[llvm] r289817 - [TEST] Initial commit of tests for minmax horizontal reductions.
Alexey Bataev via llvm-commits
llvm-commits at lists.llvm.org
Thu Dec 15 05:21:30 PST 2016
Author: abataev
Date: Thu Dec 15 07:21:29 2016
New Revision: 289817
URL: http://llvm.org/viewvc/llvm-project?rev=289817&view=rev
Log:
[TEST] Initial commit of tests for minmax horizontal reductions.
Added:
llvm/trunk/test/Transforms/SLPVectorizer/X86/horizontal-minmax.ll
Added: llvm/trunk/test/Transforms/SLPVectorizer/X86/horizontal-minmax.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Transforms/SLPVectorizer/X86/horizontal-minmax.ll?rev=289817&view=auto
==============================================================================
--- llvm/trunk/test/Transforms/SLPVectorizer/X86/horizontal-minmax.ll (added)
+++ llvm/trunk/test/Transforms/SLPVectorizer/X86/horizontal-minmax.ll Thu Dec 15 07:21:29 2016
@@ -0,0 +1,1725 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt < %s -mtriple=x86_64-unknown-linux -slp-vectorizer -S | FileCheck %s
+; RUN: opt < %s -mtriple=x86_64-unknown-linux -mcpu=corei7-avx -slp-vectorizer -S | FileCheck %s --check-prefix=AVX
+; RUN: opt < %s -mtriple=x86_64-unknown-linux -mcpu=core-avx2 -slp-vectorizer -S | FileCheck %s --check-prefix=AVX2
+; RUN: opt < %s -mtriple=x86_64-unknown-linux -mcpu=skx -slp-vectorizer -S | FileCheck %s --check-prefix=SKX
+
+ at arr = local_unnamed_addr global [32 x i32] zeroinitializer, align 16
+ at arr1 = local_unnamed_addr global [32 x float] zeroinitializer, align 16
+
+define i32 @maxi8(i32) {
+; CHECK-LABEL: @maxi8(
+; CHECK-NEXT: [[TMP2:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 0), align 16
+; CHECK-NEXT: [[TMP3:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 1), align 4
+; CHECK-NEXT: [[TMP4:%.*]] = icmp sgt i32 [[TMP2]], [[TMP3]]
+; CHECK-NEXT: [[TMP5:%.*]] = select i1 [[TMP4]], i32 [[TMP2]], i32 [[TMP3]]
+; CHECK-NEXT: [[TMP6:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 2), align 8
+; CHECK-NEXT: [[TMP7:%.*]] = icmp sgt i32 [[TMP5]], [[TMP6]]
+; CHECK-NEXT: [[TMP8:%.*]] = select i1 [[TMP7]], i32 [[TMP5]], i32 [[TMP6]]
+; CHECK-NEXT: [[TMP9:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 3), align 4
+; CHECK-NEXT: [[TMP10:%.*]] = icmp sgt i32 [[TMP8]], [[TMP9]]
+; CHECK-NEXT: [[TMP11:%.*]] = select i1 [[TMP10]], i32 [[TMP8]], i32 [[TMP9]]
+; CHECK-NEXT: [[TMP12:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 4), align 16
+; CHECK-NEXT: [[TMP13:%.*]] = icmp sgt i32 [[TMP11]], [[TMP12]]
+; CHECK-NEXT: [[TMP14:%.*]] = select i1 [[TMP13]], i32 [[TMP11]], i32 [[TMP12]]
+; CHECK-NEXT: [[TMP15:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 5), align 4
+; CHECK-NEXT: [[TMP16:%.*]] = icmp sgt i32 [[TMP14]], [[TMP15]]
+; CHECK-NEXT: [[TMP17:%.*]] = select i1 [[TMP16]], i32 [[TMP14]], i32 [[TMP15]]
+; CHECK-NEXT: [[TMP18:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 6), align 8
+; CHECK-NEXT: [[TMP19:%.*]] = icmp sgt i32 [[TMP17]], [[TMP18]]
+; CHECK-NEXT: [[TMP20:%.*]] = select i1 [[TMP19]], i32 [[TMP17]], i32 [[TMP18]]
+; CHECK-NEXT: [[TMP21:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 7), align 4
+; CHECK-NEXT: [[TMP22:%.*]] = icmp sgt i32 [[TMP20]], [[TMP21]]
+; CHECK-NEXT: [[TMP23:%.*]] = select i1 [[TMP22]], i32 [[TMP20]], i32 [[TMP21]]
+; CHECK-NEXT: ret i32 [[TMP23]]
+;
+; AVX-LABEL: @maxi8(
+; AVX-NEXT: [[TMP2:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 0), align 16
+; AVX-NEXT: [[TMP3:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 1), align 4
+; AVX-NEXT: [[TMP4:%.*]] = icmp sgt i32 [[TMP2]], [[TMP3]]
+; AVX-NEXT: [[TMP5:%.*]] = select i1 [[TMP4]], i32 [[TMP2]], i32 [[TMP3]]
+; AVX-NEXT: [[TMP6:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 2), align 8
+; AVX-NEXT: [[TMP7:%.*]] = icmp sgt i32 [[TMP5]], [[TMP6]]
