1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-25 20:23:11 +01:00
llvm-mirror/test/Transforms/LoopVectorize/hoist-loads.ll
Philip Reames 63d4c607da [LoopVectorize] Leverage speculation safety to avoid masked.loads
If we're vectorizing a load in a predicated block, check to see if the load can be speculated rather than predicated.  This allows us to generate a normal vector load instead of a masked.load.

To do so, we must prove that all bytes accessed on any iteration of the original loop are dereferenceable, and that all loads (across all iterations) are properly aligned.  This is equivelent to proving that hoisting the load into the loop header in the original scalar loop is safe.

Note: There are a couple of code motion todos in the code.  My intention is to wait about a day - to be sure this sticks - and then perform the NFC motion without furthe review.

Differential Revision: https://reviews.llvm.org/D66688

llvm-svn: 371452
2019-09-09 20:54:13 +00:00

71 lines
2.5 KiB
LLVM

; RUN: opt -loop-vectorize -force-vector-width=2 -force-vector-interleave=1 -S < %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 [1024 x float] zeroinitializer, align 16
@B = common global [1024 x float] zeroinitializer, align 16
; Make sure we can vectorize in the presence of hoistable conditional loads.
; CHECK-LABEL: @hoist_cond_load(
; CHECK: load <2 x float>
define void @hoist_cond_load() {
entry:
br label %for.body
for.body:
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %if.end9 ]
%arrayidx = getelementptr inbounds [1024 x float], [1024 x float]* @A, i64 0, i64 %indvars.iv
%arrayidx2 = getelementptr inbounds [1024 x float], [1024 x float]* @B, i64 0, i64 %indvars.iv
%0 = load float, float* %arrayidx2, align 4
%cmp3 = fcmp oeq float %0, 0.000000e+00
br i1 %cmp3, label %if.end9, label %if.else
if.else:
%1 = load float, float* %arrayidx, align 4
br label %if.end9
if.end9:
%tmp.0 = phi float [ %1, %if.else ], [ 0.000000e+00, %for.body ]
store float %tmp.0, float* %arrayidx, align 4
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp ne i32 %lftr.wideiv, 1024
br i1 %exitcond, label %for.body, label %for.end
for.end:
ret void
}
; However, we can't hoist loads whose address we have not seen unconditionally
; accessed. One wide load is fine, but not the second.
; CHECK-LABEL: @dont_hoist_cond_load(
; CHECK: load <2 x float>
; CHECK-NOT: load <2 x float>
define void @dont_hoist_cond_load([1024 x float]* %a) {
entry:
br label %for.body
for.body:
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %if.end9 ]
%arrayidx = getelementptr inbounds [1024 x float], [1024 x float]* %a, i64 0, i64 %indvars.iv
%arrayidx2 = getelementptr inbounds [1024 x float], [1024 x float]* @B, i64 0, i64 %indvars.iv
%0 = load float, float* %arrayidx2, align 4
%cmp3 = fcmp oeq float %0, 0.000000e+00
br i1 %cmp3, label %if.end9, label %if.else
if.else:
%1 = load float, float* %arrayidx, align 4
br label %if.end9
if.end9:
%tmp.0 = phi float [ %1, %if.else ], [ 0.000000e+00, %for.body ]
store float %tmp.0, float* %arrayidx2, align 4
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp ne i32 %lftr.wideiv, 1024
br i1 %exitcond, label %for.body, label %for.end
for.end:
ret void
}