mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-25 20:23:11 +01:00
f5c69e04e3
I broke 2 of these with a patch, but were not covered by existing tests. https://reviews.llvm.org/D63035 llvm-svn: 363158
49 lines
2.0 KiB
LLVM
49 lines
2.0 KiB
LLVM
; RUN: opt < %s -loop-vectorize -force-vector-interleave=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"
|
|
|
|
;CHECK-LABEL: @read_mod_write_single_ptr(
|
|
;CHECK: load <4 x float>
|
|
;CHECK: ret i32
|
|
define i32 @read_mod_write_single_ptr(float* nocapture %a, i32 %n) nounwind uwtable ssp {
|
|
%1 = icmp sgt i32 %n, 0
|
|
br i1 %1, label %.lr.ph, label %._crit_edge
|
|
|
|
.lr.ph: ; preds = %0, %.lr.ph
|
|
%indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ 0, %0 ]
|
|
%2 = getelementptr inbounds float, float* %a, i64 %indvars.iv
|
|
%3 = load float, float* %2, align 4
|
|
%4 = fmul float %3, 3.000000e+00
|
|
store float %4, float* %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: ; preds = %.lr.ph, %0
|
|
ret i32 undef
|
|
}
|
|
|
|
; Ensure that volatile stores are not vectorized.
|
|
; CHECK-LABEL: @read_mod_write_single_ptr_volatile_store(
|
|
; CHECK-NOT: store <4 x float>
|
|
; CHECK: ret i32
|
|
define i32 @read_mod_write_single_ptr_volatile_store(float* nocapture %a, i32 %n) nounwind uwtable ssp {
|
|
%1 = icmp sgt i32 %n, 0
|
|
br i1 %1, label %.lr.ph, label %._crit_edge
|
|
|
|
.lr.ph: ; preds = %0, %.lr.ph
|
|
%indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ 0, %0 ]
|
|
%2 = getelementptr inbounds float, float* %a, i64 %indvars.iv
|
|
%3 = load float, float* %2, align 4
|
|
%4 = fmul float %3, 3.000000e+00
|
|
store volatile float %4, float* %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: ; preds = %.lr.ph, %0
|
|
ret i32 undef
|
|
}
|