+; AVX-NEXT: [[TMP8:%.*]] = select i1 [[TMP7]], i32 [[TMP5]], i32 [[TMP6]]
+; AVX-NEXT: [[TMP9:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 3), align 4
+; AVX-NEXT: [[TMP10:%.*]] = icmp sgt i32 [[TMP8]], [[TMP9]]
+; AVX-NEXT: [[TMP11:%.*]] = select i1 [[TMP10]], i32 [[TMP8]], i32 [[TMP9]]
+; AVX-NEXT: [[TMP12:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 4), align 16
+; AVX-NEXT: [[TMP13:%.*]] = icmp sgt i32 [[TMP11]], [[TMP12]]
+; AVX-NEXT: [[TMP14:%.*]] = select i1 [[TMP13]], i32 [[TMP11]], i32 [[TMP12]]
+; AVX-NEXT: [[TMP15:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 5), align 4
+; AVX-NEXT: [[TMP16:%.*]] = icmp sgt i32 [[TMP14]], [[TMP15]]
+; AVX-NEXT: [[TMP17:%.*]] = select i1 [[TMP16]], i32 [[TMP14]], i32 [[TMP15]]
+; AVX-NEXT: [[TMP18:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 6), align 8
+; AVX-NEXT: [[TMP19:%.*]] = icmp sgt i32 [[TMP17]], [[TMP18]]
+; AVX-NEXT: [[TMP20:%.*]] = select i1 [[TMP19]], i32 [[TMP17]], i32 [[TMP18]]
+; AVX-NEXT: [[TMP21:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 7), align 4
+; AVX-NEXT: [[TMP22:%.*]] = icmp sgt i32 [[TMP20]], [[TMP21]]
+; AVX-NEXT: [[TMP23:%.*]] = select i1 [[TMP22]], i32 [[TMP20]], i32 [[TMP21]]
+; AVX-NEXT: ret i32 [[TMP23]]
+;
+; AVX2-LABEL: @maxi8(
+; AVX2-NEXT: [[TMP2:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 0), align 16
+; AVX2-NEXT: [[TMP3:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 1), align 4
+; AVX2-NEXT: [[TMP4:%.*]] = icmp sgt i32 [[TMP2]], [[TMP3]]
+; AVX2-NEXT: [[TMP5:%.*]] = select i1 [[TMP4]], i32 [[TMP2]], i32 [[TMP3]]
+; AVX2-NEXT: [[TMP6:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 2), align 8
+; AVX2-NEXT: [[TMP7:%.*]] = icmp sgt i32 [[TMP5]], [[TMP6]]
+; AVX2-NEXT: [[TMP8:%.*]] = select i1 [[TMP7]], i32 [[TMP5]], i32 [[TMP6]]
+; AVX2-NEXT: [[TMP9:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 3), align 4
+; AVX2-NEXT: [[TMP10:%.*]] = icmp sgt i32 [[TMP8]], [[TMP9]]
+; AVX2-NEXT: [[TMP11:%.*]] = select i1 [[TMP10]], i32 [[TMP8]], i32 [[TMP9]]
+; AVX2-NEXT: [[TMP12:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 4), align 16
+; AVX2-NEXT: [[TMP13:%.*]] = icmp sgt i32 [[TMP11]], [[TMP12]]
+; AVX2-NEXT: [[TMP14:%.*]] = select i1 [[TMP13]], i32 [[TMP11]], i32 [[TMP12]]
+; AVX2-NEXT: [[TMP15:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 5), align 4
+; AVX2-NEXT: [[TMP16:%.*]] = icmp sgt i32 [[TMP14]], [[TMP15]]
+; AVX2-NEXT: [[TMP17:%.*]] = select i1 [[TMP16]], i32 [[TMP14]], i32 [[TMP15]]
+; AVX2-NEXT: [[TMP18:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 6), align 8
+; AVX2-NEXT: [[TMP19:%.*]] = icmp sgt i32 [[TMP17]], [[TMP18]]
+; AVX2-NEXT: [[TMP20:%.*]] = select i1 [[TMP19]], i32 [[TMP17]], i32 [[TMP18]]
+; AVX2-NEXT: [[TMP21:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 7), align 4
+; AVX2-NEXT: [[TMP22:%.*]] = icmp sgt i32 [[TMP20]], [[TMP21]]
+; AVX2-NEXT: [[TMP23:%.*]] = select i1 [[TMP22]], i32 [[TMP20]], i32 [[TMP21]]
+; AVX2-NEXT: ret i32 [[TMP23]]
+;
+; SKX-LABEL: @maxi8(
+; SKX-NEXT: [[TMP2:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 0), align 16
+; SKX-NEXT: [[TMP3:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 1), align 4
+; SKX-NEXT: [[TMP4:%.*]] = icmp sgt i32 [[TMP2]], [[TMP3]]
+; SKX-NEXT: [[TMP5:%.*]] = select i1 [[TMP4]], i32 [[TMP2]], i32 [[TMP3]]
+; SKX-NEXT: [[TMP6:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 2), align 8
+; SKX-NEXT: [[TMP7:%.*]] = icmp sgt i32 [[TMP5]], [[TMP6]]
+; SKX-NEXT: [[TMP8:%.*]] = select i1 [[TMP7]], i32 [[TMP5]], i32 [[TMP6]]
+; SKX-NEXT: [[TMP9:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 3), align 4
+; SKX-NEXT: [[TMP10:%.*]] = icmp sgt i32 [[TMP8]], [[TMP9]]
+; SKX-NEXT: [[TMP11:%.*]] = select i1 [[TMP10]], i32 [[TMP8]], i32 [[TMP9]]
