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

[LV] Account for predicated stores in instruction costs 

This patch ensures that we scale the estimated cost of predicated stores by
block probability. This is a follow-on patch for r284123.

llvm-svn: 284126
This commit is contained in:
Matthew Simpson 2016-10-13 14:54:31 +00:00
parent 8295d54868
commit 1d4b163fc0
2 changed files with 45 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
View File

@ -6700,6 +6700,12 @@ unsigned LoopVectorizationCostModel::getInstructionCost(Instruction *I,
// we might create due to scalarization.
Cost += getScalarizationOverhead(I, VF, TTI);
// If we have a predicated store, it may not be executed for each vector
// lane. Scale the cost by the probability of executing the predicated
// block.
if (Legal->isScalarWithPredication(I))
Cost /= getReciprocalPredBlockProb();
return Cost;
}

40
llvm/test/Transforms/LoopVectorize/AArch64/predication_costs.ll
View File

@ -1,5 +1,5 @@
; REQUIRES: asserts
; RUN: opt < %s -force-vector-width=2 -loop-vectorize -debug-only=loop-vectorize -disable-output 2>&1 | FileCheck %s
; RUN: opt < %s -force-vector-width=2 -enable-cond-stores-vec -loop-vectorize -debug-only=loop-vectorize -disable-output 2>&1 | FileCheck %s
target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
target triple = "aarch64--linux-gnu"
@ -51,3 +51,41 @@ for.end:
%tmp7 = phi i32 [ %tmp6, %for.inc ]
ret i32 %tmp7
}
; CHECK-LABEL: predicated_store
;
; This test checks that we correctly compute the cost of the predicated store
; instruction. If we assume the block probability is 50%, we compute the cost
; as:
;
; Cost for vector lane zero:
; (store(2) + 2 * extractelement(0)) / 2 = 1
; Cost for vector lane one:
; (store(2) + 2 * extractelement(3)) / 2 = 4
;
; CHECK: Found an estimated cost of 5 for VF 2 For instruction: store i32 %tmp2, i32* %tmp0, align 4
; CHECK: Scalarizing and predicating: store i32 %tmp2, i32* %tmp0, align 4
;
define void @predicated_store(i32* %a, i1 %c, i32 %x, i64 %n) {
entry:
br label %for.body
for.body:
%i = phi i64 [ 0, %entry ], [ %i.next, %for.inc ]
%tmp0 = getelementptr inbounds i32, i32* %a, i64 %i
%tmp1 = load i32, i32* %tmp0, align 4
br i1 %c, label %if.then, label %for.inc
if.then:
%tmp2 = add nsw i32 %tmp1, %x
store i32 %tmp2, i32* %tmp0, align 4
br label %for.inc
for.inc:
%i.next = add nuw nsw i64 %i, 1
%cond = icmp slt i64 %i.next, %n
br i1 %cond, label %for.body, label %for.end
for.end:
ret void
}