26b7d9d622
This patch adds further support for vectorisation of loops that involve
selecting an integer value based on a previous comparison. Consider the
following C++ loop:
int r = a;
for (int i = 0; i < n; i++) {
if (src[i] > 3) {
r = b;
}
src[i] += 2;
}
We should be able to vectorise this loop because all we are doing is
selecting between two states - 'a' and 'b' - both of which are loop
invariant. This just involves building a vector of values that contain
either 'a' or 'b', where the final reduced value will be 'b' if any lane
contains 'b'.
The IR generated by clang typically looks like this:
%phi = phi i32 [ %a, %entry ], [ %phi.update, %for.body ]
...
%pred = icmp ugt i32 %val, i32 3
%phi.update = select i1 %pred, i32 %b, i32 %phi
We already detect min/max patterns, which also involve a select + cmp.
However, with the min/max patterns we are selecting loaded values (and
hence loop variant) in the loop. In addition we only support certain
cmp predicates. This patch adds a new pattern matching function
(isSelectCmpPattern) and new RecurKind enums - SelectICmp & SelectFCmp.
We only support selecting values that are integer and loop invariant,
however we can support any kind of compare - integer or float.
Tests have been added here:
Transforms/LoopVectorize/AArch64/sve-select-cmp.ll
Transforms/LoopVectorize/select-cmp-predicated.ll
Transforms/LoopVectorize/select-cmp.ll
Differential Revision: https://reviews.llvm.org/D108136
61 lines
4.0 KiB
LLVM
61 lines
4.0 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt < %s -loop-vectorize -force-target-supports-scalable-vectors=true -scalable-vectorization=on -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"
|
|
|
|
define i8 @reduction_add_trunc(i8* noalias nocapture %A) {
|
|
; CHECK-LABEL: @reduction_add_trunc(
|
|
; CHECK: vector.body:
|
|
; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, %vector.ph ], [ [[INDEX_NEXT:%.*]], %vector.body ]
|
|
; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <vscale x 8 x i32> [ insertelement (<vscale x 8 x i32> shufflevector (<vscale x 8 x i32> insertelement (<vscale x 8 x i32> poison, i32 0, i32 0), <vscale x 8 x i32> poison, <vscale x 8 x i32> zeroinitializer), i32 255, i32 0), %vector.ph ], [ [[TMP34:%.*]], %vector.body ]
|
|
; CHECK-NEXT: [[VEC_PHI1:%.*]] = phi <vscale x 8 x i32> [ shufflevector (<vscale x 8 x i32> insertelement (<vscale x 8 x i32> poison, i32 0, i32 0), <vscale x 8 x i32> poison, <vscale x 8 x i32> zeroinitializer), %vector.ph ], [ [[TMP36:%.*]], %vector.body ]
|
|
; CHECK: [[TMP14:%.*]] = and <vscale x 8 x i32> [[VEC_PHI]], shufflevector (<vscale x 8 x i32> insertelement (<vscale x 8 x i32> poison, i32 255, i32 0), <vscale x 8 x i32> poison, <vscale x 8 x i32> zeroinitializer)
