mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-26 04:32:44 +01:00
c640adbe73
In the following loop the dependence distance is 2 and can only be
vectorized if the vector length is no larger than this.
void foo(int *a, int *b, int N) {
#pragma clang loop vectorize(enable) vectorize_width(4)
for (int i=0; i<N; ++i) {
a[i + 2] = a[i] + b[i];
}
}
However, when specifying a VF of 4 via a loop hint this loop is
vectorized. According to [1][2], loop hints are ignored if the
optimization is not safe to apply.
This patch introduces a check to bail of vectorization if the user
specified VF is greater than the maximum feasible VF, unless explicitly
forced with '-force-vector-width=X'.
[1] https://llvm.org/docs/LangRef.html#llvm-loop-vectorize-and-llvm-loop-interleave
[2] https://clang.llvm.org/docs/LanguageExtensions.html#extensions-for-loop-hint-optimizations
Reviewed By: sdesmalen, fhahn, Meinersbur
Differential Revision: https://reviews.llvm.org/D90687
47 lines
1.5 KiB
LLVM
47 lines
1.5 KiB
LLVM
; REQUIRES: asserts
|
|
; RUN: opt -loop-vectorize -pass-remarks-analysis=loop-vectorize -debug-only=loop-vectorize -S < %s 2>&1 | FileCheck %s
|
|
|
|
; Make sure the unsafe user specified vectorization factor is clamped.
|
|
|
|
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"
|
|
|
|
; void foo(int *a, int *b) {
|
|
; #pragma clang loop vectorize(enable) vectorize_width(4)
|
|
; for (int i=0; i < 1024; ++i) {
|
|
; a[i + 2] = a[i] + b[i];
|
|
; }
|
|
; }
|
|
|
|
; CHECK: LV: User VF=4 is unsafe, clamping to max safe VF=2.
|
|
; CHECK: remark: <unknown>:0:0: User-specified vectorization factor 4 is unsafe, clamping to maximum safe vectorization factor 2
|
|
; CHECK-LABEL: @foo
|
|
; CHECK: <2 x i32>
|
|
define void @foo(i32* %a, i32* %b) {
|
|
entry:
|
|
br label %loop.ph
|
|
|
|
loop.ph:
|
|
br label %loop
|
|
|
|
loop:
|
|
%iv = phi i64 [ 0, %loop.ph ], [ %iv.next, %loop ]
|
|
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %iv
|
|
%0 = load i32, i32* %arrayidx, align 4
|
|
%arrayidx2 = getelementptr inbounds i32, i32* %b, i64 %iv
|
|
%1 = load i32, i32* %arrayidx2, align 4
|
|
%add = add nsw i32 %1, %0
|
|
%2 = add nuw nsw i64 %iv, 2
|
|
%arrayidx5 = getelementptr inbounds i32, i32* %a, i64 %2
|
|
store i32 %add, i32* %arrayidx5, align 4
|
|
%iv.next = add nuw nsw i64 %iv, 1
|
|
%exitcond.not = icmp eq i64 %iv.next, 1024
|
|
br i1 %exitcond.not, label %exit, label %loop, !llvm.loop !0
|
|
|
|
exit:
|
|
ret void
|
|
}
|
|
|
|
!0 = !{!0, !1, !2}
|
|
!1 = !{!"llvm.loop.vectorize.width", i32 4}
|
|
!2 = !{!"llvm.loop.vectorize.enable", i1 true}
|