; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
-; RUN: opt -S -slp-vectorizer -slp-threshold=-10000 < %s | FileCheck %s --check-prefixes=ANY,BIGTHRESH
-; RUN: opt -S -slp-vectorizer -slp-threshold=0 < %s | FileCheck %s --check-prefixes=ANY,ZEROTHRESH
+; RUN: opt -S -slp-vectorizer -slp-threshold=-10000 < %s | FileCheck %s
+; RUN: opt -S -slp-vectorizer -slp-threshold=0 < %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-n8:16:32:64-S128"
target triple = "x86_64-apple-macosx10.8.0"
define <4 x float> @simple_select(<4 x float> %a, <4 x float> %b, <4 x i32> %c) #0 {
-; ANY-LABEL: @simple_select(
-; ANY-NEXT: [[TMP1:%.*]] = icmp ne <4 x i32> [[C:%.*]], zeroinitializer
-; ANY-NEXT: [[TMP2:%.*]] = select <4 x i1> [[TMP1]], <4 x float> [[A:%.*]], <4 x float> [[B:%.*]]
-; ANY-NEXT: [[TMP3:%.*]] = extractelement <4 x float> [[TMP2]], i32 0
-; ANY-NEXT: [[RA:%.*]] = insertelement <4 x float> undef, float [[TMP3]], i32 0
-; ANY-NEXT: [[TMP4:%.*]] = extractelement <4 x float> [[TMP2]], i32 1
-; ANY-NEXT: [[RB:%.*]] = insertelement <4 x float> [[RA]], float [[TMP4]], i32 1
-; ANY-NEXT: [[TMP5:%.*]] = extractelement <4 x float> [[TMP2]], i32 2
-; ANY-NEXT: [[RC:%.*]] = insertelement <4 x float> [[RB]], float [[TMP5]], i32 2
-; ANY-NEXT: [[TMP6:%.*]] = extractelement <4 x float> [[TMP2]], i32 3
-; ANY-NEXT: [[RD:%.*]] = insertelement <4 x float> [[RC]], float [[TMP6]], i32 3
-; ANY-NEXT: ret <4 x float> [[RD]]
+; CHECK-LABEL: @simple_select(
+; CHECK-NEXT: [[TMP1:%.*]] = icmp ne <4 x i32> [[C:%.*]], zeroinitializer
+; CHECK-NEXT: [[TMP2:%.*]] = select <4 x i1> [[TMP1]], <4 x float> [[A:%.*]], <4 x float> [[B:%.*]]
+; CHECK-NEXT: [[TMP3:%.*]] = extractelement <4 x float> [[TMP2]], i32 0
+; CHECK-NEXT: [[RA:%.*]] = insertelement <4 x float> undef, float [[TMP3]], i32 0
+; CHECK-NEXT: [[TMP4:%.*]] = extractelement <4 x float> [[TMP2]], i32 1
+; CHECK-NEXT: [[RB:%.*]] = insertelement <4 x float> [[RA]], float [[TMP4]], i32 1
+; CHECK-NEXT: [[TMP5:%.*]] = extractelement <4 x float> [[TMP2]], i32 2
+; CHECK-NEXT: [[RC:%.*]] = insertelement <4 x float> [[RB]], float [[TMP5]], i32 2
+; CHECK-NEXT: [[TMP6:%.*]] = extractelement <4 x float> [[TMP2]], i32 3
+; CHECK-NEXT: [[RD:%.*]] = insertelement <4 x float> [[RC]], float [[TMP6]], i32 3
+; CHECK-NEXT: ret <4 x float> [[RD]]
;
%c0 = extractelement <4 x i32> %c, i32 0
%c1 = extractelement <4 x i32> %c, i32 1
; This entire tree is ephemeral, don't vectorize any of it.
define <4 x float> @simple_select_eph(<4 x float> %a, <4 x float> %b, <4 x i32> %c) #0 {
-; ANY-LABEL: @simple_select_eph(
-; ANY-NEXT: [[C0:%.*]] = extractelement <4 x i32> [[C:%.*]], i32 0
-; ANY-NEXT: [[C1:%.*]] = extractelement <4 x i32> [[C]], i32 1
-; ANY-NEXT: [[C2:%.*]] = extractelement <4 x i32> [[C]], i32 2
-; ANY-NEXT: [[C3:%.*]] = extractelement <4 x i32> [[C]], i32 3
-; ANY-NEXT: [[A0:%.*]] = extractelement <4 x float> [[A:%.*]], i32 0
-; ANY-NEXT: [[A1:%.*]] = extractelement <4 x float> [[A]], i32 1
-; ANY-NEXT: [[A2:%.*]] = extractelement <4 x float> [[A]], i32 2
-; ANY-NEXT: [[A3:%.*]] = extractelement <4 x float> [[A]], i32 3
-; ANY-NEXT: [[B0:%.*]] = extractelement <4 x float> [[B:%.*]], i32 0
-; ANY-NEXT: [[B1:%.*]] = extractelement <4 x float> [[B]], i32 1
-; ANY-NEXT: [[B2:%.*]] = extractelement <4 x float> [[B]], i32 2
-; ANY-NEXT: [[B3:%.*]] = extractelement <4 x float> [[B]], i32 3
-; ANY-NEXT: [[CMP0:%.*]] = icmp ne i32 [[C0]], 0
-; ANY-NEXT: [[CMP1:%.*]] = icmp ne i32 [[C1]], 0
-; ANY-NEXT: [[CMP2:%.*]] = icmp ne i32 [[C2]], 0
-; ANY-NEXT: [[CMP3:%.*]] = icmp ne i32 [[C3]], 0
-; ANY-NEXT: [[S0:%.*]] = select i1 [[CMP0]], float [[A0]], float [[B0]]
-; ANY-NEXT: [[S1:%.*]] = select i1 [[CMP1]], float [[A1]], float [[B1]]
-; ANY-NEXT: [[S2:%.*]] = select i1 [[CMP2]], float [[A2]], float [[B2]]
-; ANY-NEXT: [[S3:%.*]] = select i1 [[CMP3]], float [[A3]], float [[B3]]
-; ANY-NEXT: [[RA:%.*]] = insertelement <4 x float> undef, float [[S0]], i32 0
-; ANY-NEXT: [[RB:%.*]] = insertelement <4 x float> [[RA]], float [[S1]], i32 1
-; ANY-NEXT: [[RC:%.*]] = insertelement <4 x float> [[RB]], float [[S2]], i32 2
-; ANY-NEXT: [[RD:%.*]] = insertelement <4 x float> [[RC]], float [[S3]], i32 3
-; ANY-NEXT: [[Q0:%.*]] = extractelement <4 x float> [[RD]], i32 0
-; ANY-NEXT: [[Q1:%.*]] = extractelement <4 x float> [[RD]], i32 1