+; SKX-NEXT: [[TMP12:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 4), align 16
+; SKX-NEXT: [[TMP13:%.*]] = icmp sgt i32 [[TMP11]], [[TMP12]]
+; SKX-NEXT: [[TMP14:%.*]] = select i1 [[TMP13]], i32 [[TMP11]], i32 [[TMP12]]
+; SKX-NEXT: [[TMP15:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 5), align 4
+; SKX-NEXT: [[TMP16:%.*]] = icmp sgt i32 [[TMP14]], [[TMP15]]
+; SKX-NEXT: [[TMP17:%.*]] = select i1 [[TMP16]], i32 [[TMP14]], i32 [[TMP15]]
+; SKX-NEXT: [[TMP18:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 6), align 8
+; SKX-NEXT: [[TMP19:%.*]] = icmp sgt i32 [[TMP17]], [[TMP18]]
+; SKX-NEXT: [[TMP20:%.*]] = select i1 [[TMP19]], i32 [[TMP17]], i32 [[TMP18]]
+; SKX-NEXT: [[TMP21:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 7), align 4
+; SKX-NEXT: [[TMP22:%.*]] = icmp sgt i32 [[TMP20]], [[TMP21]]
+; SKX-NEXT: [[TMP23:%.*]] = select i1 [[TMP22]], i32 [[TMP20]], i32 [[TMP21]]
+; SKX-NEXT: ret i32 [[TMP23]]
+;
+ %2 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 0), align 16
+ %3 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 1), align 4
+ %4 = icmp sgt i32 %2, %3
+ %5 = select i1 %4, i32 %2, i32 %3
+ %6 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 2), align 8
+ %7 = icmp sgt i32 %5, %6
+ %8 = select i1 %7, i32 %5, i32 %6
+ %9 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 3), align 4
+ %10 = icmp sgt i32 %8, %9
+ %11 = select i1 %10, i32 %8, i32 %9
+ %12 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 4), align 16
+ %13 = icmp sgt i32 %11, %12
+ %14 = select i1 %13, i32 %11, i32 %12
+ %15 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 5), align 4
+ %16 = icmp sgt i32 %14, %15
+ %17 = select i1 %16, i32 %14, i32 %15
+ %18 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 6), align 8
+ %19 = icmp sgt i32 %17, %18
+ %20 = select i1 %19, i32 %17, i32 %18
+ %21 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 7), align 4
+ %22 = icmp sgt i32 %20, %21
+ %23 = select i1 %22, i32 %20, i32 %21
+ ret i32 %23
+}
+
+define i32 @maxi16(i32) {
+; CHECK-LABEL: @maxi16(
+; CHECK-NEXT: [[TMP2:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 0), align 16
+; CHECK-NEXT: [[TMP3:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 1), align 4
+; CHECK-NEXT: [[TMP4:%.*]] = icmp sgt i32 [[TMP2]], [[TMP3]]
+; CHECK-NEXT: [[TMP5:%.*]] = select i1 [[TMP4]], i32 [[TMP2]], i32 [[TMP3]]
+; CHECK-NEXT: [[TMP6:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 2), align 8
+; CHECK-NEXT: [[TMP7:%.*]] = icmp sgt i32 [[TMP5]], [[TMP6]]
+; CHECK-NEXT: [[TMP8:%.*]] = select i1 [[TMP7]], i32 [[TMP5]], i32 [[TMP6]]
+; CHECK-NEXT: [[TMP9:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 3), align 4
+; CHECK-NEXT: [[TMP10:%.*]] = icmp sgt i32 [[TMP8]], [[TMP9]]
+; CHECK-NEXT: [[TMP11:%.*]] = select i1 [[TMP10]], i32 [[TMP8]], i32 [[TMP9]]
+; CHECK-NEXT: [[TMP12:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 4), align 16
+; CHECK-NEXT: [[TMP13:%.*]] = icmp sgt i32 [[TMP11]], [[TMP12]]
+; CHECK-NEXT: [[TMP14:%.*]] = select i1 [[TMP13]], i32 [[TMP11]], i32 [[TMP12]]
+; CHECK-NEXT: [[TMP15:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 5), align 4
+; CHECK-NEXT: [[TMP16:%.*]] = icmp sgt i32 [[TMP14]], [[TMP15]]
+; CHECK-NEXT: [[TMP17:%.*]] = select i1 [[TMP16]], i32 [[TMP14]], i32 [[TMP15]]
+; CHECK-NEXT: [[TMP18:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 6), align 8
+; CHECK-NEXT: [[TMP19:%.*]] = icmp sgt i32 [[TMP17]], [[TMP18]]
+; CHECK-NEXT: [[TMP20:%.*]] = select i1 [[TMP19]], i32 [[TMP17]], i32 [[TMP18]]
+; CHECK-NEXT: [[TMP21:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 7), align 4
+; CHECK-NEXT: [[TMP22:%.*]] = icmp sgt i32 [[TMP20]], [[TMP21]]
+; CHECK-NEXT: [[TMP23:%.*]] = select i1 [[TMP22]], i32 [[TMP20]], i32 [[TMP21]]
