mirror of
https://github.com/RPCSX/llvm.git
synced 2024-12-16 16:37:30 +00:00
9e24ab7252
This patch adds a pass for doing PowerPC peephole optimizations at the MI level while the code is still in SSA form. This allows for easy modifications to the instructions while depending on a subsequent pass of DCE. Both passes are very fast due to the characteristics of SSA. At this time, the only peepholes added are for cleaning up various redundancies involving the XXPERMDI instruction. However, I would expect this will be a useful place to add more peepholes for inefficiencies generated during instruction selection. The pass is placed after VSX swap optimization, as it is best to let that pass remove unnecessary swaps before performing any remaining clean-ups. The utility of these clean-ups are demonstrated by changes to four existing test cases, all of which now have tighter expected code generation. I've also added Eric Schweiz's bugpoint-reduced test from PR25157, for which we now generate tight code. One other test started failing for me, and I've fixed it (test/Transforms/PlaceSafepoints/finite-loops.ll) as well; this is not related to my changes, and I'm not sure why it works before and not after. The problem is that the CHECK-NOT: of "statepoint" from test1 fails because of the "statepoint" in test2, and so forth. Adding a CHECK-LABEL in between keeps the different occurrences of that string properly scoped. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@252651 91177308-0d34-0410-b5e6-96231b3b80d8
62 lines
2.8 KiB
LLVM
62 lines
2.8 KiB
LLVM
; RUN: llc -mcpu=pwr8 -mtriple=powerpc64le-unknown-linux-gnu < %s | FileCheck %s
|
|
|
|
; Verify peephole simplification of splats and swaps. Bugpoint-reduced
|
|
; test from Eric Schweitz.
|
|
|
|
%struct.BSS38.51.4488.9911.14348.16813.20264.24701.28152.31603.35054.39491.44914.45407.46393.46886.47872.49351.49844.50830.51323.52309.53295.53788.54281.55267.55760.59211.61625 = type <{ [28 x i8] }>
|
|
%struct_main1_2_.491.4928.10351.14788.17253.20704.25141.28592.32043.35494.39931.45354.45847.46833.47326.48312.49791.50284.51270.51763.52749.53735.54228.54721.55707.56200.59651.61626 = type <{ [64 x i8] }>
|
|
|
|
@.BSS38 = external global %struct.BSS38.51.4488.9911.14348.16813.20264.24701.28152.31603.35054.39491.44914.45407.46393.46886.47872.49351.49844.50830.51323.52309.53295.53788.54281.55267.55760.59211.61625, align 32
|
|
@_main1_2_ = external global %struct_main1_2_.491.4928.10351.14788.17253.20704.25141.28592.32043.35494.39931.45354.45847.46833.47326.48312.49791.50284.51270.51763.52749.53735.54228.54721.55707.56200.59651.61626, section ".comm", align 16
|
|
|
|
define void @aercalc_() {
|
|
L.entry:
|
|
br i1 undef, label %L.LB38_2426, label %L.LB38_2911
|
|
|
|
L.LB38_2911:
|
|
br i1 undef, label %L.LB38_2140, label %L.LB38_2640
|
|
|
|
L.LB38_2640:
|
|
unreachable
|
|
|
|
L.LB38_2426:
|
|
br i1 undef, label %L.LB38_2438, label %L.LB38_2920
|
|
|
|
L.LB38_2920:
|
|
br i1 undef, label %L.LB38_2438, label %L.LB38_2921
|
|
|
|
L.LB38_2921:
|
|
br label %L.LB38_2140
|
|
|
|
L.LB38_2140:
|
|
ret void
|
|
|
|
L.LB38_2438:
|
|
br i1 undef, label %L.LB38_2451, label %L.LB38_2935
|
|
|
|
L.LB38_2935:
|
|
br i1 undef, label %L.LB38_2451, label %L.LB38_2936
|
|
|
|
L.LB38_2936:
|
|
unreachable
|
|
|
|
L.LB38_2451:
|
|
br i1 undef, label %L.LB38_2452, label %L.LB38_2937
|
|
|
|
L.LB38_2937:
|
|
unreachable
|
|
|
|
L.LB38_2452:
|
|
%0 = load float, float* bitcast (i8* getelementptr inbounds (%struct.BSS38.51.4488.9911.14348.16813.20264.24701.28152.31603.35054.39491.44914.45407.46393.46886.47872.49351.49844.50830.51323.52309.53295.53788.54281.55267.55760.59211.61625, %struct.BSS38.51.4488.9911.14348.16813.20264.24701.28152.31603.35054.39491.44914.45407.46393.46886.47872.49351.49844.50830.51323.52309.53295.53788.54281.55267.55760.59211.61625* @.BSS38, i64 0, i32 0, i64 16) to float*), align 16
|
|
%1 = fpext float %0 to double
|
|
%2 = insertelement <2 x double> undef, double %1, i32 1
|
|
store <2 x double> %2, <2 x double>* bitcast (i8* getelementptr inbounds (%struct_main1_2_.491.4928.10351.14788.17253.20704.25141.28592.32043.35494.39931.45354.45847.46833.47326.48312.49791.50284.51270.51763.52749.53735.54228.54721.55707.56200.59651.61626, %struct_main1_2_.491.4928.10351.14788.17253.20704.25141.28592.32043.35494.39931.45354.45847.46833.47326.48312.49791.50284.51270.51763.52749.53735.54228.54721.55707.56200.59651.61626* @_main1_2_, i64 0, i32 0, i64 32) to <2 x double>*), align 16
|
|
unreachable
|
|
}
|
|
|
|
; CHECK-LABEL: @aercalc_
|
|
; CHECK: lxsspx
|
|
; CHECK: xxspltd
|
|
; CHECK: stxvd2x
|
|
; CHECK-NOT: xxswapd
|