-; ANY-NEXT: [[Q2:%.*]] = extractelement <4 x float> [[RD]], i32 2
-; ANY-NEXT: [[Q3:%.*]] = extractelement <4 x float> [[RD]], i32 3
-; ANY-NEXT: [[Q4:%.*]] = fadd float [[Q0]], [[Q1]]
-; ANY-NEXT: [[Q5:%.*]] = fadd float [[Q2]], [[Q3]]
-; ANY-NEXT: [[Q6:%.*]] = fadd float [[Q4]], [[Q5]]
-; ANY-NEXT: [[QI:%.*]] = fcmp olt float [[Q6]], [[Q5]]
-; ANY-NEXT: call void @llvm.assume(i1 [[QI]])
-; ANY-NEXT: ret <4 x float> undef
+; CHECK-LABEL: @simple_select_eph(
+; CHECK-NEXT: [[C0:%.*]] = extractelement <4 x i32> [[C:%.*]], i32 0
+; CHECK-NEXT: [[C1:%.*]] = extractelement <4 x i32> [[C]], i32 1
+; CHECK-NEXT: [[C2:%.*]] = extractelement <4 x i32> [[C]], i32 2
+; CHECK-NEXT: [[C3:%.*]] = extractelement <4 x i32> [[C]], i32 3
+; CHECK-NEXT: [[A0:%.*]] = extractelement <4 x float> [[A:%.*]], i32 0
+; CHECK-NEXT: [[A1:%.*]] = extractelement <4 x float> [[A]], i32 1
+; CHECK-NEXT: [[A2:%.*]] = extractelement <4 x float> [[A]], i32 2
+; CHECK-NEXT: [[A3:%.*]] = extractelement <4 x float> [[A]], i32 3
+; CHECK-NEXT: [[B0:%.*]] = extractelement <4 x float> [[B:%.*]], i32 0
+; CHECK-NEXT: [[B1:%.*]] = extractelement <4 x float> [[B]], i32 1
+; CHECK-NEXT: [[B2:%.*]] = extractelement <4 x float> [[B]], i32 2
+; CHECK-NEXT: [[B3:%.*]] = extractelement <4 x float> [[B]], i32 3
+; CHECK-NEXT: [[CMP0:%.*]] = icmp ne i32 [[C0]], 0
+; CHECK-NEXT: [[CMP1:%.*]] = icmp ne i32 [[C1]], 0
+; CHECK-NEXT: [[CMP2:%.*]] = icmp ne i32 [[C2]], 0
+; CHECK-NEXT: [[CMP3:%.*]] = icmp ne i32 [[C3]], 0
+; CHECK-NEXT: [[S0:%.*]] = select i1 [[CMP0]], float [[A0]], float [[B0]]
+; CHECK-NEXT: [[S1:%.*]] = select i1 [[CMP1]], float [[A1]], float [[B1]]
+; CHECK-NEXT: [[S2:%.*]] = select i1 [[CMP2]], float [[A2]], float [[B2]]
+; CHECK-NEXT: [[S3:%.*]] = select i1 [[CMP3]], float [[A3]], float [[B3]]
+; CHECK-NEXT: [[RA:%.*]] = insertelement <4 x float> undef, float [[S0]], i32 0
+; CHECK-NEXT: [[RB:%.*]] = insertelement <4 x float> [[RA]], float [[S1]], i32 1
+; CHECK-NEXT: [[RC:%.*]] = insertelement <4 x float> [[RB]], float [[S2]], i32 2
+; CHECK-NEXT: [[RD:%.*]] = insertelement <4 x float> [[RC]], float [[S3]], i32 3
+; CHECK-NEXT: [[Q0:%.*]] = extractelement <4 x float> [[RD]], i32 0
+; CHECK-NEXT: [[Q1:%.*]] = extractelement <4 x float> [[RD]], i32 1
+; CHECK-NEXT: [[Q2:%.*]] = extractelement <4 x float> [[RD]], i32 2
+; CHECK-NEXT: [[Q3:%.*]] = extractelement <4 x float> [[RD]], i32 3
+; CHECK-NEXT: [[Q4:%.*]] = fadd float [[Q0]], [[Q1]]
+; CHECK-NEXT: [[Q5:%.*]] = fadd float [[Q2]], [[Q3]]
+; CHECK-NEXT: [[Q6:%.*]] = fadd float [[Q4]], [[Q5]]
+; CHECK-NEXT: [[QI:%.*]] = fcmp olt float [[Q6]], [[Q5]]
+; CHECK-NEXT: call void @llvm.assume(i1 [[QI]])
+; CHECK-NEXT: ret <4 x float> undef
;
%c0 = extractelement <4 x i32> %c, i32 0
%c1 = extractelement <4 x i32> %c, i32 1
; Insert in an order different from the vector indices to make sure it
; doesn't matter
define <4 x float> @simple_select_insert_out_of_order(<4 x float> %a, <4 x float> %b, <4 x i32> %c) #0 {
-; ANY-LABEL: @simple_select_insert_out_of_order(
-; ANY-NEXT: [[REORDER_SHUFFLE:%.*]] = shufflevector <4 x i32> [[C:%.*]], <4 x i32> undef, <4 x i32> <i32 2, i32 1, i32 0, i32 3>
-; ANY-NEXT: [[REORDER_SHUFFLE1:%.*]] = shufflevector <4 x float> [[A:%.*]], <4 x float> undef, <4 x i32> <i32 2, i32 1, i32 0, i32 3>
-; ANY-NEXT: [[REORDER_SHUFFLE2:%.*]] = shufflevector <4 x float> [[B:%.*]], <4 x float> undef, <4 x i32> <i32 2, i32 1, i32 0, i32 3>
-; ANY-NEXT: [[TMP1:%.*]] = icmp ne <4 x i32> [[REORDER_SHUFFLE]], zeroinitializer
-; ANY-NEXT: [[TMP2:%.*]] = select <4 x i1> [[TMP1]], <4 x float> [[REORDER_SHUFFLE1]], <4 x float> [[REORDER_SHUFFLE2]]
-; ANY-NEXT: [[TMP3:%.*]] = extractelement <4 x float> [[TMP2]], i32 2
-; ANY-NEXT: [[RA:%.*]] = insertelement <4 x float> undef, float [[TMP3]], i32 2
-; ANY-NEXT: [[TMP4:%.*]] = extractelement <4 x float> [[TMP2]], i32 1
-; ANY-NEXT: [[RB:%.*]] = insertelement <4 x float> [[RA]], float [[TMP4]], i32 1
-; ANY-NEXT: [[TMP5:%.*]] = extractelement <4 x float> [[TMP2]], i32 0
-; ANY-NEXT: [[RC:%.*]] = insertelement <4 x float> [[RB]], float [[TMP5]], i32 0
-; ANY-NEXT: [[TMP6:%.*]] = extractelement <4 x float> [[TMP2]], i32 3
-; ANY-NEXT: [[RD:%.*]] = insertelement <4 x float> [[RC]], float [[TMP6]], i32 3
-; ANY-NEXT: ret <4 x float> [[RD]]
+; CHECK-LABEL: @simple_select_insert_out_of_order(
