vitalybuka created this revision.
vitalybuka added reviewers: pcc, eugenis, glider, jfb.
Herald added subscribers: cfe-commits, dexonsmith.
Herald added a project: clang.
Patch extends effect of D63967 <https://reviews.llvm.org/D63967> to 32bit
platforms and improves pattern
initialization there. It cuts size of 32bit binary compiled with
-ftrivial-auto-var-init=pattern by 2%.
Using pointer on the first page was useful but is not worth of 2%
Binary size change on CTMark, (with -fuse-ld=lld -Wl,--icf=all, similar results
with default linker options)
master patch diff
Os pattern 7.915580e+05 7.727164e+05 -0.026256
O3 pattern 9.953688e+05 9.769336e+05 -0.018545
Zero vs Pattern on master
zero pattern diff
Os 7.689712e+05 7.915580e+05 0.031380
O3 9.744796e+05 9.953688e+05 0.021133
Zero vs Pattern with the patch
zero pattern diff
Os 7.689712e+05 7.727164e+05 0.003025
O3 9.744796e+05 9.769336e+05 0.001525
Repository:
rG LLVM Github Monorepo
https://reviews.llvm.org/D64597
Files:
clang/lib/CodeGen/PatternInit.cpp
clang/test/CodeGenCXX/auto-var-init.cpp
Index: clang/test/CodeGenCXX/auto-var-init.cpp
===================================================================
--- clang/test/CodeGenCXX/auto-var-init.cpp
+++ clang/test/CodeGenCXX/auto-var-init.cpp
@@ -65,9 +65,9 @@
// PATTERN-O1-NOT: @__const.test_nullinit_uninit.uninit
// PATTERN-O1-NOT: @__const.test_nullinit_braces.braces
// PATTERN-O1-NOT: @__const.test_nullinit_custom.custom
-// PATTERN-I386: @__const.test_nullinit_uninit.uninit = private unnamed_addr constant %struct.nullinit { i8* inttoptr (i32 170 to i8*) }, align 4
-// PATTERN-I386: @__const.test_nullinit_braces.braces = private unnamed_addr constant %struct.nullinit { i8* inttoptr (i32 170 to i8*) }, align 4
-// PATTERN-I386: @__const.test_nullinit_custom.custom = private unnamed_addr constant %struct.nullinit { i8* inttoptr (i32 170 to i8*) }, align 4
+// PATTERN-I386: @__const.test_nullinit_uninit.uninit = private unnamed_addr constant %struct.nullinit { i8* inttoptr (i32 -1431655766 to i8*) }, align 4
+// PATTERN-I386: @__const.test_nullinit_braces.braces = private unnamed_addr constant %struct.nullinit { i8* inttoptr (i32 -1431655766 to i8*) }, align 4
+// PATTERN-I386: @__const.test_nullinit_custom.custom = private unnamed_addr constant %struct.nullinit { i8* inttoptr (i32 -1431655766 to i8*) }, align 4
struct nullinit { char* null = nullptr; };
// PATTERN-O0: @__const.test_padded_uninit.uninit = private unnamed_addr constant { i8, [3 x i8], i32 } { i8 -86, [3 x i8] c"\AA\AA\AA", i32 -1431655766 }, align 4
// PATTERN-O0: @__const.test_padded_custom.custom = private unnamed_addr constant { i8, [3 x i8], i32 } { i8 42, [3 x i8] zeroinitializer, i32 13371337 }, align 4
@@ -181,19 +181,19 @@
// PATTERN-O1-NOT: @__const.test_base_uninit.uninit
// PATTERN-O0: @__const.test_base_braces.braces = private unnamed_addr constant %struct.base { i32 (...)** inttoptr (i64 -6148914691236517206 to i32 (...)**) }, align 8
// PATTERN-O1-NOT: @__const.test_base_braces.braces
-// PATTERN-I386: @__const.test_base_uninit.uninit = private unnamed_addr constant %struct.base { i32 (...)** inttoptr (i32 170 to i32 (...)**) }, align 4
+// PATTERN-I386: @__const.test_base_uninit.uninit = private unnamed_addr constant %struct.base { i32 (...)** inttoptr (i32 -1431655766 to i32 (...)**) }, align 4
struct base { virtual ~base(); };
// PATTERN-O0: @__const.test_derived_uninit.uninit = private unnamed_addr constant %struct.derived { %struct.base { i32 (...)** inttoptr (i64 -6148914691236517206 to i32 (...)**) } }, align 8
// PATTERN-O1-NOT: @__const.test_derived_uninit.uninit
// PATTERN-O0: @__const.test_derived_braces.braces = private unnamed_addr constant %struct.derived { %struct.base { i32 (...)** inttoptr (i64 -6148914691236517206 to i32 (...)**) } }, align 8
// PATTERN-O1-NOT: @__const.test_derived_braces.braces
-// PATTERN-I386: @__const.test_derived_uninit.uninit = private unnamed_addr constant %struct.derived { %struct.base { i32 (...)** inttoptr (i32 170 to i32 (...)**) } }, align 4
+// PATTERN-I386: @__const.test_derived_uninit.uninit = private unnamed_addr constant %struct.derived { %struct.base { i32 (...)** inttoptr (i32 -1431655766 to i32 (...)**) } }, align 4
struct derived : public base {};
