ba91dd14b9
We no longer need to declare LLVM intrinsics in .ll files as the intrinsics are populated automatically in the module. Remove the declarations from tests to reduce test noise and size. This came from a suggestion on PR #190786.
45 lines
1.9 KiB
LLVM
45 lines
1.9 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 2
|
|
; RUN: opt < %s -passes=loop-vectorize -force-vector-width=2 -S | FileCheck %s
|
|
|
|
define void @d() {
|
|
; CHECK-LABEL: define void @d() {
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: br label [[VECTOR_PH:%.*]]
|
|
; CHECK: vector.ph:
|
|
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
|
|
; CHECK: vector.body:
|
|
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
|
|
; CHECK-NEXT: [[TMP0:%.*]] = load float, ptr null, align 4
|
|
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <2 x float> poison, float [[TMP0]], i64 0
|
|
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <2 x float> [[BROADCAST_SPLATINSERT]], <2 x float> poison, <2 x i32> zeroinitializer
|
|
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr float, ptr @d, i64 [[INDEX]]
|
|
; CHECK-NEXT: [[TMP2:%.*]] = call <2 x i1> @llvm.is.fpclass.v2f32(<2 x float> [[BROADCAST_SPLAT]], i32 0)
|
|
; CHECK-NEXT: [[TMP3:%.*]] = select <2 x i1> [[TMP2]], <2 x float> zeroinitializer, <2 x float> splat (float 1.000000e+00)
|
|
; CHECK-NEXT: store <2 x float> [[TMP3]], ptr [[TMP1]], align 4
|
|
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 2
|
|
; CHECK-NEXT: [[TMP7:%.*]] = icmp eq i64 [[INDEX_NEXT]], 128
|
|
; CHECK-NEXT: br i1 [[TMP7]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
|
|
; CHECK: middle.block:
|
|
; CHECK-NEXT: br label [[LOOP:%.*]]
|
|
; CHECK: exit:
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
br label %loop
|
|
|
|
loop:
|
|
%i = phi i64 [ 0, %entry ], [ %i7, %loop ]
|
|
%i3 = load float, ptr null, align 4
|
|
%i4 = getelementptr float, ptr @d, i64 %i
|
|
%i5 = tail call i1 @llvm.is.fpclass.f32(float %i3, i32 0)
|
|
%i6 = select i1 %i5, float 0.0, float 1.0
|
|
store float %i6, ptr %i4, align 4
|
|
%i7 = add i64 %i, 1
|
|
%i8 = icmp eq i64 %i7, 128
|
|
br i1 %i8, label %exit, label %loop
|
|
|
|
exit:
|
|
ret void
|
|
}
|
|
|