+; CHECK-NEXT: [[REORDER_SHUFFLE:%.*]] = shufflevector <4 x i32> [[C:%.*]], <4 x i32> undef, <4 x i32> <i32 2, i32 1, i32 0, i32 3>
+; CHECK-NEXT: [[REORDER_SHUFFLE1:%.*]] = shufflevector <4 x float> [[A:%.*]], <4 x float> undef, <4 x i32> <i32 2, i32 1, i32 0, i32 3>
+; CHECK-NEXT: [[REORDER_SHUFFLE2:%.*]] = shufflevector <4 x float> [[B:%.*]], <4 x float> undef, <4 x i32> <i32 2, i32 1, i32 0, i32 3>
+; CHECK-NEXT: [[TMP1:%.*]] = icmp ne <4 x i32> [[REORDER_SHUFFLE]], zeroinitializer
+; CHECK-NEXT: [[TMP2:%.*]] = select <4 x i1> [[TMP1]], <4 x float> [[REORDER_SHUFFLE1]], <4 x float> [[REORDER_SHUFFLE2]]
+; CHECK-NEXT: [[TMP3:%.*]] = extractelement <4 x float> [[TMP2]], i32 2
+; CHECK-NEXT: [[RA:%.*]] = insertelement <4 x float> undef, float [[TMP3]], i32 2
+; CHECK-NEXT: [[TMP4:%.*]] = extractelement <4 x float> [[TMP2]], i32 1
+; CHECK-NEXT: [[RB:%.*]] = insertelement <4 x float> [[RA]], float [[TMP4]], i32 1
+; CHECK-NEXT: [[TMP5:%.*]] = extractelement <4 x float> [[TMP2]], i32 0
+; CHECK-NEXT: [[RC:%.*]] = insertelement <4 x float> [[RB]], float [[TMP5]], i32 0
+; CHECK-NEXT: [[TMP6:%.*]] = extractelement <4 x float> [[TMP2]], i32 3
+; CHECK-NEXT: [[RD:%.*]] = insertelement <4 x float> [[RC]], float [[TMP6]], i32 3
+; CHECK-NEXT: ret <4 x float> [[RD]]
;
%c0 = extractelement <4 x i32> %c, i32 0
%c1 = extractelement <4 x i32> %c, i32 1
; Multiple users of the final constructed vector
define <4 x float> @simple_select_users(<4 x float> %a, <4 x float> %b, <4 x i32> %c) #0 {
-; ANY-LABEL: @simple_select_users(
-; ANY-NEXT: [[TMP1:%.*]] = icmp ne <4 x i32> [[C:%.*]], zeroinitializer
-; ANY-NEXT: [[TMP2:%.*]] = select <4 x i1> [[TMP1]], <4 x float> [[A:%.*]], <4 x float> [[B:%.*]]
-; ANY-NEXT: [[TMP3:%.*]] = extractelement <4 x float> [[TMP2]], i32 0
-; ANY-NEXT: [[RA:%.*]] = insertelement <4 x float> undef, float [[TMP3]], i32 0
-; ANY-NEXT: [[TMP4:%.*]] = extractelement <4 x float> [[TMP2]], i32 1
-; ANY-NEXT: [[RB:%.*]] = insertelement <4 x float> [[RA]], float [[TMP4]], i32 1
-; ANY-NEXT: [[TMP5:%.*]] = extractelement <4 x float> [[TMP2]], i32 2
-; ANY-NEXT: [[RC:%.*]] = insertelement <4 x float> [[RB]], float [[TMP5]], i32 2
-; ANY-NEXT: [[TMP6:%.*]] = extractelement <4 x float> [[TMP2]], i32 3
-; ANY-NEXT: [[RD:%.*]] = insertelement <4 x float> [[RC]], float [[TMP6]], i32 3
-; ANY-NEXT: call void @v4f32_user(<4 x float> [[RD]]) #0
-; ANY-NEXT: ret <4 x float> [[RD]]
+; CHECK-LABEL: @simple_select_users(
+; CHECK-NEXT: [[TMP1:%.*]] = icmp ne <4 x i32> [[C:%.*]], zeroinitializer
+; CHECK-NEXT: [[TMP2:%.*]] = select <4 x i1> [[TMP1]], <4 x float> [[A:%.*]], <4 x float> [[B:%.*]]
+; CHECK-NEXT: [[TMP3:%.*]] = extractelement <4 x float> [[TMP2]], i32 0
+; CHECK-NEXT: [[RA:%.*]] = insertelement <4 x float> undef, float [[TMP3]], i32 0
+; CHECK-NEXT: [[TMP4:%.*]] = extractelement <4 x float> [[TMP2]], i32 1
+; CHECK-NEXT: [[RB:%.*]] = insertelement <4 x float> [[RA]], float [[TMP4]], i32 1
+; CHECK-NEXT: [[TMP5:%.*]] = extractelement <4 x float> [[TMP2]], i32 2
+; CHECK-NEXT: [[RC:%.*]] = insertelement <4 x float> [[RB]], float [[TMP5]], i32 2
+; CHECK-NEXT: [[TMP6:%.*]] = extractelement <4 x float> [[TMP2]], i32 3
+; CHECK-NEXT: [[RD:%.*]] = insertelement <4 x float> [[RC]], float [[TMP6]], i32 3
+; CHECK-NEXT: call void @v4f32_user(<4 x float> [[RD]]) #0
+; CHECK-NEXT: ret <4 x float> [[RD]]
;
%c0 = extractelement <4 x i32> %c, i32 0
%c1 = extractelement <4 x i32> %c, i32 1
; Unused insertelement
define <4 x float> @simple_select_no_users(<4 x float> %a, <4 x float> %b, <4 x i32> %c) #0 {
-; ANY-LABEL: @simple_select_no_users(
-; ANY-NEXT: [[C0:%.*]] = extractelement <4 x i32> [[C:%.*]], i32 0
-; ANY-NEXT: [[C1:%.*]] = extractelement <4 x i32> [[C]], i32 1
-; ANY-NEXT: [[C2:%.*]] = extractelement <4 x i32> [[C]], i32 2
-; ANY-NEXT: [[C3:%.*]] = extractelement <4 x i32> [[C]], i32 3
-; ANY-NEXT: [[A0:%.*]] = extractelement <4 x float> [[A:%.*]], i32 0
-; ANY-NEXT: [[A1:%.*]] = extractelement <4 x float> [[A]], i32 1
-; ANY-NEXT: [[A2:%.*]] = extractelement <4 x float> [[A]], i32 2
-; ANY-NEXT: [[A3:%.*]] = extractelement <4 x float> [[A]], i32 3
-; ANY-NEXT: [[B0:%.*]] = extractelement <4 x float> [[B:%.*]], i32 0
-; ANY-NEXT: [[B1:%.*]] = extractelement <4 x float> [[B]], i32 1
-; ANY-NEXT: [[B2:%.*]] = extractelement <4 x float> [[B]], i32 2