+; CHECK-NEXT: [[TMP24:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 8), align 16
+; CHECK-NEXT: [[TMP25:%.*]] = icmp sgt i32 [[TMP23]], [[TMP24]]
+; CHECK-NEXT: [[TMP26:%.*]] = select i1 [[TMP25]], i32 [[TMP23]], i32 [[TMP24]]
+; CHECK-NEXT: [[TMP27:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 9), align 4
+; CHECK-NEXT: [[TMP28:%.*]] = icmp sgt i32 [[TMP26]], [[TMP27]]
+; CHECK-NEXT: [[TMP29:%.*]] = select i1 [[TMP28]], i32 [[TMP26]], i32 [[TMP27]]
+; CHECK-NEXT: [[TMP30:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 10), align 8
+; CHECK-NEXT: [[TMP31:%.*]] = icmp sgt i32 [[TMP29]], [[TMP30]]
+; CHECK-NEXT: [[TMP32:%.*]] = select i1 [[TMP31]], i32 [[TMP29]], i32 [[TMP30]]
+; CHECK-NEXT: [[TMP33:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 11), align 4
+; CHECK-NEXT: [[TMP34:%.*]] = icmp sgt i32 [[TMP32]], [[TMP33]]
+; CHECK-NEXT: [[TMP35:%.*]] = select i1 [[TMP34]], i32 [[TMP32]], i32 [[TMP33]]
+; CHECK-NEXT: [[TMP36:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 12), align 16
+; CHECK-NEXT: [[TMP37:%.*]] = icmp sgt i32 [[TMP35]], [[TMP36]]
+; CHECK-NEXT: [[TMP38:%.*]] = select i1 [[TMP37]], i32 [[TMP35]], i32 [[TMP36]]
+; CHECK-NEXT: [[TMP39:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 13), align 4
+; CHECK-NEXT: [[TMP40:%.*]] = icmp sgt i32 [[TMP38]], [[TMP39]]
+; CHECK-NEXT: [[TMP41:%.*]] = select i1 [[TMP40]], i32 [[TMP38]], i32 [[TMP39]]
+; CHECK-NEXT: [[TMP42:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 14), align 8
+; CHECK-NEXT: [[TMP43:%.*]] = icmp sgt i32 [[TMP41]], [[TMP42]]
+; CHECK-NEXT: [[TMP44:%.*]] = select i1 [[TMP43]], i32 [[TMP41]], i32 [[TMP42]]
+; CHECK-NEXT: [[TMP45:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 15), align 4
+; CHECK-NEXT: [[TMP46:%.*]] = icmp sgt i32 [[TMP44]], [[TMP45]]
+; CHECK-NEXT: [[TMP47:%.*]] = select i1 [[TMP46]], i32 [[TMP44]], i32 [[TMP45]]
+; CHECK-NEXT: ret i32 [[TMP47]]
+;
+; AVX-LABEL: @maxi16(
+; AVX-NEXT: [[TMP2:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 0), align 16
+; AVX-NEXT: [[TMP3:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 1), align 4
+; AVX-NEXT: [[TMP4:%.*]] = icmp sgt i32 [[TMP2]], [[TMP3]]
+; AVX-NEXT: [[TMP5:%.*]] = select i1 [[TMP4]], i32 [[TMP2]], i32 [[TMP3]]
+; AVX-NEXT: [[TMP6:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 2), align 8
+; AVX-NEXT: [[TMP7:%.*]] = icmp sgt i32 [[TMP5]], [[TMP6]]
+; AVX-NEXT: [[TMP8:%.*]] = select i1 [[TMP7]], i32 [[TMP5]], i32 [[TMP6]]
+; AVX-NEXT: [[TMP9:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 3), align 4
+; AVX-NEXT: [[TMP10:%.*]] = icmp sgt i32 [[TMP8]], [[TMP9]]
+; AVX-NEXT: [[TMP11:%.*]] = select i1 [[TMP10]], i32 [[TMP8]], i32 [[TMP9]]
+; AVX-NEXT: [[TMP12:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 4), align 16
+; AVX-NEXT: [[TMP13:%.*]] = icmp sgt i32 [[TMP11]], [[TMP12]]
+; AVX-NEXT: [[TMP14:%.*]] = select i1 [[TMP13]], i32 [[TMP11]], i32 [[TMP12]]
+; AVX-NEXT: [[TMP15:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 5), align 4
+; AVX-NEXT: [[TMP16:%.*]] = icmp sgt i32 [[TMP14]], [[TMP15]]
+; AVX-NEXT: [[TMP17:%.*]] = select i1 [[TMP16]], i32 [[TMP14]], i32 [[TMP15]]
+; AVX-NEXT: [[TMP18:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 6), align 8
+; AVX-NEXT: [[TMP19:%.*]] = icmp sgt i32 [[TMP17]], [[TMP18]]
+; AVX-NEXT: [[TMP20:%.*]] = select i1 [[TMP19]], i32 [[TMP17]], i32 [[TMP18]]
+; AVX-NEXT: [[TMP21:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 7), align 4
+; AVX-NEXT: [[TMP22:%.*]] = icmp sgt i32 [[TMP20]], [[TMP21]]
+; AVX-NEXT: [[TMP23:%.*]] = select i1 [[TMP22]], i32 [[TMP20]], i32 [[TMP21]]
+; AVX-NEXT: [[TMP24:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 8), align 16
+; AVX-NEXT: [[TMP25:%.*]] = icmp sgt i32 [[TMP23]], [[TMP24]]
