mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2025-01-23 02:32:11 +00:00
ac2cc0170f
Pass down the fact that an operand is going to be a vector of constants. This should bring the performance of MultiSource/Benchmarks/PAQ8p/paq8p on x86 back. It had degraded to scalar performance due to my pervious shift cost change that made all shifts expensive on x86. radar://13576547 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178809 91177308-0d34-0410-b5e6-96231b3b80d8
29 lines
1.0 KiB
LLVM
29 lines
1.0 KiB
LLVM
; RUN: opt -mtriple=x86_64-apple-darwin -mcpu=core2 -loop-vectorize -dce -instcombine -S < %s | FileCheck %s
|
|
|
|
@B = common global [1024 x i32] zeroinitializer, align 16
|
|
@A = common global [1024 x i32] zeroinitializer, align 16
|
|
|
|
; We use to not vectorize this loop because the shift was deemed to expensive.
|
|
; Now that we differentiate shift cost base on the operand value kind, we will
|
|
; vectorize this loop.
|
|
; CHECK: ashr <4 x i32>
|
|
define void @f() {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body:
|
|
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
|
|
%arrayidx = getelementptr inbounds [1024 x i32]* @B, i64 0, i64 %indvars.iv
|
|
%0 = load i32* %arrayidx, align 4
|
|
%shl = ashr i32 %0, 3
|
|
%arrayidx2 = getelementptr inbounds [1024 x i32]* @A, i64 0, i64 %indvars.iv
|
|
store i32 %shl, i32* %arrayidx2, align 4
|
|
%indvars.iv.next = add i64 %indvars.iv, 1
|
|
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
|
|
%exitcond = icmp eq i32 %lftr.wideiv, 1024
|
|
br i1 %exitcond, label %for.end, label %for.body
|
|
|
|
for.end:
|
|
ret void
|
|
}
|