1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-23 19:23:23 +01:00
llvm-mirror/test/Transforms/LoopVectorize/gep_with_bitcast.ll
Matthew Simpson 5671f9d0a9 [LV] Don't widen trivial induction variables
We currently always vectorize induction variables. However, if an induction
variable is only used for counting loop iterations or computing addresses with
getelementptr instructions, we don't need to do this. Vectorizing these trivial
induction variables can create vector code that is difficult to simplify later
on. This is especially true when the unroll factor is greater than one, and we
create vector arithmetic when computing step vectors. With this patch, we check
if an induction variable is only used for counting iterations or computing
addresses, and if so, scalarize the arithmetic when computing step vectors
instead. This allows for greater simplification.

This patch addresses the suboptimal pointer arithmetic sequence seen in
PR27881.

Reference: https://llvm.org/bugs/show_bug.cgi?id=27881
Differential Revision: http://reviews.llvm.org/D21620

llvm-svn: 274627
2016-07-06 14:26:59 +00:00

42 lines
1.5 KiB
LLVM

; RUN: opt -S -loop-vectorize -instcombine -force-vector-width=4 < %s | FileCheck %s
target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
; Vectorization of loop with bitcast between GEP and load
; Simplified source code:
;void foo (double** __restrict__ in, bool * __restrict__ res) {
;
; for (int i = 0; i < 4096; ++i)
; res[i] = ((unsigned long long)in[i] == 0);
;}
; CHECK-LABEL: @foo
; CHECK: vector.body
; CHECK: %[[IV:.+]] = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ]
; CHECK: %[[v0:.+]] = getelementptr inbounds double*, double** %in, i64 %[[IV]]
; CHECK: %[[v1:.+]] = bitcast double** %[[v0]] to <4 x i64>*
; CHECK: %wide.load = load <4 x i64>, <4 x i64>* %[[v1]], align 8
; CHECK: icmp eq <4 x i64> %wide.load, zeroinitializer
; CHECK: br i1
define void @foo(double** noalias nocapture readonly %in, double** noalias nocapture readnone %out, i8* noalias nocapture %res) #0 {
entry:
br label %for.body
for.body:
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%arrayidx = getelementptr inbounds double*, double** %in, i64 %indvars.iv
%tmp53 = bitcast double** %arrayidx to i64*
%tmp54 = load i64, i64* %tmp53, align 8
%cmp1 = icmp eq i64 %tmp54, 0
%arrayidx3 = getelementptr inbounds i8, i8* %res, i64 %indvars.iv
%frombool = zext i1 %cmp1 to i8
store i8 %frombool, i8* %arrayidx3, align 1
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv.next, 4096
br i1 %exitcond, label %for.end, label %for.body
for.end:
ret void
}