-; ANY-NEXT: [[B3:%.*]] = extractelement <4 x float> [[B]], i32 3
-; ANY-NEXT: [[TMP1:%.*]] = insertelement <2 x i32> undef, i32 [[C0]], i32 0
-; ANY-NEXT: [[TMP2:%.*]] = insertelement <2 x i32> [[TMP1]], i32 [[C1]], i32 1
-; ANY-NEXT: [[TMP3:%.*]] = icmp ne <2 x i32> [[TMP2]], zeroinitializer
-; ANY-NEXT: [[TMP4:%.*]] = insertelement <2 x i32> undef, i32 [[C2]], i32 0
-; ANY-NEXT: [[TMP5:%.*]] = insertelement <2 x i32> [[TMP4]], i32 [[C3]], i32 1
-; ANY-NEXT: [[TMP6:%.*]] = icmp ne <2 x i32> [[TMP5]], zeroinitializer
-; ANY-NEXT: [[TMP7:%.*]] = insertelement <2 x float> undef, float [[A0]], i32 0
-; ANY-NEXT: [[TMP8:%.*]] = insertelement <2 x float> [[TMP7]], float [[A1]], i32 1
-; ANY-NEXT: [[TMP9:%.*]] = insertelement <2 x float> undef, float [[B0]], i32 0
-; ANY-NEXT: [[TMP10:%.*]] = insertelement <2 x float> [[TMP9]], float [[B1]], i32 1
-; ANY-NEXT: [[TMP11:%.*]] = select <2 x i1> [[TMP3]], <2 x float> [[TMP8]], <2 x float> [[TMP10]]
-; ANY-NEXT: [[TMP12:%.*]] = insertelement <2 x float> undef, float [[A2]], i32 0
-; ANY-NEXT: [[TMP13:%.*]] = insertelement <2 x float> [[TMP12]], float [[A3]], i32 1
-; ANY-NEXT: [[TMP14:%.*]] = insertelement <2 x float> undef, float [[B2]], i32 0
-; ANY-NEXT: [[TMP15:%.*]] = insertelement <2 x float> [[TMP14]], float [[B3]], i32 1
-; ANY-NEXT: [[TMP16:%.*]] = select <2 x i1> [[TMP6]], <2 x float> [[TMP13]], <2 x float> [[TMP15]]
-; ANY-NEXT: [[TMP17:%.*]] = extractelement <2 x float> [[TMP11]], i32 0
-; ANY-NEXT: [[RA:%.*]] = insertelement <4 x float> undef, float [[TMP17]], i32 0
-; ANY-NEXT: [[TMP18:%.*]] = extractelement <2 x float> [[TMP11]], i32 1
-; ANY-NEXT: [[RB:%.*]] = insertelement <4 x float> [[RA]], float [[TMP18]], i32 1
-; ANY-NEXT: [[TMP19:%.*]] = extractelement <2 x float> [[TMP16]], i32 0
-; ANY-NEXT: [[RC:%.*]] = insertelement <4 x float> undef, float [[TMP19]], i32 2
-; ANY-NEXT: [[TMP20:%.*]] = extractelement <2 x float> [[TMP16]], i32 1
-; ANY-NEXT: [[RD:%.*]] = insertelement <4 x float> [[RC]], float [[TMP20]], i32 3
-; ANY-NEXT: ret <4 x float> [[RD]]
+; CHECK-LABEL: @simple_select_no_users(
+; CHECK-NEXT: [[C0:%.*]] = extractelement <4 x i32> [[C:%.*]], i32 0
+; CHECK-NEXT: [[C1:%.*]] = extractelement <4 x i32> [[C]], i32 1
+; CHECK-NEXT: [[C2:%.*]] = extractelement <4 x i32> [[C]], i32 2
+; CHECK-NEXT: [[C3:%.*]] = extractelement <4 x i32> [[C]], i32 3
+; CHECK-NEXT: [[A0:%.*]] = extractelement <4 x float> [[A:%.*]], i32 0
+; CHECK-NEXT: [[A1:%.*]] = extractelement <4 x float> [[A]], i32 1
+; CHECK-NEXT: [[A2:%.*]] = extractelement <4 x float> [[A]], i32 2
+; CHECK-NEXT: [[A3:%.*]] = extractelement <4 x float> [[A]], i32 3
+; CHECK-NEXT: [[B0:%.*]] = extractelement <4 x float> [[B:%.*]], i32 0
+; CHECK-NEXT: [[B1:%.*]] = extractelement <4 x float> [[B]], i32 1
+; CHECK-NEXT: [[B2:%.*]] = extractelement <4 x float> [[B]], i32 2
+; CHECK-NEXT: [[B3:%.*]] = extractelement <4 x float> [[B]], i32 3
+; CHECK-NEXT: [[TMP1:%.*]] = insertelement <2 x i32> undef, i32 [[C0]], i32 0
+; CHECK-NEXT: [[TMP2:%.*]] = insertelement <2 x i32> [[TMP1]], i32 [[C1]], i32 1
+; CHECK-NEXT: [[TMP3:%.*]] = icmp ne <2 x i32> [[TMP2]], zeroinitializer
+; CHECK-NEXT: [[TMP4:%.*]] = insertelement <2 x i32> undef, i32 [[C2]], i32 0
+; CHECK-NEXT: [[TMP5:%.*]] = insertelement <2 x i32> [[TMP4]], i32 [[C3]], i32 1
+; CHECK-NEXT: [[TMP6:%.*]] = icmp ne <2 x i32> [[TMP5]], zeroinitializer
+; CHECK-NEXT: [[TMP7:%.*]] = insertelement <2 x float> undef, float [[A0]], i32 0
+; CHECK-NEXT: [[TMP8:%.*]] = insertelement <2 x float> [[TMP7]], float [[A1]], i32 1
+; CHECK-NEXT: [[TMP9:%.*]] = insertelement <2 x float> undef, float [[B0]], i32 0
+; CHECK-NEXT: [[TMP10:%.*]] = insertelement <2 x float> [[TMP9]], float [[B1]], i32 1
+; CHECK-NEXT: [[TMP11:%.*]] = select <2 x i1> [[TMP3]], <2 x float> [[TMP8]], <2 x float> [[TMP10]]
+; CHECK-NEXT: [[TMP12:%.*]] = insertelement <2 x float> undef, float [[A2]], i32 0
+; CHECK-NEXT: [[TMP13:%.*]] = insertelement <2 x float> [[TMP12]], float [[A3]], i32 1
+; CHECK-NEXT: [[TMP14:%.*]] = insertelement <2 x float> undef, float [[B2]], i32 0
+; CHECK-NEXT: [[TMP15:%.*]] = insertelement <2 x float> [[TMP14]], float [[B3]], i32 1
+; CHECK-NEXT: [[TMP16:%.*]] = select <2 x i1> [[TMP6]], <2 x float> [[TMP13]], <2 x float> [[TMP15]]
+; CHECK-NEXT: [[TMP17:%.*]] = extractelement <2 x float> [[TMP11]], i32 0
