forked from OSchip/llvm-project
[PowerPC] Mark all instructions as non-cheap for MachineLICM
MachineLICM uses a callback named hasLowDefLatency to determine if an instruction def operand has a 'low' latency. If all relevant operands have a 'low' latency, the instruction is considered too cheap to hoist out of loops even in low-register-pressure situations. On PowerPC cores, both the embedded cores and the others, there is no reason to believe that this is a good choice: all instructions have a cost inside a loop, and hoisting them when not limited by register pressure is a reasonable default. llvm-svn: 225471
This commit is contained in:
parent
0709f5160f
commit
3c0952b072
|
@ -106,6 +106,15 @@ public:
|
|||
UseNode, UseIdx);
|
||||
}
|
||||
|
||||
bool hasLowDefLatency(const InstrItineraryData *ItinData,
|
||||
const MachineInstr *DefMI,
|
||||
unsigned DefIdx) const override {
|
||||
// Machine LICM should hoist all instructions in low-register-pressure
|
||||
// situations; none are sufficiently free to justify leaving in a loop
|
||||
// body.
|
||||
return false;
|
||||
}
|
||||
|
||||
bool isCoalescableExtInstr(const MachineInstr &MI,
|
||||
unsigned &SrcReg, unsigned &DstReg,
|
||||
unsigned &SubIdx) const override;
|
||||
|
|
|
@ -0,0 +1,55 @@
|
|||
; RUN: llc -mcpu=pwr7 < %s | FileCheck %s
|
||||
target datalayout = "E-m:e-i64:64-n32:64"
|
||||
target triple = "powerpc64-unknown-linux-gnu"
|
||||
|
||||
; Function Attrs: nounwind
|
||||
define double @foo() #1 {
|
||||
entry:
|
||||
%x = alloca [2048 x float], align 4
|
||||
%y = alloca [2048 x float], align 4
|
||||
%0 = bitcast [2048 x float]* %x to i8*
|
||||
call void @llvm.lifetime.start(i64 8192, i8* %0) #2
|
||||
%1 = bitcast [2048 x float]* %y to i8*
|
||||
call void @llvm.lifetime.start(i64 8192, i8* %1) #2
|
||||
br label %for.body.i
|
||||
|
||||
; CHECK-LABEL: @foo
|
||||
; CHECK: addi [[REG1:[0-9]+]], 1,
|
||||
; CHECK: addi [[REG2:[0-9]+]], 1,
|
||||
; CHECK: %for.body.i
|
||||
; CHECK-DAG: lfsx {{[0-9]+}}, [[REG1]],
|
||||
; CHECK-DAG: lfsx {{[0-9]+}}, [[REG2]],
|
||||
; CHECK: blr
|
||||
|
||||
for.body.i: ; preds = %for.body.i.preheader, %for.body.i
|
||||
%accumulator.09.i = phi double [ %add.i, %for.body.i ], [ 0.000000e+00, %entry ]
|
||||
%i.08.i = phi i64 [ %inc.i, %for.body.i ], [ 0, %entry ]
|
||||
%arrayidx.i = getelementptr inbounds [2048 x float]* %x, i64 0, i64 %i.08.i
|
||||
%v14 = load float* %arrayidx.i, align 4
|
||||
%conv.i = fpext float %v14 to double
|
||||
%arrayidx1.i = getelementptr inbounds [2048 x float]* %y, i64 0, i64 %i.08.i
|
||||
%v15 = load float* %arrayidx1.i, align 4
|
||||
%conv2.i = fpext float %v15 to double
|
||||
%mul.i = fmul double %conv.i, %conv2.i
|
||||
%add.i = fadd double %accumulator.09.i, %mul.i
|
||||
%inc.i = add nuw nsw i64 %i.08.i, 1
|
||||
%exitcond.i = icmp eq i64 %i.08.i, 2047
|
||||
br i1 %exitcond.i, label %loop.exit, label %for.body.i
|
||||
|
||||
loop.exit: ; preds = %for.body.i
|
||||
ret double %accumulator.09.i
|
||||
}
|
||||
|
||||
; Function Attrs: nounwind
|
||||
declare void @llvm.lifetime.start(i64, i8* nocapture) #2
|
||||
|
||||
declare void @bar(float*, float*)
|
||||
|
||||
; Function Attrs: nounwind
|
||||
declare void @llvm.lifetime.end(i64, i8* nocapture) #2
|
||||
|
||||
attributes #0 = { nounwind readonly }
|
||||
attributes #1 = { nounwind }
|
||||
attributes #2 = { nounwind }
|
||||
|
||||
|
Loading…
Reference in New Issue