+; AVX-NEXT: [[TMP26:%.*]] = select i1 [[TMP25]], i32 [[TMP23]], i32 [[TMP24]]
+; AVX-NEXT: [[TMP27:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 9), align 4
+; AVX-NEXT: [[TMP28:%.*]] = icmp sgt i32 [[TMP26]], [[TMP27]]
+; AVX-NEXT: [[TMP29:%.*]] = select i1 [[TMP28]], i32 [[TMP26]], i32 [[TMP27]]
+; AVX-NEXT: [[TMP30:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 10), align 8
+; AVX-NEXT: [[TMP31:%.*]] = icmp sgt i32 [[TMP29]], [[TMP30]]
+; AVX-NEXT: [[TMP32:%.*]] = select i1 [[TMP31]], i32 [[TMP29]], i32 [[TMP30]]
+; AVX-NEXT: [[TMP33:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 11), align 4
+; AVX-NEXT: [[TMP34:%.*]] = icmp sgt i32 [[TMP32]], [[TMP33]]
+; AVX-NEXT: [[TMP35:%.*]] = select i1 [[TMP34]], i32 [[TMP32]], i32 [[TMP33]]
+; AVX-NEXT: [[TMP36:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 12), align 16
+; AVX-NEXT: [[TMP37:%.*]] = icmp sgt i32 [[TMP35]], [[TMP36]]
+; AVX-NEXT: [[TMP38:%.*]] = select i1 [[TMP37]], i32 [[TMP35]], i32 [[TMP36]]
+; AVX-NEXT: [[TMP39:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 13), align 4
+; AVX-NEXT: [[TMP40:%.*]] = icmp sgt i32 [[TMP38]], [[TMP39]]
+; AVX-NEXT: [[TMP41:%.*]] = select i1 [[TMP40]], i32 [[TMP38]], i32 [[TMP39]]
+; AVX-NEXT: [[TMP42:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 14), align 8
+; AVX-NEXT: [[TMP43:%.*]] = icmp sgt i32 [[TMP41]], [[TMP42]]
+; AVX-NEXT: [[TMP44:%.*]] = select i1 [[TMP43]], i32 [[TMP41]], i32 [[TMP42]]
+; AVX-NEXT: [[TMP45:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 15), align 4
+; AVX-NEXT: [[TMP46:%.*]] = icmp sgt i32 [[TMP44]], [[TMP45]]
+; AVX-NEXT: [[TMP47:%.*]] = select i1 [[TMP46]], i32 [[TMP44]], i32 [[TMP45]]
+; AVX-NEXT: ret i32 [[TMP47]]
+;
+; AVX2-LABEL: @maxi16(
+; AVX2-NEXT: [[TMP2:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 0), align 16
+; AVX2-NEXT: [[TMP3:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 1), align 4
+; AVX2-NEXT: [[TMP4:%.*]] = icmp sgt i32 [[TMP2]], [[TMP3]]
+; AVX2-NEXT: [[TMP5:%.*]] = select i1 [[TMP4]], i32 [[TMP2]], i32 [[TMP3]]
+; AVX2-NEXT: [[TMP6:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 2), align 8
+; AVX2-NEXT: [[TMP7:%.*]] = icmp sgt i32 [[TMP5]], [[TMP6]]
+; AVX2-NEXT: [[TMP8:%.*]] = select i1 [[TMP7]], i32 [[TMP5]], i32 [[TMP6]]
+; AVX2-NEXT: [[TMP9:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 3), align 4
+; AVX2-NEXT: [[TMP10:%.*]] = icmp sgt i32 [[TMP8]], [[TMP9]]
+; AVX2-NEXT: [[TMP11:%.*]] = select i1 [[TMP10]], i32 [[TMP8]], i32 [[TMP9]]
+; AVX2-NEXT: [[TMP12:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 4), align 16
+; AVX2-NEXT: [[TMP13:%.*]] = icmp sgt i32 [[TMP11]], [[TMP12]]
+; AVX2-NEXT: [[TMP14:%.*]] = select i1 [[TMP13]], i32 [[TMP11]], i32 [[TMP12]]
+; AVX2-NEXT: [[TMP15:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 5), align 4
+; AVX2-NEXT: [[TMP16:%.*]] = icmp sgt i32 [[TMP14]], [[TMP15]]
+; AVX2-NEXT: [[TMP17:%.*]] = select i1 [[TMP16]], i32 [[TMP14]], i32 [[TMP15]]
+; AVX2-NEXT: [[TMP18:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 6), align 8
+; AVX2-NEXT: [[TMP19:%.*]] = icmp sgt i32 [[TMP17]], [[TMP18]]
+; AVX2-NEXT: [[TMP20:%.*]] = select i1 [[TMP19]], i32 [[TMP17]], i32 [[TMP18]]
+; AVX2-NEXT: [[TMP21:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 7), align 4
+; AVX2-NEXT: [[TMP22:%.*]] = icmp sgt i32 [[TMP20]], [[TMP21]]
+; AVX2-NEXT: [[TMP23:%.*]] = select i1 [[TMP22]], i32 [[TMP20]], i32 [[TMP21]]
+; AVX2-NEXT: [[TMP24:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 8), align 16
+; AVX2-NEXT: [[TMP25:%.*]] = icmp sgt i32 [[TMP23]], [[TMP24]]
+; AVX2-NEXT: [[TMP26:%.*]] = select i1 [[TMP25]], i32 [[TMP23]], i32 [[TMP24]]
+; AVX2-NEXT: [[TMP27:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 9), align 4
+; AVX2-NEXT: [[TMP28:%.*]] = icmp sgt i32 [[TMP26]], [[TMP27]]