+; CHECK-NEXT: [[RA:%.*]] = insertelement <4 x float> undef, float [[TMP17]], i32 0
+; CHECK-NEXT: [[TMP18:%.*]] = extractelement <2 x float> [[TMP11]], i32 1
+; CHECK-NEXT: [[RB:%.*]] = insertelement <4 x float> [[RA]], float [[TMP18]], i32 1
+; CHECK-NEXT: [[TMP19:%.*]] = extractelement <2 x float> [[TMP16]], i32 0
+; CHECK-NEXT: [[RC:%.*]] = insertelement <4 x float> undef, float [[TMP19]], i32 2
+; CHECK-NEXT: [[TMP20:%.*]] = extractelement <2 x float> [[TMP16]], i32 1
+; CHECK-NEXT: [[RD:%.*]] = insertelement <4 x float> [[RC]], float [[TMP20]], i32 3
+; CHECK-NEXT: ret <4 x float> [[RD]]
;
%c0 = extractelement <4 x i32> %c, i32 0
%c1 = extractelement <4 x i32> %c, i32 1
; Make sure infinite loop doesn't happen which I ran into when trying
; to do this backwards this backwards
define <4 x i32> @reconstruct(<4 x i32> %c) #0 {
-; ANY-LABEL: @reconstruct(
-; ANY-NEXT: [[C0:%.*]] = extractelement <4 x i32> [[C:%.*]], i32 0
-; ANY-NEXT: [[C1:%.*]] = extractelement <4 x i32> [[C]], i32 1
-; ANY-NEXT: [[C2:%.*]] = extractelement <4 x i32> [[C]], i32 2
-; ANY-NEXT: [[C3:%.*]] = extractelement <4 x i32> [[C]], i32 3
-; ANY-NEXT: [[RA:%.*]] = insertelement <4 x i32> undef, i32 [[C0]], i32 0
-; ANY-NEXT: [[RB:%.*]] = insertelement <4 x i32> [[RA]], i32 [[C1]], i32 1
-; ANY-NEXT: [[RC:%.*]] = insertelement <4 x i32> [[RB]], i32 [[C2]], i32 2
-; ANY-NEXT: [[RD:%.*]] = insertelement <4 x i32> [[RC]], i32 [[C3]], i32 3
-; ANY-NEXT: ret <4 x i32> [[RD]]
+; CHECK-LABEL: @reconstruct(
+; CHECK-NEXT: [[C0:%.*]] = extractelement <4 x i32> [[C:%.*]], i32 0
+; CHECK-NEXT: [[C1:%.*]] = extractelement <4 x i32> [[C]], i32 1
+; CHECK-NEXT: [[C2:%.*]] = extractelement <4 x i32> [[C]], i32 2
+; CHECK-NEXT: [[C3:%.*]] = extractelement <4 x i32> [[C]], i32 3
+; CHECK-NEXT: [[RA:%.*]] = insertelement <4 x i32> undef, i32 [[C0]], i32 0
+; CHECK-NEXT: [[RB:%.*]] = insertelement <4 x i32> [[RA]], i32 [[C1]], i32 1
+; CHECK-NEXT: [[RC:%.*]] = insertelement <4 x i32> [[RB]], i32 [[C2]], i32 2
+; CHECK-NEXT: [[RD:%.*]] = insertelement <4 x i32> [[RC]], i32 [[C3]], i32 3
+; CHECK-NEXT: ret <4 x i32> [[RD]]
;
%c0 = extractelement <4 x i32> %c, i32 0
%c1 = extractelement <4 x i32> %c, i32 1
}
define <2 x float> @simple_select_v2(<2 x float> %a, <2 x float> %b, <2 x i32> %c) #0 {
-; ANY-LABEL: @simple_select_v2(
-; ANY-NEXT: [[TMP1:%.*]] = icmp ne <2 x i32> [[C:%.*]], zeroinitializer
-; ANY-NEXT: [[TMP2:%.*]] = select <2 x i1> [[TMP1]], <2 x float> [[A:%.*]], <2 x float> [[B:%.*]]
-; ANY-NEXT: [[TMP3:%.*]] = extractelement <2 x float> [[TMP2]], i32 0
-; ANY-NEXT: [[RA:%.*]] = insertelement <2 x float> undef, float [[TMP3]], i32 0
-; ANY-NEXT: [[TMP4:%.*]] = extractelement <2 x float> [[TMP2]], i32 1
-; ANY-NEXT: [[RB:%.*]] = insertelement <2 x float> [[RA]], float [[TMP4]], i32 1
-; ANY-NEXT: ret <2 x float> [[RB]]
+; CHECK-LABEL: @simple_select_v2(
+; CHECK-NEXT: [[TMP1:%.*]] = icmp ne <2 x i32> [[C:%.*]], zeroinitializer
+; CHECK-NEXT: [[TMP2:%.*]] = select <2 x i1> [[TMP1]], <2 x float> [[A:%.*]], <2 x float> [[B:%.*]]
+; CHECK-NEXT: [[TMP3:%.*]] = extractelement <2 x float> [[TMP2]], i32 0
+; CHECK-NEXT: [[RA:%.*]] = insertelement <2 x float> undef, float [[TMP3]], i32 0
+; CHECK-NEXT: [[TMP4:%.*]] = extractelement <2 x float> [[TMP2]], i32 1
+; CHECK-NEXT: [[RB:%.*]] = insertelement <2 x float> [[RA]], float [[TMP4]], i32 1
+; CHECK-NEXT: ret <2 x float> [[RB]]
;
%c0 = extractelement <2 x i32> %c, i32 0
%c1 = extractelement <2 x i32> %c, i32 1
; re-visiting the insertelement chains starting with undef
; (low cost threshold needed to force this to happen)
define <4 x float> @simple_select_partial_vector(<4 x float> %a, <4 x float> %b, <4 x i32> %c) #0 {
-; ANY-LABEL: @simple_select_partial_vector(
-; ANY-NEXT: [[C0:%.*]] = extractelement <4 x i32> [[C:%.*]], i32 0
-; ANY-NEXT: [[C1:%.*]] = extractelement <4 x i32> [[C]], i32 1
-; ANY-NEXT: [[A0:%.*]] = extractelement <4 x float> [[A:%.*]], i32 0
-; ANY-NEXT: [[A1:%.*]] = extractelement <4 x float> [[A]], i32 1
-; ANY-NEXT: [[B0:%.*]] = extractelement <4 x float> [[B:%.*]], i32 0
-; ANY-NEXT: [[B1:%.*]] = extractelement <4 x float> [[B]], i32 1
-; ANY-NEXT: [[TMP1:%.*]] = insertelement <2 x i32> undef, i32 [[C0]], i32 0
-; ANY-NEXT: [[TMP2:%.*]] = insertelement <2 x i32> [[TMP1]], i32 [[C1]], i32 1
