maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[SROA] rewritePartition()/findCommonType(): if uses have conflicting type, try getTypePartition() before falling back to largest integral use type (PR47592) 

And another step towards transformss not introducing inttoptr and/or
ptrtoint casts that weren't there already.

In this case, when load/store uses have conflicting types,
instead of falling back to the iN, we can try to use allocated sub-type.
As disscussed, this isn't the best idea overall (we shouldn't rely on
allocated type), but it works fine as a temporary measure.

I've measured, and @ `-O3` as of vanilla llvm test-suite + RawSpeed,
this results in +0.05% more bitcasts, -5.51% less inttoptr
and -1.05% less ptrtoint (at the end of middle-end opt pipeline)

See https://bugs.llvm.org/show_bug.cgi?id=47592

Reviewed By: efriedma

Differential Revision: https://reviews.llvm.org/D88788
This commit is contained in:
Roman Lebedev 2020-10-07 09:17:23 +03:00
parent edd71db38b
commit 7fa503ef4a
No known key found for this signature in database
GPG Key ID: 083C3EBB4A1689E0
4 changed files with 26 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
llvm/lib/Transforms/Scalar/SROA.cpp
View File

@ -1128,9 +1128,9 @@ LLVM_DUMP_METHOD void AllocaSlices::dump() const { print(dbgs()); }
/// Walk the range of a partitioning looking for a common type to cover this
/// sequence of slices.
static Type *findCommonType(AllocaSlices::const_iterator B,
AllocaSlices::const_iterator E,
uint64_t EndOffset) {
static std::pair<Type *, IntegerType *>
findCommonType(AllocaSlices::const_iterator B, AllocaSlices::const_iterator E,
uint64_t EndOffset) {
Type *Ty = nullptr;
bool TyIsCommon = true;
IntegerType *ITy = nullptr;
@ -1174,7 +1174,7 @@ static Type *findCommonType(AllocaSlices::const_iterator B,
Ty = UserTy;
}
return TyIsCommon ? Ty : ITy;
return {TyIsCommon ? Ty : nullptr, ITy};
}
/// PHI instructions that use an alloca and are subsequently loaded can be
@ -4264,13 +4264,21 @@ AllocaInst *SROA::rewritePartition(AllocaInst &AI, AllocaSlices &AS,
// or an i8 array of an appropriate size.
Type *SliceTy = nullptr;
const DataLayout &DL = AI.getModule()->getDataLayout();
if (Type *CommonUseTy = findCommonType(P.begin(), P.end(), P.endOffset()))
if (DL.getTypeAllocSize(CommonUseTy).getFixedSize() >= P.size())
SliceTy = CommonUseTy;
std::pair<Type *, IntegerType *> CommonUseTy =
findCommonType(P.begin(), P.end(), P.endOffset());
// Do all uses operate on the same type?
if (CommonUseTy.first)
if (DL.getTypeAllocSize(CommonUseTy.first).getFixedSize() >= P.size())
SliceTy = CommonUseTy.first;
// If not, can we find an appropriate subtype in the original allocated type?
if (!SliceTy)
if (Type *TypePartitionTy = getTypePartition(DL, AI.getAllocatedType(),
P.beginOffset(), P.size()))
SliceTy = TypePartitionTy;
// If still not, can we use the largest bitwidth integer type used?
if (!SliceTy && CommonUseTy.second)
if (DL.getTypeAllocSize(CommonUseTy.second).getFixedSize() >= P.size())
SliceTy = CommonUseTy.second;
if ((!SliceTy || (SliceTy->isArrayTy() &&
SliceTy->getArrayElementType()->isIntegerTy())) &&
DL.isLegalInteger(P.size() * 8))

