b76089c7f3
Update the logic in narrowToSingleScalar to allow narrowing even if not all users use scalars, if at least one of the operands already needs broadcasting. In that case, there won't be any additional broadcasts introduced. This should allow removing the special handling for stores, which can introduce additional broadcasts currently. Fixes https://github.com/llvm/llvm-project/issues/169668. PR: https://github.com/llvm/llvm-project/pull/168246
76 lines
4.5 KiB
LLVM
76 lines
4.5 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 4
|
|
; RUN: opt -passes=loop-vectorize -mtriple=riscv64 -mattr=+v -S %s | FileCheck %s
|
|
|
|
define void @test(ptr %p, i64 %a, i8 %b) {
|
|
; CHECK-LABEL: define void @test(
|
|
; CHECK-SAME: ptr [[P:%.*]], i64 [[A:%.*]], i8 [[B:%.*]]) #[[ATTR0:[0-9]+]] {
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: br label [[VECTOR_PH:%.*]]
|
|
; CHECK: vector.ph:
|
|
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 2 x i8> poison, i8 [[B]], i64 0
|
|
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 2 x i8> [[BROADCAST_SPLATINSERT]], <vscale x 2 x i8> poison, <vscale x 2 x i32> zeroinitializer
|
|
; CHECK-NEXT: [[TMP0:%.*]] = shl i64 [[A]], 48
|
|
; CHECK-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[TMP0]], i64 0
|
|
; CHECK-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <vscale x 2 x i64> [[BROADCAST_SPLATINSERT1]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
|
|
; CHECK-NEXT: [[TMP6:%.*]] = ashr <vscale x 2 x i64> [[BROADCAST_SPLAT2]], splat (i64 52)
|
|
; CHECK-NEXT: [[TMP7:%.*]] = trunc <vscale x 2 x i64> [[TMP6]] to <vscale x 2 x i32>
|
|
; CHECK-NEXT: [[TMP8:%.*]] = zext <vscale x 2 x i8> [[BROADCAST_SPLAT]] to <vscale x 2 x i32>
|
|
; CHECK-NEXT: [[BROADCAST_SPLATINSERT3:%.*]] = insertelement <vscale x 2 x ptr> poison, ptr [[P]], i64 0
|
|
; CHECK-NEXT: [[BROADCAST_SPLAT4:%.*]] = shufflevector <vscale x 2 x ptr> [[BROADCAST_SPLATINSERT3]], <vscale x 2 x ptr> poison, <vscale x 2 x i32> zeroinitializer
|
|
; CHECK-NEXT: [[TMP9:%.*]] = call <vscale x 2 x i32> @llvm.stepvector.nxv2i32()
|
|
; CHECK-NEXT: [[TMP10:%.*]] = mul <vscale x 2 x i32> [[TMP9]], splat (i32 1)
|
|
; CHECK-NEXT: [[INDUCTION:%.*]] = add <vscale x 2 x i32> zeroinitializer, [[TMP10]]
|
|
; CHECK-NEXT: br label [[FOR_COND:%.*]]
|
|
; CHECK: vector.body:
|
|
; CHECK-NEXT: [[VEC_IND:%.*]] = phi <vscale x 2 x i32> [ [[INDUCTION]], [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[FOR_COND]] ]
|
|
; CHECK-NEXT: [[AVL:%.*]] = phi i32 [ 9, [[VECTOR_PH]] ], [ [[AVL_NEXT:%.*]], [[FOR_COND]] ]
|
|
; CHECK-NEXT: [[TMP11:%.*]] = call i32 @llvm.experimental.get.vector.length.i32(i32 [[AVL]], i32 2, i1 true)
|
|
; CHECK-NEXT: [[BROADCAST_SPLATINSERT7:%.*]] = insertelement <vscale x 2 x i32> poison, i32 [[TMP11]], i64 0
|
|
; CHECK-NEXT: [[BROADCAST_SPLAT8:%.*]] = shufflevector <vscale x 2 x i32> [[BROADCAST_SPLATINSERT7]], <vscale x 2 x i32> poison, <vscale x 2 x i32> zeroinitializer
|
|
; CHECK-NEXT: [[TMP12:%.*]] = icmp slt <vscale x 2 x i32> [[VEC_IND]], splat (i32 2)
|
|
; CHECK-NEXT: [[PREDPHI:%.*]] = select <vscale x 2 x i1> [[TMP12]], <vscale x 2 x i32> [[TMP8]], <vscale x 2 x i32> [[TMP7]]
|
|
; CHECK-NEXT: [[TMP16:%.*]] = shl <vscale x 2 x i32> [[PREDPHI]], splat (i32 8)
|
|
; CHECK-NEXT: [[TMP17:%.*]] = trunc <vscale x 2 x i32> [[TMP16]] to <vscale x 2 x i8>
|
|
; CHECK-NEXT: call void @llvm.vp.scatter.nxv2i8.nxv2p0(<vscale x 2 x i8> [[TMP17]], <vscale x 2 x ptr> align 1 [[BROADCAST_SPLAT4]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP11]])
|
|
; CHECK-NEXT: [[AVL_NEXT]] = sub nuw i32 [[AVL]], [[TMP11]]
|
|
; CHECK-NEXT: [[VEC_IND_NEXT]] = add <vscale x 2 x i32> [[VEC_IND]], [[BROADCAST_SPLAT8]]
|
|
; CHECK-NEXT: [[TMP21:%.*]] = icmp eq i32 [[AVL_NEXT]], 0
|
|
; CHECK-NEXT: br i1 [[TMP21]], label [[MIDDLE_BLOCK:%.*]], label [[FOR_COND]], !llvm.loop [[LOOP0:![0-9]+]]
|
|
; CHECK: middle.block:
|
|
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
|
|
; CHECK: exit:
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
br label %for.cond
|
|
|
|
for.cond: ; preds = %for.body, %entry
|
|
%iv = phi i32 [ 0, %entry ], [ %add, %for.body ]
|
|
%add = add i32 %iv, 1
|
|
%cmp.slt = icmp slt i32 %iv, 2
|
|
%shl = shl i64 %a, 48
|
|
%ashr = ashr i64 %shl, 52
|
|
%trunc.i32 = trunc i64 %ashr to i32
|
|
br i1 %cmp.slt, label %cond.false, label %for.body
|
|
|
|
cond.false: ; preds = %for.cond
|
|
%zext = zext i8 %b to i32
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %cond.false, %for.cond
|
|
%cond = phi i32 [ %trunc.i32, %for.cond ], [ %zext, %cond.false ]
|
|
%shl.i32 = shl i32 %cond, 8
|
|
%trunc = trunc i32 %shl.i32 to i8
|
|
store i8 %trunc, ptr %p, align 1
|
|
%cmp = icmp slt i32 %iv, 8
|
|
br i1 %cmp, label %for.cond, label %exit
|
|
|
|
exit: ; preds = %for.body
|
|
ret void
|
|
}
|
|
;.
|
|
; CHECK: [[LOOP0]] = distinct !{[[LOOP0]], [[META1:![0-9]+]], [[META2:![0-9]+]]}
|
|
; CHECK: [[META1]] = !{!"llvm.loop.isvectorized", i32 1}
|
|
; CHECK: [[META2]] = !{!"llvm.loop.unroll.runtime.disable"}
|
|
;.
|