-; ANY-NEXT: [[TMP3:%.*]] = icmp ne <2 x i32> [[TMP2]], zeroinitializer
-; ANY-NEXT: [[TMP4:%.*]] = insertelement <2 x float> undef, float [[A0]], i32 0
-; ANY-NEXT: [[TMP5:%.*]] = insertelement <2 x float> [[TMP4]], float [[A1]], i32 1
-; ANY-NEXT: [[TMP6:%.*]] = insertelement <2 x float> undef, float [[B0]], i32 0
-; ANY-NEXT: [[TMP7:%.*]] = insertelement <2 x float> [[TMP6]], float [[B1]], i32 1
-; ANY-NEXT: [[TMP8:%.*]] = select <2 x i1> [[TMP3]], <2 x float> [[TMP5]], <2 x float> [[TMP7]]
-; ANY-NEXT: [[TMP9:%.*]] = extractelement <2 x float> [[TMP8]], i32 0
-; ANY-NEXT: [[RA:%.*]] = insertelement <4 x float> undef, float [[TMP9]], i32 0
-; ANY-NEXT: [[TMP10:%.*]] = extractelement <2 x float> [[TMP8]], i32 1
-; ANY-NEXT: [[RB:%.*]] = insertelement <4 x float> [[RA]], float [[TMP10]], i32 1
-; ANY-NEXT: ret <4 x float> [[RB]]
+; CHECK-LABEL: @simple_select_partial_vector(
+; CHECK-NEXT: [[C0:%.*]] = extractelement <4 x i32> [[C:%.*]], i32 0
+; CHECK-NEXT: [[C1:%.*]] = extractelement <4 x i32> [[C]], i32 1
+; CHECK-NEXT: [[A0:%.*]] = extractelement <4 x float> [[A:%.*]], i32 0
+; CHECK-NEXT: [[A1:%.*]] = extractelement <4 x float> [[A]], i32 1
+; CHECK-NEXT: [[B0:%.*]] = extractelement <4 x float> [[B:%.*]], i32 0
+; CHECK-NEXT: [[B1:%.*]] = extractelement <4 x float> [[B]], i32 1
+; CHECK-NEXT: [[TMP1:%.*]] = insertelement <2 x i32> undef, i32 [[C0]], i32 0
+; CHECK-NEXT: [[TMP2:%.*]] = insertelement <2 x i32> [[TMP1]], i32 [[C1]], i32 1
+; CHECK-NEXT: [[TMP3:%.*]] = icmp ne <2 x i32> [[TMP2]], zeroinitializer
+; CHECK-NEXT: [[TMP4:%.*]] = insertelement <2 x float> undef, float [[A0]], i32 0
+; CHECK-NEXT: [[TMP5:%.*]] = insertelement <2 x float> [[TMP4]], float [[A1]], i32 1
+; CHECK-NEXT: [[TMP6:%.*]] = insertelement <2 x float> undef, float [[B0]], i32 0
+; CHECK-NEXT: [[TMP7:%.*]] = insertelement <2 x float> [[TMP6]], float [[B1]], i32 1
+; CHECK-NEXT: [[TMP8:%.*]] = select <2 x i1> [[TMP3]], <2 x float> [[TMP5]], <2 x float> [[TMP7]]
+; CHECK-NEXT: [[TMP9:%.*]] = extractelement <2 x float> [[TMP8]], i32 0
+; CHECK-NEXT: [[RA:%.*]] = insertelement <4 x float> undef, float [[TMP9]], i32 0
+; CHECK-NEXT: [[TMP10:%.*]] = extractelement <2 x float> [[TMP8]], i32 1
+; CHECK-NEXT: [[RB:%.*]] = insertelement <4 x float> [[RA]], float [[TMP10]], i32 1
+; CHECK-NEXT: ret <4 x float> [[RB]]
;
%c0 = extractelement <4 x i32> %c, i32 0
%c1 = extractelement <4 x i32> %c, i32 1
; Make sure that vectorization happens even if insertelements operations
; must be rescheduled. The case here is from compiling Julia.
define <4 x float> @reschedule_extract(<4 x float> %a, <4 x float> %b) {
-; ANY-LABEL: @reschedule_extract(
-; ANY-NEXT: [[TMP1:%.*]] = fadd <4 x float> [[A:%.*]], [[B:%.*]]
-; ANY-NEXT: [[TMP2:%.*]] = extractelement <4 x float> [[TMP1]], i32 0
-; ANY-NEXT: [[V0:%.*]] = insertelement <4 x float> undef, float [[TMP2]], i32 0
-; ANY-NEXT: [[TMP3:%.*]] = extractelement <4 x float> [[TMP1]], i32 1
-; ANY-NEXT: [[V1:%.*]] = insertelement <4 x float> [[V0]], float [[TMP3]], i32 1
-; ANY-NEXT: [[TMP4:%.*]] = extractelement <4 x float> [[TMP1]], i32 2
-; ANY-NEXT: [[V2:%.*]] = insertelement <4 x float> [[V1]], float [[TMP4]], i32 2
-; ANY-NEXT: [[TMP5:%.*]] = extractelement <4 x float> [[TMP1]], i32 3
-; ANY-NEXT: [[V3:%.*]] = insertelement <4 x float> [[V2]], float [[TMP5]], i32 3
-; ANY-NEXT: ret <4 x float> [[V3]]
+; CHECK-LABEL: @reschedule_extract(
+; CHECK-NEXT: [[TMP1:%.*]] = fadd <4 x float> [[A:%.*]], [[B:%.*]]
+; CHECK-NEXT: [[TMP2:%.*]] = extractelement <4 x float> [[TMP1]], i32 0
+; CHECK-NEXT: [[V0:%.*]] = insertelement <4 x float> undef, float [[TMP2]], i32 0
+; CHECK-NEXT: [[TMP3:%.*]] = extractelement <4 x float> [[TMP1]], i32 1
+; CHECK-NEXT: [[V1:%.*]] = insertelement <4 x float> [[V0]], float [[TMP3]], i32 1
+; CHECK-NEXT: [[TMP4:%.*]] = extractelement <4 x float> [[TMP1]], i32 2
+; CHECK-NEXT: [[V2:%.*]] = insertelement <4 x float> [[V1]], float [[TMP4]], i32 2
+; CHECK-NEXT: [[TMP5:%.*]] = extractelement <4 x float> [[TMP1]], i32 3
+; CHECK-NEXT: [[V3:%.*]] = insertelement <4 x float> [[V2]], float [[TMP5]], i32 3
+; CHECK-NEXT: ret <4 x float> [[V3]]
;
%a0 = extractelement <4 x float> %a, i32 0
%b0 = extractelement <4 x float> %b, i32 0
; Check that cost model for vectorization takes credit for
; instructions that are erased.