+; AVX2-NEXT: [[TMP29:%.*]] = select i1 [[TMP28]], i32 [[TMP26]], i32 [[TMP27]]
+; AVX2-NEXT: [[TMP30:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 10), align 8
+; AVX2-NEXT: [[TMP31:%.*]] = icmp sgt i32 [[TMP29]], [[TMP30]]
+; AVX2-NEXT: [[TMP32:%.*]] = select i1 [[TMP31]], i32 [[TMP29]], i32 [[TMP30]]
+; AVX2-NEXT: [[TMP33:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 11), align 4
+; AVX2-NEXT: [[TMP34:%.*]] = icmp sgt i32 [[TMP32]], [[TMP33]]
+; AVX2-NEXT: [[TMP35:%.*]] = select i1 [[TMP34]], i32 [[TMP32]], i32 [[TMP33]]
+; AVX2-NEXT: [[TMP36:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 12), align 16
+; AVX2-NEXT: [[TMP37:%.*]] = icmp sgt i32 [[TMP35]], [[TMP36]]
+; AVX2-NEXT: [[TMP38:%.*]] = select i1 [[TMP37]], i32 [[TMP35]], i32 [[TMP36]]
+; AVX2-NEXT: [[TMP39:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 13), align 4
+; AVX2-NEXT: [[TMP40:%.*]] = icmp sgt i32 [[TMP38]], [[TMP39]]
+; AVX2-NEXT: [[TMP41:%.*]] = select i1 [[TMP40]], i32 [[TMP38]], i32 [[TMP39]]
+; AVX2-NEXT: [[TMP42:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 14), align 8
+; AVX2-NEXT: [[TMP43:%.*]] = icmp sgt i32 [[TMP41]], [[TMP42]]
+; AVX2-NEXT: [[TMP44:%.*]] = select i1 [[TMP43]], i32 [[TMP41]], i32 [[TMP42]]
+; AVX2-NEXT: [[TMP45:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 15), align 4
+; AVX2-NEXT: [[TMP46:%.*]] = icmp sgt i32 [[TMP44]], [[TMP45]]
+; AVX2-NEXT: [[TMP47:%.*]] = select i1 [[TMP46]], i32 [[TMP44]], i32 [[TMP45]]
+; AVX2-NEXT: ret i32 [[TMP47]]
+;
+; SKX-LABEL: @maxi16(
+; SKX-NEXT: [[TMP2:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 0), align 16
+; SKX-NEXT: [[TMP3:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 1), align 4
+; SKX-NEXT: [[TMP4:%.*]] = icmp sgt i32 [[TMP2]], [[TMP3]]
+; SKX-NEXT: [[TMP5:%.*]] = select i1 [[TMP4]], i32 [[TMP2]], i32 [[TMP3]]
+; SKX-NEXT: [[TMP6:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 2), align 8
+; SKX-NEXT: [[TMP7:%.*]] = icmp sgt i32 [[TMP5]], [[TMP6]]
+; SKX-NEXT: [[TMP8:%.*]] = select i1 [[TMP7]], i32 [[TMP5]], i32 [[TMP6]]
+; SKX-NEXT: [[TMP9:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 3), align 4
+; SKX-NEXT: [[TMP10:%.*]] = icmp sgt i32 [[TMP8]], [[TMP9]]
+; SKX-NEXT: [[TMP11:%.*]] = select i1 [[TMP10]], i32 [[TMP8]], i32 [[TMP9]]
+; SKX-NEXT: [[TMP12:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 4), align 16
+; SKX-NEXT: [[TMP13:%.*]] = icmp sgt i32 [[TMP11]], [[TMP12]]
+; SKX-NEXT: [[TMP14:%.*]] = select i1 [[TMP13]], i32 [[TMP11]], i32 [[TMP12]]
+; SKX-NEXT: [[TMP15:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 5), align 4
+; SKX-NEXT: [[TMP16:%.*]] = icmp sgt i32 [[TMP14]], [[TMP15]]
+; SKX-NEXT: [[TMP17:%.*]] = select i1 [[TMP16]], i32 [[TMP14]], i32 [[TMP15]]
+; SKX-NEXT: [[TMP18:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 6), align 8
+; SKX-NEXT: [[TMP19:%.*]] = icmp sgt i32 [[TMP17]], [[TMP18]]
+; SKX-NEXT: [[TMP20:%.*]] = select i1 [[TMP19]], i32 [[TMP17]], i32 [[TMP18]]
+; SKX-NEXT: [[TMP21:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 7), align 4
+; SKX-NEXT: [[TMP22:%.*]] = icmp sgt i32 [[TMP20]], [[TMP21]]
+; SKX-NEXT: [[TMP23:%.*]] = select i1 [[TMP22]], i32 [[TMP20]], i32 [[TMP21]]
+; SKX-NEXT: [[TMP24:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 8), align 16
+; SKX-NEXT: [[TMP25:%.*]] = icmp sgt i32 [[TMP23]], [[TMP24]]
+; SKX-NEXT: [[TMP26:%.*]] = select i1 [[TMP25]], i32 [[TMP23]], i32 [[TMP24]]
+; SKX-NEXT: [[TMP27:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 9), align 4
+; SKX-NEXT: [[TMP28:%.*]] = icmp sgt i32 [[TMP26]], [[TMP27]]
+; SKX-NEXT: [[TMP29:%.*]] = select i1 [[TMP28]], i32 [[TMP26]], i32 [[TMP27]]
+; SKX-NEXT: [[TMP30:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 10), align 8
+; SKX-NEXT: [[TMP31:%.*]] = icmp sgt i32 [[TMP29]], [[TMP30]]
