llvm-6502/test/CodeGen/X86/2010-09-17-SideEffectsInChain.ll
Eric Christopher 7c2cdb1c05 Turn on list-ilp scheduling by default on x86 and x86-64, fix up
testcases accordingly. Some are currently xfailed and will be filed
as bugs to be fixed or understood.

Performance results:

roughly neutral on SPEC
some micro benchmarks in the llvm suite are up between 100 and 150%, only
a pair of regressions that are due to be investigated

john-the-ripper saw:
10% improvement in traditional DES
8% improvement in BSDI DES
59% improvement in FreeBSD MD5
67% improvement in OpenBSD Blowfish
14% improvement in LM DES

Small compile time impact.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127208 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-08 02:42:25 +00:00

27 lines
1.0 KiB
LLVM

; RUN: llc < %s -combiner-alias-analysis -march=x86-64 | FileCheck %s
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
target triple = "x86_64-apple-darwin10.4"
declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind
define fastcc i32 @cli_magic_scandesc(i8* %in) nounwind ssp {
entry:
%a = alloca [64 x i8]
%b = getelementptr inbounds [64 x i8]* %a, i64 0, i32 0
%c = getelementptr inbounds [64 x i8]* %a, i64 0, i32 30
%d = load i8* %b, align 8
%e = load i8* %c, align 8
%f = bitcast [64 x i8]* %a to i8*
call void @llvm.memcpy.p0i8.p0i8.i64(i8* %f, i8* %in, i64 64, i32 8, i1 false) nounwind
store i8 %d, i8* %b, align 8
store i8 %e, i8* %c, align 8
ret i32 0
}
; CHECK: movq ___stack_chk_guard@GOTPCREL(%rip), %rax
; CHECK: movb 38(%rsp), %bl
; CHECK: movb 8(%rsp), %dl
; CHECK: movb %dl, 8(%rsp)
; CHECK: movb %bl, 38(%rsp)
; CHECK: callq ___stack_chk_fail