Revert r122936. I'll re-implement the change.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@122949 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Evan Cheng
2011-01-06 06:17:53 +00:00
parent 238589ebf5
commit 255874ff52
3 changed files with 26 additions and 57 deletions

View File

@@ -50,7 +50,6 @@
#include "llvm/ADT/SmallSet.h" #include "llvm/ADT/SmallSet.h"
#include "llvm/ADT/SmallVector.h" #include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/StringExtras.h" #include "llvm/ADT/StringExtras.h"
#include "llvm/ADT/Triple.h"
#include <algorithm> #include <algorithm>
#include <cmath> #include <cmath>
using namespace llvm; using namespace llvm;
@@ -3287,14 +3286,8 @@ static bool FindOptimalMemOpLowering(std::vector<EVT> &MemOps,
// the size of a call to memcpy or memset (3 arguments + call). // the size of a call to memcpy or memset (3 arguments + call).
if (Limit != ~0U) { if (Limit != ~0U) {
const Function *F = DAG.getMachineFunction().getFunction(); const Function *F = DAG.getMachineFunction().getFunction();
if (F->hasFnAttr(Attribute::OptimizeForSize)) { if (F->hasFnAttr(Attribute::OptimizeForSize))
Triple T(((LLVMTargetMachine&)TLI.getTargetMachine()).getTargetTriple()); Limit = 4;
if (T.getOS() != Triple::Darwin)
// A pretty terrible hack to defat the wild guess. On Darwin, -Os means
// optimize for size without hurting performance so we don't want to
// bump down the limit.
Limit = 4;
}
} }
unsigned NumMemOps = 0; unsigned NumMemOps = 0;

View File

@@ -1,4 +1,4 @@
; RUN: llc -O1 -mtriple=x86_64-unknown-linux-gnu -relocation-model=pic -disable-fp-elim < %s | FileCheck %s ; RUN: llc -O1 -mtriple=x86_64-apple-darwin10 -relocation-model=pic -disable-fp-elim < %s | FileCheck %s
; <rdar://problem/8124405> ; <rdar://problem/8124405>
%struct.type = type { %struct.subtype*, i32, i8, i32, i8, i32, i32, i32, i32, i32, i8, i32, i32, i32, i32, i32, [256 x i32], i32, [257 x i32], [257 x i32], i32*, i16*, i8*, i32, i32, i32, i32, i32, [256 x i8], [16 x i8], [256 x i8], [4096 x i8], [16 x i32], [18002 x i8], [18002 x i8], [6 x [258 x i8]], [6 x [258 x i32]], [6 x [258 x i32]], [6 x [258 x i32]], [6 x i32], i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32*, i32*, i32* } %struct.type = type { %struct.subtype*, i32, i8, i32, i8, i32, i32, i32, i32, i32, i8, i32, i32, i32, i32, i32, [256 x i32], i32, [257 x i32], [257 x i32], i32*, i16*, i8*, i32, i32, i32, i32, i32, [256 x i8], [16 x i8], [256 x i8], [4096 x i8], [16 x i32], [18002 x i8], [18002 x i8], [6 x [258 x i8]], [6 x [258 x i32]], [6 x [258 x i32]], [6 x [258 x i32]], [6 x i32], i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32*, i32*, i32* }
@@ -21,9 +21,9 @@ bb:
; statement. It can be an ADD or LEA instruction, it's not important which one ; statement. It can be an ADD or LEA instruction, it's not important which one
; it is. ; it is.
; ;
; CHECK: # %bb ; CHECK: ## %bb
; CHECK: addq $64036, %rdi ; CHECK-NEXT: addq $64036, %rdi
; CHECK: rep;stosl ; CHECK: rep;stosl
%tmp5 = bitcast i32* %tmp4 to i8* %tmp5 = bitcast i32* %tmp4 to i8*
call void @llvm.memset.p0i8.i64(i8* %tmp5, i8 0, i64 84, i32 4, i1 false) call void @llvm.memset.p0i8.i64(i8* %tmp5, i8 0, i64 84, i32 4, i1 false)

View File

@@ -1,5 +1,4 @@
; RUN: llc < %s -mtriple=x86_64-unknown-linux-gnu | FileCheck %s -check-prefix=LINUX ; RUN: llc < %s -march=x86-64 | FileCheck %s
; RUN: llc < %s -mtriple=x86_64-apple-darwin | FileCheck %s -check-prefix=DARWIN
declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind
@@ -10,8 +9,8 @@ entry:
tail call void @llvm.memcpy.p0i8.p0i8.i64( i8* %a, i8* %b, i64 %n, i32 1, i1 0 ) tail call void @llvm.memcpy.p0i8.p0i8.i64( i8* %a, i8* %b, i64 %n, i32 1, i1 0 )
ret i8* %a ret i8* %a
; LINUX: test1: ; CHECK: test1:
; LINUX: memcpy ; CHECK: memcpy
} }
; Variable memcpy's should lower to calls. ; Variable memcpy's should lower to calls.
@@ -22,41 +21,18 @@ entry:
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %tmp14, i8* %tmp25, i64 %n, i32 8, i1 0 ) tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %tmp14, i8* %tmp25, i64 %n, i32 8, i1 0 )
ret i8* %tmp14 ret i8* %tmp14
; LINUX: test2: ; CHECK: test2:
; LINUX: memcpy ; CHECK: memcpy
} }
; Large constant memcpy's should lower to a call when optimizing for size. ; Large constant memcpy's should lower to a call when optimizing for size.
; PR6623 ; PR6623
; On the other hand, Darwin's definition of -Os is optimizing for size without
; hurting performance so it should just ignore optsize when expanding memcpy.
; rdar://8821501
define void @test3(i8* nocapture %A, i8* nocapture %B) nounwind optsize noredzone { define void @test3(i8* nocapture %A, i8* nocapture %B) nounwind optsize noredzone {
entry: entry:
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %A, i8* %B, i64 64, i32 1, i1 false) tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %A, i8* %B, i64 64, i32 1, i1 false)
ret void ret void
; LINUX: test3: ; CHECK: test3:
; LINUX: memcpy ; CHECK: memcpy
; DARWIN: test3:
; DARWIN-NOT: memcpy
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
} }
; Large constant memcpy's should be inlined when not optimizing for size. ; Large constant memcpy's should be inlined when not optimizing for size.
@@ -64,18 +40,18 @@ define void @test4(i8* nocapture %A, i8* nocapture %B) nounwind noredzone {
entry: entry:
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %A, i8* %B, i64 64, i32 1, i1 false) tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %A, i8* %B, i64 64, i32 1, i1 false)
ret void ret void
; LINUX: test4: ; CHECK: test4:
; LINUX movq ; CHECK: movq
; LINUX movq ; CHECK: movq
; LINUX movq ; CHECK: movq
; LINUX movq ; CHECK: movq
; LINUX movq ; CHECK: movq
; LINUX movq ; CHECK: movq
; LINUX movq ; CHECK: movq
; LINUX movq ; CHECK: movq
; LINUX movq ; CHECK: movq
; LINUX movq ; CHECK: movq
; LINUX movq ; CHECK: movq
; LINUX movq ; CHECK: movq
} }