maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

LoopUnroll: Allow analyzing intrinsic call costs 

I'm not sure why the code here is skipping calls since
TTI does try to do something for general calls, but it
at least should allow intrinsics.

Skip intrinsics that should not be omitted as calls, which
is by far the most common case on AMDGPU.

llvm-svn: 335645
This commit is contained in:
Matt Arsenault 2018-06-26 18:51:17 +00:00
parent e745cf9bf3
commit 2c1a570aab
2 changed files with 84 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
llvm/lib/Transforms/Scalar/LoopUnrollPass.cpp
View File

@ -515,8 +515,13 @@ static Optional<EstimatedUnrollCost> analyzeLoopUnrollCost(
// Can't properly model a cost of a call.
// FIXME: With a proper cost model we should be able to do it.
if(isa<CallInst>(&I))
return None;
if (auto *CI = dyn_cast<CallInst>(&I)) {
const Function *Callee = CI->getCalledFunction();
if (!Callee || TTI.isLoweredToCall(Callee)) {
LLVM_DEBUG(dbgs() << "Can't analyze cost of loop with call\n");
return None;
}
}
// If the instruction might have a side-effect recursively account for
// the cost of it and all the instructions leading up to it.

77
llvm/test/Transforms/LoopUnroll/AMDGPU/unroll-cost-call.ll Normal file
View File

@ -0,0 +1,77 @@
; RUN: opt -S -mtriple=amdgcn-unknown-amdhsa -mcpu=hawaii -loop-unroll -unroll-threshold=100 -unroll-peel-count=0 -unroll-allow-partial=false -unroll-max-iteration-count-to-analyze=16 < %s | FileCheck %s
; CHECK-LABEL: @test_intrinsic_call_cost(
; CHECK-NOT: br i1
define amdgpu_kernel void @test_intrinsic_call_cost(float addrspace(1)* noalias nocapture %out, float addrspace(1)* noalias nocapture %in) #0 {
entry:
br label %for.body
for.body:
%indvars.iv = phi i32 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%sum.02 = phi float [ %fmul, %for.body ], [ 0.0, %entry ]
%arrayidx.in = getelementptr inbounds float, float addrspace(1)* %in, i32 %indvars.iv
%arrayidx.out = getelementptr inbounds float, float addrspace(1)* %out, i32 %indvars.iv
%load = load float, float addrspace(1)* %arrayidx.in
%call = call float @llvm.minnum.f32(float %load, float 1.0);
%fmul = fmul float %call, %sum.02
store float %fmul, float addrspace(1)* %arrayidx.out
%indvars.iv.next = add i32 %indvars.iv, 1
%exitcond = icmp eq i32 %indvars.iv.next, 16
br i1 %exitcond, label %for.end, label %for.body
for.end:
ret void
}
; CHECK-LABEL: @test_func_call_cost(
; CHECK: br i1 %exitcond
define amdgpu_kernel void @test_func_call_cost(float addrspace(1)* noalias nocapture %out, float addrspace(1)* noalias nocapture %in) #0 {
entry:
br label %for.body
for.body:
%indvars.iv = phi i32 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%sum.02 = phi float [ %fmul, %for.body ], [ 0.0, %entry ]
%arrayidx.in = getelementptr inbounds float, float addrspace(1)* %in, i32 %indvars.iv
%arrayidx.out = getelementptr inbounds float, float addrspace(1)* %out, i32 %indvars.iv
%load = load float, float addrspace(1)* %arrayidx.in
%fptr = load float(float, float)*, float(float, float )* addrspace(4)* null
%call = tail call float %fptr(float %load, float 1.0)
%fmul = fmul float %call, %sum.02
store float %fmul, float addrspace(1)* %arrayidx.out
%indvars.iv.next = add i32 %indvars.iv, 1
%exitcond = icmp eq i32 %indvars.iv.next, 16
br i1 %exitcond, label %for.end, label %for.body
for.end:
ret void
}
; CHECK-LABEL: @test_indirect_call_cost(
; CHECK: br i1 %exitcond
define amdgpu_kernel void @test_indirect_call_cost(float addrspace(1)* noalias nocapture %out, float addrspace(1)* noalias nocapture %in) #0 {
entry:
br label %for.body
for.body:
%indvars.iv = phi i32 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%sum.02 = phi float [ %fmul, %for.body ], [ 0.0, %entry ]
%arrayidx.in = getelementptr inbounds float, float addrspace(1)* %in, i32 %indvars.iv
%arrayidx.out = getelementptr inbounds float, float addrspace(1)* %out, i32 %indvars.iv
%load = load float, float addrspace(1)* %arrayidx.in
%min = call float @func(float %load, float 1.0);
%fmul = fmul float %min, %sum.02
store float %fmul, float addrspace(1)* %arrayidx.out
%indvars.iv.next = add i32 %indvars.iv, 1
%exitcond = icmp eq i32 %indvars.iv.next, 16
br i1 %exitcond, label %for.end, label %for.body
for.end:
ret void
}
declare float @llvm.minnum.f32(float, float) #1
declare float @func(float, float) #1
attributes #0 = { nounwind }
attributes #1 = { nounwind readnone speculatable }