RPCS3/llvm
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm.git synced 2024-12-18 09:27:27 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

[AArch64] Enable post-RA MI scheduler.

Browse Source 
Phabricator Revision: http://reviews.llvm.org/D5278
Patch by Sanjin Sijaric!

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@217693 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Chad Rosier 2014-09-12 17:40:39 +00:00
parent ca332457ba
commit 4fb3a966d0
3 changed files with 37 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
lib/Target/AArch64/AArch64Subtarget.h
View File

@ -86,6 +86,9 @@ public:
return &getInstrInfo()->getRegisterInfo();
}
bool enableMachineScheduler() const override { return true; }
bool enablePostMachineScheduler() const override {
return isCortexA53() || isCortexA57();
}
bool hasZeroCycleRegMove() const { return HasZeroCycleRegMove; }

4
lib/Target/AArch64/AArch64TargetMachine.cpp
View File

@ -128,7 +128,9 @@ namespace {
class AArch64PassConfig : public TargetPassConfig {
public:
AArch64PassConfig(AArch64TargetMachine *TM, PassManagerBase &PM)
: TargetPassConfig(TM, PM) {}
: TargetPassConfig(TM, PM) {
substitutePass(&PostRASchedulerID, &PostMachineSchedulerID);
}
AArch64TargetMachine &getAArch64TargetMachine() const {
return getTM<AArch64TargetMachine>();

31
test/CodeGen/AArch64/postra-mi-sched.ll Normal file
View File

@ -0,0 +1,31 @@
; RUN: llc < %s -O3 -march=aarch64 -mcpu=cortex-a53 | FileCheck %s
; With cortex-a53, each of fmul and fcvt have latency of 6 cycles. After the
; pre-RA MI scheduler, fmul, fcvt and fdiv will be consecutive. The top-down
; post-RA MI scheduler will clean this up.
@d1 = common global double 0.000000e+00, align 8
define i32 @test1(float %s2, float %s3, double %d, i32 %i2, i32 %i3) {
entry:
; CHECK-LABEL: @test1
; CHECK: fmul
; CHECK-NEXT: add
; CHECK: fcvt
; CHECK-NEXT: mul
%mul = fmul float %s2, %s3
%conv = fpext float %mul to double
%div = fdiv double %d, %conv
store double %div, double* @d1, align 8
%factor = shl i32 %i3, 1
%add1 = add i32 %i2, 4
%add2 = add i32 %add1, %factor
%add3 = add nsw i32 %add2, %i2
%add4 = add nsw i32 %add3, %add2
%mul5 = mul i32 %add3, %add3
%mul6 = mul i32 %mul5, %add4
%mul7 = shl i32 %add4, 1
%factor18 = mul i32 %mul7, %mul6
%add9 = add i32 %factor18, %mul6
ret i32 %add9
}