1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-01 16:33:37 +01:00
llvm-mirror/test/CodeGen/CellSPU/2009-01-01-BrCond.ll
Chandler Carruth 728acc9bd9 Flip the new block-placement pass to be on by default.
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
2012-04-16 13:49:17 +00:00

32 lines
920 B
LLVM

; RUN: llc < %s -march=cellspu -o - | grep brz
; PR3274
target datalayout = "E-p:32:32:128-i1:8:128-i8:8:128-i16:16:128-i32:32:128-i64:32:128-f32:32:128-f64:64:128-v64:64:64-v128:128:128-a0:0:128-s0:128:128"
target triple = "spu"
%struct.anon = type { i64 }
%struct.fp_number_type = type { i32, i32, i32, [4 x i8], %struct.anon }
define double @__floatunsidf(i32 %arg_a) nounwind {
entry:
%in = alloca %struct.fp_number_type, align 16
%0 = getelementptr %struct.fp_number_type* %in, i32 0, i32 1
store i32 0, i32* %0, align 4
%1 = icmp eq i32 %arg_a, 0
%2 = getelementptr %struct.fp_number_type* %in, i32 0, i32 0
br i1 %1, label %bb, label %bb1
bb: ; preds = %entry
store i32 2, i32* %2, align 8
br label %bb7
bb1: ; preds = %entry
ret double 0.0
bb7: ; preds = %bb5, %bb1, %bb
ret double 1.0
}
; declare i32 @llvm.ctlz.i32(i32) nounwind readnone
declare double @__pack_d(%struct.fp_number_type*)