mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-29 23:12:55 +01:00
728acc9bd9
This is mostly to test the waters. I'd like to get results from FNT build bots and other bots running on non-x86 platforms. This feature has been pretty heavily tested over the last few months by me, and it fixes several of the execution time regressions caused by the inlining work by preventing inlining decisions from radically impacting block layout. I've seen very large improvements in yacr2 and ackermann benchmarks, along with the expected noise across all of the benchmark suite whenever code layout changes. I've analyzed all of the regressions and fixed them, or found them to be impossible to fix. See my email to llvmdev for more details. I'd like for this to be in 3.1 as it complements the inliner changes, but if any failures are showing up or anyone has concerns, it is just a flag flip and so can be easily turned off. I'm switching it on tonight to try and get at least one run through various folks' performance suites in case SPEC or something else has serious issues with it. I'll watch bots and revert if anything shows up. llvm-svn: 154816
46 lines
1.7 KiB
LLVM
46 lines
1.7 KiB
LLVM
; RUN: llc < %s -march=x86 -mtriple=i686-apple-darwin9.4.0 -disable-branch-fold | FileCheck %s
|
|
; PR2659
|
|
|
|
target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:128:128"
|
|
target triple = "i686-apple-darwin9.4.0"
|
|
|
|
define i32 @binomial(i32 %n, i32 %k) nounwind {
|
|
entry:
|
|
%cmp = icmp ugt i32 %k, %n ; <i1> [#uses=1]
|
|
br i1 %cmp, label %ifthen, label %forcond.preheader
|
|
|
|
forcond.preheader: ; preds = %entry
|
|
%cmp44 = icmp eq i32 %k, 0 ; <i1> [#uses=1]
|
|
br i1 %cmp44, label %afterfor, label %forbody
|
|
|
|
; CHECK: %forcond.preheader
|
|
; CHECK: movl $1
|
|
; CHECK-NOT: xorl
|
|
; CHECK-NOT: movl
|
|
; CHECK-NOT: LBB
|
|
; CHECK: je
|
|
|
|
; There should be no moves required in the for loop body.
|
|
; CHECK: %forbody
|
|
; CHECK-NOT: mov
|
|
; CHECK: jbe
|
|
|
|
ifthen: ; preds = %entry
|
|
ret i32 0
|
|
|
|
forbody: ; preds = %forbody, %forcond.preheader
|
|
%indvar = phi i32 [ 0, %forcond.preheader ], [ %divisor.02, %forbody ] ; <i32> [#uses=3]
|
|
%accumulator.01 = phi i32 [ 1, %forcond.preheader ], [ %div, %forbody ] ; <i32> [#uses=1]
|
|
%divisor.02 = add i32 %indvar, 1 ; <i32> [#uses=2]
|
|
%n.addr.03 = sub i32 %n, %indvar ; <i32> [#uses=1]
|
|
%mul = mul i32 %n.addr.03, %accumulator.01 ; <i32> [#uses=1]
|
|
%div = udiv i32 %mul, %divisor.02 ; <i32> [#uses=2]
|
|
%inc = add i32 %indvar, 2 ; <i32> [#uses=1]
|
|
%cmp4 = icmp ugt i32 %inc, %k ; <i1> [#uses=1]
|
|
br i1 %cmp4, label %afterfor, label %forbody
|
|
|
|
afterfor: ; preds = %forbody, %forcond.preheader
|
|
%accumulator.0.lcssa = phi i32 [ 1, %forcond.preheader ], [ %div, %forbody ] ; <i32> [#uses=1]
|
|
ret i32 %accumulator.0.lcssa
|
|
}
|