mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-17 03:30:28 +00:00
bc7c58d2b1
This should hopefully have fixed the stage2/stage3 miscompare on the dragonegg
testers.
"LoopVectorize: Use the dependence test utility class
We now no longer need alias analysis - the cases that alias analysis would
handle are now handled as accesses with a large dependence distance.
We can now vectorize loops with simple constant dependence distances.
for (i = 8; i < 256; ++i) {
a[i] = a[i+4] * a[i+8];
}
for (i = 8; i < 256; ++i) {
a[i] = a[i-4] * a[i-8];
}
We would be able to vectorize about 200 more loops (in many cases the cost model
instructs us no to) in the test suite now. Results on x86-64 are a wash.
I have seen one degradation in ammp. Interestingly, the function in which we
now vectorize a loop is never executed so we probably see some instruction
cache effects. There is a 2% improvement in h264ref. There is one or the other
TSCV loop kernel that speeds up.
radar://13681598"
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@184724 91177308-0d34-0410-b5e6-96231b3b80d8
37 lines
1.5 KiB
LLVM
37 lines
1.5 KiB
LLVM
; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s
|
|
|
|
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
|
|
target triple = "x86_64-apple-macosx10.9.0"
|
|
|
|
; Make sure we vectorize this loop:
|
|
; int foo(float *a, float *b, int n) {
|
|
; for (int i=0; i<n; ++i)
|
|
; a[i] = b[i] * 3;
|
|
; }
|
|
|
|
;CHECK: for.body.preheader:
|
|
;CHECK: br i1 %cmp.zero, label %middle.block, label %vector.memcheck
|
|
;CHECK: vector.memcheck:
|
|
;CHECK: br i1 %memcheck.conflict, label %middle.block, label %vector.ph
|
|
;CHECK: load <4 x float>
|
|
define i32 @foo(float* nocapture %a, float* nocapture %b, i32 %n) nounwind uwtable ssp {
|
|
entry:
|
|
%cmp6 = icmp sgt i32 %n, 0
|
|
br i1 %cmp6, label %for.body, label %for.end
|
|
|
|
for.body: ; preds = %entry, %for.body
|
|
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
|
|
%arrayidx = getelementptr inbounds float* %b, i64 %indvars.iv
|
|
%0 = load float* %arrayidx, align 4
|
|
%mul = fmul float %0, 3.000000e+00
|
|
%arrayidx2 = getelementptr inbounds float* %a, i64 %indvars.iv
|
|
store float %mul, float* %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, %n
|
|
br i1 %exitcond, label %for.end, label %for.body
|
|
|
|
for.end: ; preds = %for.body, %entry
|
|
ret i32 undef
|
|
}
|