; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -passes=slp-vectorizer -S -mtriple=amdgcn-amd-amdhsa -mcpu=gfx906 < %s | FileCheck %s
define <4 x half> @phis(i1 %cmp1, <4 x half> %in1, <4 x half> %in2) {
; CHECK-LABEL: @phis(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = shufflevector <4 x half> [[IN1:%.*]], <4 x half> poison, <2 x i32> <i32 0, i32 1>
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <4 x half> [[IN1]], <4 x half> poison, <2 x i32> <i32 2, i32 3>
; CHECK-NEXT: br i1 [[CMP1:%.*]], label [[BB1:%.*]], label [[BB0:%.*]]
; CHECK: bb0:
; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <4 x half> [[IN2:%.*]], <4 x half> poison, <2 x i32> <i32 0, i32 1>
; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <4 x half> [[IN2]], <4 x half> poison, <2 x i32> <i32 2, i32 3>
; CHECK-NEXT: br label [[BB1]]
; CHECK: bb1:
; CHECK-NEXT: [[TMP4:%.*]] = phi <2 x half> [ [[TMP0]], [[ENTRY:%.*]] ], [ [[TMP2]], [[BB0]] ]
; CHECK-NEXT: [[TMP5:%.*]] = phi <2 x half> [ [[TMP1]], [[ENTRY]] ], [ [[TMP3]], [[BB0]] ]
; CHECK-NEXT: [[TMP6:%.*]] = shufflevector <2 x half> [[TMP4]], <2 x half> poison, <4 x i32> <i32 0, i32 1, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP7:%.*]] = shufflevector <2 x half> [[TMP5]], <2 x half> poison, <4 x i32> <i32 0, i32 1, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP8:%.*]] = shufflevector <2 x half> [[TMP4]], <2 x half> [[TMP5]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
; CHECK-NEXT: ret <4 x half> [[TMP8]]
;
entry:
%a0 = extractelement <4 x half> %in1, i64 0
%a1 = extractelement <4 x half> %in1, i64 1
%a2 = extractelement <4 x half> %in1, i64 2
%a3 = extractelement <4 x half> %in1, i64 3
br i1 %cmp1, label %bb1, label %bb0
bb0:
%b0 = extractelement <4 x half> %in2, i64 0
%b1 = extractelement <4 x half> %in2, i64 1
%b2 = extractelement <4 x half> %in2, i64 2
%b3 = extractelement <4 x half> %in2, i64 3
br label %bb1
bb1:
%c0 = phi half [ %a0, %entry ], [ %b0, %bb0 ]
%c1 = phi half [ %a1, %entry ], [ %b1, %bb0 ]
%c2 = phi half [ %a2, %entry ], [ %b2, %bb0 ]
%c3 = phi half [ %a3, %entry ], [ %b3, %bb0 ]
%o0 = insertelement <4 x half> undef, half %c0, i64 0
%o1 = insertelement <4 x half> %o0, half %c1, i64 1
%o2 = insertelement <4 x half> %o1, half %c2, i64 2
%o3 = insertelement <4 x half> %o2, half %c3, i64 3
ret <4 x half> %o3
}
define <4 x half> @phis_reverse(i1 %cmp1, <4 x half> %in1, <4 x half> %in2) {
; CHECK-LABEL: @phis_reverse(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = shufflevector <4 x half> [[IN1:%.*]], <4 x half> poison, <2 x i32> <i32 2, i32 3>
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <4 x half> [[IN1]], <4 x half> poison, <2 x i32> <i32 0, i32 1>
; CHECK-NEXT: br i1 [[CMP1:%.*]], label [[BB1:%.*]], label [[BB0:%.*]]
; CHECK: bb0:
; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <4 x half> [[IN2:%.*]], <4 x half> poison, <2 x i32> <i32 2, i32 3>
; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <4 x half> [[IN2]], <4 x half> poison, <2 x i32> <i32 0, i32 1>
; CHECK-NEXT: br label [[BB1]]
; CHECK: bb1:
; CHECK-NEXT: [[TMP4:%.*]] = phi <2 x half> [ [[TMP0]], [[ENTRY:%.*]] ], [ [[TMP2]], [[BB0]] ]
; CHECK-NEXT: [[TMP5:%.*]] = phi <2 x half> [ [[TMP1]], [[ENTRY]] ], [ [[TMP3]], [[BB0]] ]
; CHECK-NEXT: [[TMP6:%.*]] = shufflevector <2 x half> [[TMP5]], <2 x half> poison, <4 x i32> <i32 0, i32 1, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP7:%.*]] = shufflevector <2 x half> [[TMP4]], <2 x half> poison, <4 x i32> <i32 0, i32 1, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP8:%.*]] = shufflevector <4 x half> [[TMP6]], <4 x half> [[TMP7]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; CHECK-NEXT: ret <4 x half> [[TMP8]]
;
entry:
%a0 = extractelement <4 x half> %in1, i64 0
%a1 = extractelement <4 x half> %in1, i64 1
%a2 = extractelement <4 x half> %in1, i64 2
%a3 = extractelement <4 x half> %in1, i64 3
br i1 %cmp1, label %bb1, label %bb0
bb0:
%b0 = extractelement <4 x half> %in2, i64 0
%b1 = extractelement <4 x half> %in2, i64 1
%b2 = extractelement <4 x half> %in2, i64 2
%b3 = extractelement <4 x half> %in2, i64 3
br label %bb1
bb1:
%c3 = phi half [ %a3, %entry ], [ %b3, %bb0 ]
%c2 = phi half [ %a2, %entry ], [ %b2, %bb0 ]
%c1 = phi half [ %a1, %entry ], [ %b1, %bb0 ]
%c0 = phi half [ %a0, %entry ], [ %b0, %bb0 ]
%o0 = insertelement <4 x half> undef, half %c0, i64 0
%o1 = insertelement <4 x half> %o0, half %c1, i64 1
%o2 = insertelement <4 x half> %o1, half %c2, i64 2
%o3 = insertelement <4 x half> %o2, half %c3, i64 3
ret <4 x half> %o3
}
Codebase Browser
llvm