// PATTERN-O0: @__const.test_virtualderived_uninit.uninit = private unnamed_addr constant %struct.virtualderived { %struct.base { i32 (...)** inttoptr (i64 -6148914691236517206 to i32 (...)**) }, %struct.derived { %struct.base { i32 (...)** inttoptr (i64 -6148914691236517206 to i32 (...)**) } } }, align 8
// PATTERN-O1-NOT: @__const.test_virtualderived_uninit.uninit
// PATTERN-O0: @__const.test_virtualderived_braces.braces = private unnamed_addr constant %struct.virtualderived { %struct.base { i32 (...)** inttoptr (i64 -6148914691236517206 to i32 (...)**) }, %struct.derived { %struct.base { i32 (...)** inttoptr (i64 -6148914691236517206 to i32 (...)**) } } }, align 8
// PATTERN-O1-NOT: @__const.test_virtualderived_braces.braces
-// PATTERN-I386: @__const.test_virtualderived_uninit.uninit = private unnamed_addr constant %struct.virtualderived { %struct.base { i32 (...)** inttoptr (i32 170 to i32 (...)**) }, %struct.derived { %struct.base { i32 (...)** inttoptr (i32 170 to i32 (...)**) } } }, align 4
+// PATTERN-I386: @__const.test_virtualderived_uninit.uninit = private unnamed_addr constant %struct.virtualderived { %struct.base { i32 (...)** inttoptr (i32 -1431655766 to i32 (...)**) }, %struct.derived { %struct.base { i32 (...)** inttoptr (i32 -1431655766 to i32 (...)**) } } }, align 4
struct virtualderived : public virtual base, public virtual derived {};
// PATTERN-O0: @__const.test_matching_uninit.uninit = private unnamed_addr constant %union.matching { i32 -1431655766 }, align 4
// PATTERN-O1-NOT: @__const.test_matching_uninit.uninit
@@ -518,7 +518,7 @@
// ZERO-LABEL: @test_intptr_uninit()
// ZERO: store i32* null, i32** %uninit, align
// PATTERN-I386-LABEL: @test_intptr_uninit()
-// PATTERN-I386: store i32* inttoptr (i32 170 to i32*), i32** %uninit, align 4
+// PATTERN-I386: store i32* inttoptr (i32 -1431655766 to i32*), i32** %uninit, align 4
TEST_BRACES(intptr, int*);
// CHECK-LABEL: @test_intptr_braces()
@@ -535,7 +535,7 @@
// ZERO-LABEL: @test_intptrptr_uninit()
// ZERO: store i32** null, i32*** %uninit, align
// PATTERN-I386-LABEL: @test_intptrptr_uninit()
-// PATTERN-I386: store i32** inttoptr (i32 170 to i32**), i32*** %uninit, align 4
+// PATTERN-I386: store i32** inttoptr (i32 -1431655766 to i32**), i32*** %uninit, align 4
TEST_BRACES(intptrptr, int**);
// CHECK-LABEL: @test_intptrptr_braces()
@@ -552,7 +552,7 @@
// ZERO-LABEL: @test_function_uninit()
// ZERO: store void ()* null, void ()** %uninit, align
// PATTERN-I386-LABEL: @test_function_uninit()
-// PATTERN-I386: store void ()* inttoptr (i32 170 to void ()*), void ()** %uninit, align 4
+// PATTERN-I386: store void ()* inttoptr (i32 -1431655766 to void ()*), void ()** %uninit, align 4
TEST_BRACES(function, void(*)());
// CHECK-LABEL: @test_function_braces()
Index: clang/lib/CodeGen/PatternInit.cpp
===================================================================
--- clang/lib/CodeGen/PatternInit.cpp
+++ clang/lib/CodeGen/PatternInit.cpp
@@ -18,11 +18,6 @@
// pointers as well as integers so that aggregates are likely to be
// initialized with this repeated value.
constexpr uint64_t LargeValue = 0xAAAAAAAAAAAAAAAAull;
- // For 32-bit platforms it's a bit trickier because, across systems, only the
- // zero page can reasonably be expected to be unmapped, and even then we need
- // a very low address. We use a smaller value, and that value sadly doesn't
- // have a repeated byte-pattern. We don't use it for integers.
- constexpr uint32_t SmallValue = 0x000000AA;
// Floating-point values are initialized as NaNs because they propagate. Using
// a repeated byte pattern means that it will be easier to initialize
// all-floating-point aggregates and arrays with memset. Further, aggregates
@@ -45,19 +40,10 @@
Ty->isVectorTy() ? Ty->getVectorElementType() : Ty);
unsigned PtrWidth = CGM.getContext().getTargetInfo().getPointerWidth(
PtrTy->getAddressSpace());
- llvm::Type *IntTy = llvm::IntegerType::get(CGM.getLLVMContext(), PtrWidth);
- uint64_t IntValue;
- switch (PtrWidth) {
- default:
+ if (PtrWidth > 64)
llvm_unreachable("pattern initialization of unsupported pointer width");
- case 64:
- IntValue = LargeValue;
- break;
- case 32:
- IntValue = SmallValue;
- break;
- }
- auto *Int = llvm::ConstantInt::get(IntTy, IntValue);
+ llvm::Type *IntTy = llvm::IntegerType::get(CGM.getLLVMContext(), PtrWidth);
+ auto *Int = llvm::ConstantInt::get(IntTy, LargeValue);
return llvm::ConstantExpr::getIntToPtr(Int, PtrTy);
}
if (Ty->isFPOrFPVectorTy()) {
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