+; SKX-NEXT: [[TMP32:%.*]] = select i1 [[TMP31]], i32 [[TMP29]], i32 [[TMP30]]
+; SKX-NEXT: [[TMP33:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 11), align 4
+; SKX-NEXT: [[TMP34:%.*]] = icmp sgt i32 [[TMP32]], [[TMP33]]
+; SKX-NEXT: [[TMP35:%.*]] = select i1 [[TMP34]], i32 [[TMP32]], i32 [[TMP33]]
+; SKX-NEXT: [[TMP36:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 12), align 16
+; SKX-NEXT: [[TMP37:%.*]] = icmp sgt i32 [[TMP35]], [[TMP36]]
+; SKX-NEXT: [[TMP38:%.*]] = select i1 [[TMP37]], i32 [[TMP35]], i32 [[TMP36]]
+; SKX-NEXT: [[TMP39:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 13), align 4
+; SKX-NEXT: [[TMP40:%.*]] = icmp sgt i32 [[TMP38]], [[TMP39]]
+; SKX-NEXT: [[TMP41:%.*]] = select i1 [[TMP40]], i32 [[TMP38]], i32 [[TMP39]]
+; SKX-NEXT: [[TMP42:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 14), align 8
+; SKX-NEXT: [[TMP43:%.*]] = icmp sgt i32 [[TMP41]], [[TMP42]]
+; SKX-NEXT: [[TMP44:%.*]] = select i1 [[TMP43]], i32 [[TMP41]], i32 [[TMP42]]
+; SKX-NEXT: [[TMP45:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 15), align 4
+; SKX-NEXT: [[TMP46:%.*]] = icmp sgt i32 [[TMP44]], [[TMP45]]
+; SKX-NEXT: [[TMP47:%.*]] = select i1 [[TMP46]], i32 [[TMP44]], i32 [[TMP45]]
+; SKX-NEXT: ret i32 [[TMP47]]
+;
+ %2 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 0), align 16
+ %3 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 1), align 4
+ %4 = icmp sgt i32 %2, %3
+ %5 = select i1 %4, i32 %2, i32 %3
+ %6 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 2), align 8
+ %7 = icmp sgt i32 %5, %6
+ %8 = select i1 %7, i32 %5, i32 %6
+ %9 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 3), align 4
+ %10 = icmp sgt i32 %8, %9
+ %11 = select i1 %10, i32 %8, i32 %9
+ %12 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 4), align 16
+ %13 = icmp sgt i32 %11, %12
+ %14 = select i1 %13, i32 %11, i32 %12
+ %15 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 5), align 4
+ %16 = icmp sgt i32 %14, %15
+ %17 = select i1 %16, i32 %14, i32 %15
+ %18 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 6), align 8
+ %19 = icmp sgt i32 %17, %18
+ %20 = select i1 %19, i32 %17, i32 %18
+ %21 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 7), align 4
+ %22 = icmp sgt i32 %20, %21
+ %23 = select i1 %22, i32 %20, i32 %21
+ %24 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 8), align 16
+ %25 = icmp sgt i32 %23, %24
+ %26 = select i1 %25, i32 %23, i32 %24
+ %27 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 9), align 4
+ %28 = icmp sgt i32 %26, %27
+ %29 = select i1 %28, i32 %26, i32 %27
+ %30 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 10), align 8
+ %31 = icmp sgt i32 %29, %30
+ %32 = select i1 %31, i32 %29, i32 %30
+ %33 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 11), align 4
+ %34 = icmp sgt i32 %32, %33
+ %35 = select i1 %34, i32 %32, i32 %33
+ %36 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 12), align 16
+ %37 = icmp sgt i32 %35, %36
+ %38 = select i1 %37, i32 %35, i32 %36
+ %39 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 13), align 4
+ %40 = icmp sgt i32 %38, %39
+ %41 = select i1 %40, i32 %38, i32 %39
+ %42 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 14), align 8
+ %43 = icmp sgt i32 %41, %42
+ %44 = select i1 %43, i32 %41, i32 %42
+ %45 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 15), align 4
+ %46 = icmp sgt i32 %44, %45
+ %47 = select i1 %46, i32 %44, i32 %45
+ ret i32 %47
+}
+
+define i32 @maxi32(i32) {
+; CHECK-LABEL: @maxi32(
+; CHECK-NEXT: [[TMP2:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 0), align 16
+; CHECK-NEXT: [[TMP3:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 1), align 4
+; CHECK-NEXT: [[TMP4:%.*]] = icmp sgt i32 [[TMP2]], [[TMP3]]