7
llvm/test/DebugInfo/ARM/sroa-complex.ll
View File

@ -15,14 +15,13 @@ entry:
%c.realp = getelementptr inbounds { double, double }, { double, double }* %c, i32 0, i32 0, !dbg !17
%c.imagp = getelementptr inbounds { double, double }, { double, double }* %c, i32 0, i32 1, !dbg !17
store double 0.000000e+00, double* %c.realp, align 8, !dbg !17
; SROA will split the complex double into two i64 values, because there is
; no native double data type available.
; SROA will split the complex double into two double values.
; Test that debug info for both values survives:
; CHECK: call void @llvm.dbg.value(metadata i64 0,
; CHECK: call void @llvm.dbg.value(metadata double 0.000000e+00,
; CHECK-SAME: metadata ![[C:[^,]*]],
; CHECK-SAME: metadata !DIExpression(DW_OP_LLVM_fragment, 0, 64))
store double 0.000000e+00, double* %c.imagp, align 8, !dbg !17
; CHECK: call void @llvm.dbg.value(metadata i64 0,
; CHECK: call void @llvm.dbg.value(metadata double 0.000000e+00,
; CHECK-SAME: metadata ![[C]],
; CHECK-SAME: metadata !DIExpression(DW_OP_LLVM_fragment, 64, 64))
ret void, !dbg !18

6
llvm/test/Transforms/SROA/ppcf128-no-fold.ll
View File

@ -1,4 +1,4 @@
; RUN: opt < %s -sroa -S | FileCheck %s
; RUN: opt < %s -sroa -S | FileCheck %s
target datalayout = "E-m:e-i64:64-n32:64"
target triple = "powerpc64-unknown-linux-gnu"
@ -27,8 +27,8 @@ entry:
; CHECK-LABEL: @foo
; CHECK-NOT: i128 4628293042053316608
; CHECK-NOT: i128 4653260752096854016
; CHECK-DAG: i128 bitcast (ppc_fp128 0xM403B0000000000000000000000000000 to i128)
; CHECK-DAG: i128 bitcast (ppc_fp128 0xM4093B400000000000000000000000000 to i128)
; CHECK-DAG: bitcast ppc_fp128 0xM403B0000000000000000000000000000 to i128
; CHECK-DAG: bitcast ppc_fp128 0xM4093B400000000000000000000000000 to i128
; CHECK: call void @bar(i8* %v, [2 x i128]
; CHECK: ret void

12
llvm/test/Transforms/SROA/preserve-nonnull.ll
View File

@ -51,11 +51,10 @@ entry:
define i8* @propagate_nonnull_to_int() {
; CHECK-LABEL: define i8* @propagate_nonnull_to_int(
; CHECK-NEXT: entry:
; CHECK-NEXT: %[[A:.*]] = alloca i64
; CHECK-NEXT: store i64 42, i64* %[[A]]
; CHECK-NEXT: %[[LOAD:.*]] = load volatile i64, i64* %[[A]]
; CHECK-NEXT: %[[CAST:.*]] = inttoptr i64 %[[LOAD]] to i8*
; CHECK-NEXT: ret i8* %[[CAST]]
; CHECK-NEXT: %[[A:.*]] = alloca i8*
; CHECK-NEXT: store i8* inttoptr (i64 42 to i8*), i8** %[[A]]
; CHECK-NEXT: %[[LOAD:.*]] = load volatile i8*, i8** %[[A]]
; CHECK-NEXT: ret i8* %[[LOAD]]
entry:
%a = alloca [2 x i8*]
%a.gep0 = getelementptr [2 x i8*], [2 x i8*]* %a, i32 0, i32 0
@ -75,8 +74,7 @@ entry:
define i8* @propagate_nonnull_to_int_and_promote() {
; CHECK-LABEL: define i8* @propagate_nonnull_to_int_and_promote(
; CHECK-NEXT: entry:
; CHECK-NEXT: %[[PROMOTED_VALUE:.*]] = inttoptr i64 42 to i8*
; CHECK-NEXT: ret i8* %[[PROMOTED_VALUE]]
; CHECK-NEXT: ret i8* inttoptr (i64 42 to i8*)
entry:
%a = alloca [2 x i8*], align 8
%a.gep0 = getelementptr [2 x i8*], [2 x i8*]* %a, i32 0, i32 0