#include "llvm/ADT/SmallSet.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/StringExtras.h"
-#include "llvm/ADT/Triple.h"
#include <algorithm>
#include <cmath>
using namespace llvm;
// the size of a call to memcpy or memset (3 arguments + call).
if (Limit != ~0U) {
const Function *F = DAG.getMachineFunction().getFunction();
- if (F->hasFnAttr(Attribute::OptimizeForSize)) {
- Triple T(((LLVMTargetMachine&)TLI.getTargetMachine()).getTargetTriple());
- 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;
- }
+ if (F->hasFnAttr(Attribute::OptimizeForSize))
+ Limit = 4;
}
unsigned NumMemOps = 0;
-; 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>
%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* }
; statement. It can be an ADD or LEA instruction, it's not important which one
; it is.
;
-; CHECK: # %bb
-; CHECK: addq $64036, %rdi
-; CHECK: rep;stosl
+; CHECK: ## %bb
+; CHECK-NEXT: addq $64036, %rdi
+; CHECK: rep;stosl
%tmp5 = bitcast i32* %tmp4 to i8*
call void @llvm.memset.p0i8.i64(i8* %tmp5, i8 0, i64 84, i32 4, i1 false)
-; RUN: llc < %s -mtriple=x86_64-unknown-linux-gnu | FileCheck %s -check-prefix=LINUX
-; RUN: llc < %s -mtriple=x86_64-apple-darwin | FileCheck %s -check-prefix=DARWIN
+; RUN: llc < %s -march=x86-64 | FileCheck %s
declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind
tail call void @llvm.memcpy.p0i8.p0i8.i64( i8* %a, i8* %b, i64 %n, i32 1, i1 0 )
ret i8* %a
-; LINUX: test1:
-; LINUX: memcpy
+; CHECK: test1:
+; CHECK: memcpy
}
; Variable memcpy's should lower to calls.
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %tmp14, i8* %tmp25, i64 %n, i32 8, i1 0 )
ret i8* %tmp14
-; LINUX: test2:
-; LINUX: memcpy
+; CHECK: test2:
+; CHECK: memcpy
}
; Large constant memcpy's should lower to a call when optimizing for size.
; 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 {
entry:
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %A, i8* %B, i64 64, i32 1, i1 false)
ret void
-; LINUX: test3:
-; LINUX: 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
+; CHECK: test3:
+; CHECK: memcpy
}
; Large constant memcpy's should be inlined when not optimizing for size.
entry:
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %A, i8* %B, i64 64, i32 1, i1 false)
ret void
-; LINUX: test4:
-; LINUX movq
-; LINUX movq
-; LINUX movq
-; LINUX movq
-; LINUX movq
-; LINUX movq
-; LINUX movq
-; LINUX movq
-; LINUX movq
-; LINUX movq
-; LINUX movq
-; LINUX movq
+; CHECK: test4:
+; CHECK: movq
+; CHECK: movq
+; CHECK: movq
+; CHECK: movq
+; CHECK: movq
+; CHECK: movq
+; CHECK: movq
+; CHECK: movq
+; CHECK: movq
+; CHECK: movq
+; CHECK: movq
+; CHECK: movq
}