|
|
; CHECK-NEXT: [[TMP15:%.*]] = and <vscale x 8 x i32> [[VEC_PHI1]], shufflevector (<vscale x 8 x i32> insertelement (<vscale x 8 x i32> poison, i32 255, i32 0), <vscale x 8 x i32> poison, <vscale x 8 x i32> zeroinitializer)
|
|
; CHECK: [[WIDE_LOAD:%.*]] = load <vscale x 8 x i8>, <vscale x 8 x i8>*
|
|
; CHECK: [[WIDE_LOAD2:%.*]] = load <vscale x 8 x i8>, <vscale x 8 x i8>*
|
|
; CHECK-NEXT: [[TMP26:%.*]] = zext <vscale x 8 x i8> [[WIDE_LOAD]] to <vscale x 8 x i32>
|
|
; CHECK-NEXT: [[TMP27:%.*]] = zext <vscale x 8 x i8> [[WIDE_LOAD2]] to <vscale x 8 x i32>
|
|
; CHECK-NEXT: [[TMP28:%.*]] = add <vscale x 8 x i32> [[TMP14]], [[TMP26]]
|
|
; CHECK-NEXT: [[TMP29:%.*]] = add <vscale x 8 x i32> [[TMP15]], [[TMP27]]
|
|
; CHECK-NEXT: [[TMP30:%.*]] = call i32 @llvm.vscale.i32()
|
|
; CHECK-NEXT: [[TMP31:%.*]] = mul i32 [[TMP30]], 16
|
|
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i32 [[INDEX]], [[TMP31]]
|
|
; CHECK-NEXT: [[TMP32:%.*]] = icmp eq i32 [[INDEX_NEXT]], {{%.*}}
|
|
; CHECK-NEXT: [[TMP33:%.*]] = trunc <vscale x 8 x i32> [[TMP28]] to <vscale x 8 x i8>
|
|
; CHECK-NEXT: [[TMP34]] = zext <vscale x 8 x i8> [[TMP33]] to <vscale x 8 x i32>
|
|
; CHECK-NEXT: [[TMP35:%.*]] = trunc <vscale x 8 x i32> [[TMP29]] to <vscale x 8 x i8>
|
|
; CHECK-NEXT: [[TMP36]] = zext <vscale x 8 x i8> [[TMP35]] to <vscale x 8 x i32>
|
|
; CHECK: middle.block:
|
|
; CHECK-NEXT: [[TMP37:%.*]] = trunc <vscale x 8 x i32> [[TMP34]] to <vscale x 8 x i8>
|
|
; CHECK-NEXT: [[TMP38:%.*]] = trunc <vscale x 8 x i32> [[TMP36]] to <vscale x 8 x i8>
|
|
; CHECK-NEXT: [[BIN_RDX:%.*]] = add <vscale x 8 x i8> [[TMP38]], [[TMP37]]
|
|
; CHECK-NEXT: [[TMP39:%.*]] = call i8 @llvm.vector.reduce.add.nxv8i8(<vscale x 8 x i8> [[BIN_RDX]])
|
|
; CHECK-NEXT: [[TMP40:%.*]] = zext i8 [[TMP39]] to i32
|
|
;
|
|
entry:
|
|
br label %loop
|
|
|
|
loop: ; preds = %entry, %loop
|
|
%indvars.iv = phi i32 [ %indvars.iv.next, %loop ], [ 0, %entry ]
|
|
%sum.02p = phi i32 [ %l9, %loop ], [ 255, %entry ]
|
|
%sum.02 = and i32 %sum.02p, 255
|
|
%l2 = getelementptr inbounds i8, i8* %A, i32 %indvars.iv
|
|
%l3 = load i8, i8* %l2, align 4
|
|
%l3e = zext i8 %l3 to i32
|
|
%l9 = add i32 %sum.02, %l3e
|
|
%indvars.iv.next = add i32 %indvars.iv, 1
|
|
%exitcond = icmp eq i32 %indvars.iv.next, 256
|
|
br i1 %exitcond, label %exit, label %loop, !llvm.loop !0
|
|
|
|
exit: ; preds = %loop
|
|
%sum.0.lcssa = phi i32 [ %l9, %loop ]
|
|
%ret = trunc i32 %sum.0.lcssa to i8
|
|
ret i8 %ret
|
|
}
|
|
|
|
!0 = distinct !{!0, !1, !2, !3, !4}
|
|
!1 = !{!"llvm.loop.vectorize.width", i32 8}
|
|
!2 = !{!"llvm.loop.vectorize.scalable.enable", i1 true}
|
|
!3 = !{!"llvm.loop.interleave.count", i32 2}
|
|
!4 = !{!"llvm.loop.vectorize.enable", i1 true}
|