a99dd8344e
Many tests were running extra passes after loop-vectorize, but they made no difference to the outcome. If tests don't require these extra passes, then we shouldn't run them because it increases the testing time.
66 lines
2.0 KiB
LLVM
66 lines
2.0 KiB
LLVM
; RUN: opt < %s -passes=loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -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"
|
|
|
|
@a = common global [2048 x i32] zeroinitializer, align 16
|
|
|
|
; This is the loop.
|
|
; for (i=0; i<n; i++){
|
|
; a[i] += i;
|
|
; }
|
|
;CHECK-LABEL: @inc(
|
|
;CHECK: load <4 x i32>
|
|
;CHECK: add nsw <4 x i32>
|
|
;CHECK: store <4 x i32>
|
|
;CHECK: ret void
|
|
define void @inc(i32 %n) noinline {
|
|
%1 = icmp sgt i32 %n, 0
|
|
br i1 %1, label %.lr.ph, label %._crit_edge
|
|
|
|
.lr.ph:
|
|
%indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ 0, %0 ]
|
|
%2 = getelementptr inbounds [2048 x i32], ptr @a, i64 0, i64 %indvars.iv
|
|
%3 = load i32, ptr %2, align 4
|
|
%4 = trunc i64 %indvars.iv to i32
|
|
%5 = add nsw i32 %3, %4
|
|
store i32 %5, ptr %2, 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 %._crit_edge, label %.lr.ph
|
|
|
|
._crit_edge:
|
|
ret void
|
|
}
|
|
|
|
; Can't vectorize this loop because the access to A[X] is non-linear.
|
|
;
|
|
; for (i = 0; i < n; ++i) {
|
|
; A[B[i]]++;
|
|
;
|
|
;CHECK-LABEL: @histogram(
|
|
;CHECK-NOT: <4 x i32>
|
|
;CHECK: ret i32
|
|
define i32 @histogram(ptr nocapture noalias %A, ptr nocapture noalias %B, i32 %n) {
|
|
entry:
|
|
%cmp6 = icmp sgt i32 %n, 0
|
|
br i1 %cmp6, label %for.body, label %for.end
|
|
|
|
for.body:
|
|
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
|
|
%arrayidx = getelementptr inbounds i32, ptr %B, i64 %indvars.iv
|
|
%0 = load i32, ptr %arrayidx, align 4
|
|
%idxprom1 = sext i32 %0 to i64
|
|
%arrayidx2 = getelementptr inbounds i32, ptr %A, i64 %idxprom1
|
|
%1 = load i32, ptr %arrayidx2, align 4
|
|
%inc = add nsw i32 %1, 1
|
|
store i32 %inc, ptr %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:
|
|
ret i32 0
|
|
}
|