define <4 x float> @take_credit(<4 x float> %a, <4 x float> %b) {
-; ANY-LABEL: @take_credit(
-; ANY-NEXT: [[TMP1:%.*]] = fadd <4 x float> [[A:%.*]], [[B:%.*]]
-; ANY-NEXT: [[TMP2:%.*]] = extractelement <4 x float> [[TMP1]], i32 0
-; ANY-NEXT: [[V0:%.*]] = insertelement <4 x float> undef, float [[TMP2]], i32 0
-; ANY-NEXT: [[TMP3:%.*]] = extractelement <4 x float> [[TMP1]], i32 1
-; ANY-NEXT: [[V1:%.*]] = insertelement <4 x float> [[V0]], float [[TMP3]], i32 1
-; ANY-NEXT: [[TMP4:%.*]] = extractelement <4 x float> [[TMP1]], i32 2
-; ANY-NEXT: [[V2:%.*]] = insertelement <4 x float> [[V1]], float [[TMP4]], i32 2
-; ANY-NEXT: [[TMP5:%.*]] = extractelement <4 x float> [[TMP1]], i32 3
-; ANY-NEXT: [[V3:%.*]] = insertelement <4 x float> [[V2]], float [[TMP5]], i32 3
-; ANY-NEXT: ret <4 x float> [[V3]]
+; CHECK-LABEL: @take_credit(
+; CHECK-NEXT: [[TMP1:%.*]] = fadd <4 x float> [[A:%.*]], [[B:%.*]]
+; CHECK-NEXT: [[TMP2:%.*]] = extractelement <4 x float> [[TMP1]], i32 0
+; CHECK-NEXT: [[V0:%.*]] = insertelement <4 x float> undef, float [[TMP2]], i32 0
+; CHECK-NEXT: [[TMP3:%.*]] = extractelement <4 x float> [[TMP1]], i32 1
+; CHECK-NEXT: [[V1:%.*]] = insertelement <4 x float> [[V0]], float [[TMP3]], i32 1
+; CHECK-NEXT: [[TMP4:%.*]] = extractelement <4 x float> [[TMP1]], i32 2
+; CHECK-NEXT: [[V2:%.*]] = insertelement <4 x float> [[V1]], float [[TMP4]], i32 2
+; CHECK-NEXT: [[TMP5:%.*]] = extractelement <4 x float> [[TMP1]], i32 3
+; CHECK-NEXT: [[V3:%.*]] = insertelement <4 x float> [[V2]], float [[TMP5]], i32 3
+; CHECK-NEXT: ret <4 x float> [[V3]]
;
%a0 = extractelement <4 x float> %a, i32 0
%b0 = extractelement <4 x float> %b, i32 0
; Make sure we handle multiple trees that feed one build vector correctly.
define <4 x double> @multi_tree(double %w, double %x, double %y, double %z) {
-; ANY-LABEL: @multi_tree(
-; ANY-NEXT: [[TMP1:%.*]] = insertelement <4 x double> undef, double [[Z:%.*]], i32 0
-; ANY-NEXT: [[TMP2:%.*]] = insertelement <4 x double> [[TMP1]], double [[Y:%.*]], i32 1
-; ANY-NEXT: [[TMP3:%.*]] = insertelement <4 x double> [[TMP2]], double [[X:%.*]], i32 2
-; ANY-NEXT: [[TMP4:%.*]] = insertelement <4 x double> [[TMP3]], double [[W:%.*]], i32 3
-; ANY-NEXT: [[TMP5:%.*]] = fadd <4 x double> [[TMP4]], <double 3.000000e+00, double 2.000000e+00, double 1.000000e+00, double 0.000000e+00>
-; ANY-NEXT: [[TMP6:%.*]] = fmul <4 x double> [[TMP5]], <double 1.000000e+00, double 1.000000e+00, double 1.000000e+00, double 1.000000e+00>
-; ANY-NEXT: [[TMP7:%.*]] = extractelement <4 x double> [[TMP6]], i32 3
-; ANY-NEXT: [[I1:%.*]] = insertelement <4 x double> undef, double [[TMP7]], i32 3
-; ANY-NEXT: [[TMP8:%.*]] = extractelement <4 x double> [[TMP6]], i32 2
-; ANY-NEXT: [[I2:%.*]] = insertelement <4 x double> [[I1]], double [[TMP8]], i32 2
-; ANY-NEXT: [[TMP9:%.*]] = extractelement <4 x double> [[TMP6]], i32 1
-; ANY-NEXT: [[I3:%.*]] = insertelement <4 x double> [[I2]], double [[TMP9]], i32 1
-; ANY-NEXT: [[TMP10:%.*]] = extractelement <4 x double> [[TMP6]], i32 0
-; ANY-NEXT: [[I4:%.*]] = insertelement <4 x double> [[I3]], double [[TMP10]], i32 0
-; ANY-NEXT: ret <4 x double> [[I4]]
+; CHECK-LABEL: @multi_tree(
+; CHECK-NEXT: [[TMP1:%.*]] = insertelement <4 x double> undef, double [[Z:%.*]], i32 0
+; CHECK-NEXT: [[TMP2:%.*]] = insertelement <4 x double> [[TMP1]], double [[Y:%.*]], i32 1
+; CHECK-NEXT: [[TMP3:%.*]] = insertelement <4 x double> [[TMP2]], double [[X:%.*]], i32 2
+; CHECK-NEXT: [[TMP4:%.*]] = insertelement <4 x double> [[TMP3]], double [[W:%.*]], i32 3
+; CHECK-NEXT: [[TMP5:%.*]] = fadd <4 x double> [[TMP4]], <double 3.000000e+00, double 2.000000e+00, double 1.000000e+00, double 0.000000e+00>
+; CHECK-NEXT: [[TMP6:%.*]] = fmul <4 x double> [[TMP5]], <double 1.000000e+00, double 1.000000e+00, double 1.000000e+00, double 1.000000e+00>
+; CHECK-NEXT: [[TMP7:%.*]] = extractelement <4 x double> [[TMP6]], i32 3
