBAA0]]
; CHECK-NEXT: [[P:%.*]] = load ptr, ptr [[RES]], align 8
; CHECK-NEXT: ret void
;
@@ -29,9 +29,9 @@ define void @memcpy_transfer(ptr dereferenceable(24) %res, float %a, float %b) {
; CHECK-SAME: ptr dereferenceable(24) [[RES:%.*]], float [[A:%.*]], float [[B:%.*]]) {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[L_PTR:%.*]] = load ptr, ptr [[RES]], align 8
-; CHECK-NEXT: store float [[A]], ptr [[L_PTR]], align 1, !tbaa.struct [[TBAA_STRUCT0]]
+; CHECK-NEXT: store float [[A]], ptr [[L_PTR]], align 1, !tbaa [[TBAA0]]
; CHECK-NEXT: [[TMP_SROA_2_0_L_PTR_SROA_IDX:%.*]] = getelementptr inbounds i8, ptr [[L_PTR]], i64 4
-; CHECK-NEXT: store float [[B]], ptr [[TMP_SROA_2_0_L_PTR_SROA_IDX]], align 1, !tbaa [[TBAA1]]
+; CHECK-NEXT: store float [[B]], ptr [[TMP_SROA_2_0_L_PTR_SROA_IDX]], align 1, !tbaa [[TBAA0]]
; CHECK-NEXT: ret void
;
entry:
@@ -49,11 +49,11 @@ define void @memcpy_transfer_tbaa_field_and_size_do_not_align(ptr dereferenceabl
; CHECK-SAME: ptr dereferenceable(24) [[RES:%.*]], float [[A:%.*]], float [[B:%.*]]) {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[L_PTR:%.*]] = load ptr, ptr [[RES]], align 8
-; CHECK-NEXT: store float [[A]], ptr [[L_PTR]], align 1, !tbaa.struct [[TBAA_STRUCT0]]
+; CHECK-NEXT: store float [[A]], ptr [[L_PTR]], align 1, !tbaa [[TBAA0]]
; CHECK-NEXT: [[TMP_SROA_2_0_L_PTR_SROA_IDX:%.*]] = getelementptr inbounds i8, ptr [[L_PTR]], i64 4
; CHECK-NEXT: [[TMP0:%.*]] = bitcast float [[B]] to i32
; CHECK-NEXT: [[TMP_SROA_2_0_EXTRACT_TRUNC:%.*]] = trunc i32 [[TMP0]] to i16
-; CHECK-NEXT: store i16 [[TMP_SROA_2_0_EXTRACT_TRUNC]], ptr [[TMP_SROA_2_0_L_PTR_SROA_IDX]], align 1, !tbaa.struct [[TBAA_STRUCT5:![0-9]+]]
+; CHECK-NEXT: store i16 [[TMP_SROA_2_0_EXTRACT_TRUNC]], ptr [[TMP_SROA_2_0_L_PTR_SROA_IDX]], align 1, !tbaa.struct [[TBAA_STRUCT4:![0-9]+]]
; CHECK-NEXT: ret void
;
entry:
@@ -74,8 +74,8 @@ define void @load_store_transfer_split_struct_tbaa_2_i31(ptr dereferenceable(24)
; CHECK-NEXT: store i31 [[A]], ptr [[TMP]], align 4
; CHECK-NEXT: [[TMP_4_TMP_4_SROA_IDX:%.*]] = getelementptr inbounds i8, ptr [[TMP]], i64 4
; CHECK-NEXT: store i31 [[B]], ptr [[TMP_4_TMP_4_SROA_IDX]], align 4
-; CHECK-NEXT: [[TMP_0_L1:%.*]] = load i62, ptr [[TMP]], align 4, !tbaa.struct [[TBAA_STRUCT0]]
-; CHECK-NEXT: store i62 [[TMP_0_L1]], ptr [[RES]], align 4, !tbaa.struct [[TBAA_STRUCT0]]
+; CHECK-NEXT: [[TMP_0_L1:%.*]] = load i62, ptr [[TMP]], align 4, !tbaa.struct [[TBAA_STRUCT5:![0-9]+]]
+; CHECK-NEXT: store i62 [[TMP_0_L1]], ptr [[RES]], align 4, !tbaa.struct [[TBAA_STRUCT5]]
; CHECK-NEXT: ret void
;
entry:
@@ -98,10 +98,10 @@ declare void @llvm.memcpy.p0.p0.i64(ptr noalias nocapture writeonly, ptr noalias
!3 = !{!"omnipotent char", !4, i64 0}
!4 = !{!"Simple C++ TBAA"}
;.
-; CHECK: [[TBAA_STRUCT0]] = !{i64 0, i64 4, [[TBAA1]], i64 4, i64 4, [[TBAA1]]}
-; CHECK: [[TBAA1]] = !{[[META2:![0-9]+]], [[META2]], i64 0}
-; CHECK: [[META2]] = !{!"float", [[META3:![0-9]+]], i64 0}
-; CHECK: [[META3]] = !{!"omnipotent char", [[META4:![0-9]+]], i64 0}
-; CHECK: [[META4]] = !{!"Simple C++ TBAA"}
-; CHECK: [[TBAA_STRUCT5]] = !{i64 0, i64 4, [[TBAA1]]}
+; CHECK: [[TBAA0]] = !{[[META1:![0-9]+]], [[META1]], i64 0}
+; CHECK: [[META1]] = !{!"float", [[META2:![0-9]+]], i64 0}
+; CHECK: [[META2]] = !{!"omnipotent char", [[META3:![0-9]+]], i64 0}
+; CHECK: [[META3]] = !{!"Simple C++ TBAA"}
+; CHECK: [[TBAA_STRUCT4]] = !{i64 0, i64 4, [[TBAA0]]}
+; CHECK: [[TBAA_STRUCT5]] = !{i64 0, i64 4, [[TBAA0]], i64 4, i64 4, [[TBAA0]]}
;.
More information about the llvm-branch-commits
mailing list