+; CHECK-NEXT: [[I1:%.*]] = insertelement <4 x double> undef, double [[TMP7]], i32 3
+; CHECK-NEXT: [[TMP8:%.*]] = extractelement <4 x double> [[TMP6]], i32 2
+; CHECK-NEXT: [[I2:%.*]] = insertelement <4 x double> [[I1]], double [[TMP8]], i32 2
+; CHECK-NEXT: [[TMP9:%.*]] = extractelement <4 x double> [[TMP6]], i32 1
+; CHECK-NEXT: [[I3:%.*]] = insertelement <4 x double> [[I2]], double [[TMP9]], i32 1
+; CHECK-NEXT: [[TMP10:%.*]] = extractelement <4 x double> [[TMP6]], i32 0
+; CHECK-NEXT: [[I4:%.*]] = insertelement <4 x double> [[I3]], double [[TMP10]], i32 0
+; CHECK-NEXT: ret <4 x double> [[I4]]
;
%t0 = fadd double %w , 0.000000e+00
%t1 = fadd double %x , 1.000000e+00
}
define <8 x float> @_vadd256(<8 x float> %a, <8 x float> %b) local_unnamed_addr #0 {
-; ANY-LABEL: @_vadd256(
-; ANY-NEXT: [[TMP1:%.*]] = fadd <8 x float> [[A:%.*]], [[B:%.*]]
-; ANY-NEXT: [[TMP2:%.*]] = extractelement <8 x float> [[TMP1]], i32 0
-; ANY-NEXT: [[VECINIT_I:%.*]] = insertelement <8 x float> undef, float [[TMP2]], i32 0
-; ANY-NEXT: [[TMP3:%.*]] = extractelement <8 x float> [[TMP1]], i32 1
-; ANY-NEXT: [[VECINIT1_I:%.*]] = insertelement <8 x float> [[VECINIT_I]], float [[TMP3]], i32 1
-; ANY-NEXT: [[TMP4:%.*]] = extractelement <8 x float> [[TMP1]], i32 2
-; ANY-NEXT: [[VECINIT2_I:%.*]] = insertelement <8 x float> [[VECINIT1_I]], float [[TMP4]], i32 2
-; ANY-NEXT: [[TMP5:%.*]] = extractelement <8 x float> [[TMP1]], i32 3
-; ANY-NEXT: [[VECINIT3_I:%.*]] = insertelement <8 x float> [[VECINIT2_I]], float [[TMP5]], i32 3
-; ANY-NEXT: [[TMP6:%.*]] = extractelement <8 x float> [[TMP1]], i32 4
-; ANY-NEXT: [[VECINIT4_I:%.*]] = insertelement <8 x float> [[VECINIT3_I]], float [[TMP6]], i32 4
-; ANY-NEXT: [[TMP7:%.*]] = extractelement <8 x float> [[TMP1]], i32 5
-; ANY-NEXT: [[VECINIT5_I:%.*]] = insertelement <8 x float> [[VECINIT4_I]], float [[TMP7]], i32 5
-; ANY-NEXT: [[TMP8:%.*]] = extractelement <8 x float> [[TMP1]], i32 6
-; ANY-NEXT: [[VECINIT6_I:%.*]] = insertelement <8 x float> [[VECINIT5_I]], float [[TMP8]], i32 6
-; ANY-NEXT: [[TMP9:%.*]] = extractelement <8 x float> [[TMP1]], i32 7
-; ANY-NEXT: [[VECINIT7_I:%.*]] = insertelement <8 x float> [[VECINIT6_I]], float [[TMP9]], i32 7
-; ANY-NEXT: ret <8 x float> [[VECINIT7_I]]
+; CHECK-LABEL: @_vadd256(
+; CHECK-NEXT: [[TMP1:%.*]] = fadd <8 x float> [[A:%.*]], [[B:%.*]]
+; CHECK-NEXT: [[TMP2:%.*]] = extractelement <8 x float> [[TMP1]], i32 0
+; CHECK-NEXT: [[VECINIT_I:%.*]] = insertelement <8 x float> undef, float [[TMP2]], i32 0
+; CHECK-NEXT: [[TMP3:%.*]] = extractelement <8 x float> [[TMP1]], i32 1
+; CHECK-NEXT: [[VECINIT1_I:%.*]] = insertelement <8 x float> [[VECINIT_I]], float [[TMP3]], i32 1
+; CHECK-NEXT: [[TMP4:%.*]] = extractelement <8 x float> [[TMP1]], i32 2
+; CHECK-NEXT: [[VECINIT2_I:%.*]] = insertelement <8 x float> [[VECINIT1_I]], float [[TMP4]], i32 2
+; CHECK-NEXT: [[TMP5:%.*]] = extractelement <8 x float> [[TMP1]], i32 3
+; CHECK-NEXT: [[VECINIT3_I:%.*]] = insertelement <8 x float> [[VECINIT2_I]], float [[TMP5]], i32 3
+; CHECK-NEXT: [[TMP6:%.*]] = extractelement <8 x float> [[TMP1]], i32 4
+; CHECK-NEXT: [[VECINIT4_I:%.*]] = insertelement <8 x float> [[VECINIT3_I]], float [[TMP6]], i32 4
+; CHECK-NEXT: [[TMP7:%.*]] = extractelement <8 x float> [[TMP1]], i32 5
+; CHECK-NEXT: [[VECINIT5_I:%.*]] = insertelement <8 x float> [[VECINIT4_I]], float [[TMP7]], i32 5
+; CHECK-NEXT: [[TMP8:%.*]] = extractelement <8 x float> [[TMP1]], i32 6
+; CHECK-NEXT: [[VECINIT6_I:%.*]] = insertelement <8 x float> [[VECINIT5_I]], float [[TMP8]], i32 6
+; CHECK-NEXT: [[TMP9:%.*]] = extractelement <8 x float> [[TMP1]], i32 7
+; CHECK-NEXT: [[VECINIT7_I:%.*]] = insertelement <8 x float> [[VECINIT6_I]], float [[TMP9]], i32 7
+; CHECK-NEXT: ret <8 x float> [[VECINIT7_I]]
;
%vecext = extractelement <8 x float> %a, i32 0
%vecext1 = extractelement <8 x float> %b, i32 0
projects / platform / upstream / llvm.git / commitdiff