+; CHECK-NEXT: [[TMP5:%.*]] = select i1 [[TMP4]], i32 [[TMP2]], i32 [[TMP3]]
+; CHECK-NEXT: [[TMP6:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 2), align 8
+; CHECK-NEXT: [[TMP7:%.*]] = icmp sgt i32 [[TMP5]], [[TMP6]]
+; CHECK-NEXT: [[TMP8:%.*]] = select i1 [[TMP7]], i32 [[TMP5]], i32 [[TMP6]]
+; CHECK-NEXT: [[TMP9:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 3), align 4
+; CHECK-NEXT: [[TMP10:%.*]] = icmp sgt i32 [[TMP8]], [[TMP9]]
+; CHECK-NEXT: [[TMP11:%.*]] = select i1 [[TMP10]], i32 [[TMP8]], i32 [[TMP9]]
+; CHECK-NEXT: [[TMP12:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 4), align 16
+; CHECK-NEXT: [[TMP13:%.*]] = icmp sgt i32 [[TMP11]], [[TMP12]]
+; CHECK-NEXT: [[TMP14:%.*]] = select i1 [[TMP13]], i32 [[TMP11]], i32 [[TMP12]]
+; CHECK-NEXT: [[TMP15:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 5), align 4
+; CHECK-NEXT: [[TMP16:%.*]] = icmp sgt i32 [[TMP14]], [[TMP15]]
+; CHECK-NEXT: [[TMP17:%.*]] = select i1 [[TMP16]], i32 [[TMP14]], i32 [[TMP15]]
+; CHECK-NEXT: [[TMP18:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 6), align 8
+; CHECK-NEXT: [[TMP19:%.*]] = icmp sgt i32 [[TMP17]], [[TMP18]]
+; CHECK-NEXT: [[TMP20:%.*]] = select i1 [[TMP19]], i32 [[TMP17]], i32 [[TMP18]]
+; CHECK-NEXT: [[TMP21:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 7), align 4
+; CHECK-NEXT: [[TMP22:%.*]] = icmp sgt i32 [[TMP20]], [[TMP21]]
+; CHECK-NEXT: [[TMP23:%.*]] = select i1 [[TMP22]], i32 [[TMP20]], i32 [[TMP21]]
+; CHECK-NEXT: [[TMP24:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 8), align 16
+; CHECK-NEXT: [[TMP25:%.*]] = icmp sgt i32 [[TMP23]], [[TMP24]]
+; CHECK-NEXT: [[TMP26:%.*]] = select i1 [[TMP25]], i32 [[TMP23]], i32 [[TMP24]]
+; CHECK-NEXT: [[TMP27:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 9), align 4
+; CHECK-NEXT: [[TMP28:%.*]] = icmp sgt i32 [[TMP26]], [[TMP27]]
+; CHECK-NEXT: [[TMP29:%.*]] = select i1 [[TMP28]], i32 [[TMP26]], i32 [[TMP27]]
+; CHECK-NEXT: [[TMP30:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 10), align 8
+; CHECK-NEXT: [[TMP31:%.*]] = icmp sgt i32 [[TMP29]], [[TMP30]]
+; CHECK-NEXT: [[TMP32:%.*]] = select i1 [[TMP31]], i32 [[TMP29]], i32 [[TMP30]]
+; CHECK-NEXT: [[TMP33:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 11), align 4
+; CHECK-NEXT: [[TMP34:%.*]] = icmp sgt i32 [[TMP32]], [[TMP33]]
+; CHECK-NEXT: [[TMP35:%.*]] = select i1 [[TMP34]], i32 [[TMP32]], i32 [[TMP33]]
+; CHECK-NEXT: [[TMP36:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 12), align 16
+; CHECK-NEXT: [[TMP37:%.*]] = icmp sgt i32 [[TMP35]], [[TMP36]]
+; CHECK-NEXT: [[TMP38:%.*]] = select i1 [[TMP37]], i32 [[TMP35]], i32 [[TMP36]]
+; CHECK-NEXT: [[TMP39:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 13), align 4
+; CHECK-NEXT: [[TMP40:%.*]] = icmp sgt i32 [[TMP38]], [[TMP39]]
+; CHECK-NEXT: [[TMP41:%.*]] = select i1 [[TMP40]], i32 [[TMP38]], i32 [[TMP39]]
+; CHECK-NEXT: [[TMP42:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 14), align 8
+; CHECK-NEXT: [[TMP43:%.*]] = icmp sgt i32 [[TMP41]], [[TMP42]]
+; CHECK-NEXT: [[TMP44:%.*]] = select i1 [[TMP43]], i32 [[TMP41]], i32 [[TMP42]]
+; CHECK-NEXT: [[TMP45:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 15), align 4
+; CHECK-NEXT: [[TMP46:%.*]] = icmp sgt i32 [[TMP44]], [[TMP45]]
+; CHECK-NEXT: [[TMP47:%.*]] = select i1 [[TMP46]], i32 [[TMP44]], i32 [[TMP45]]
+; CHECK-NEXT: [[TMP48:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 16), align 16
+; CHECK-NEXT: [[TMP49:%.*]] = icmp sgt i32 [[TMP47]], [[TMP48]]
+; CHECK-NEXT: [[TMP50:%.*]] = select i1 [[TMP49]], i32 [[TMP47]], i32 [[TMP48]]
+; CHECK-NEXT: [[TMP51:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 17), align 4
+; CHECK-NEXT: [[TMP52:%.*]] = icmp sgt i32 [[TMP50]], [[TMP51]]
+; CHECK-NEXT: [[TMP53:%.*]] = select i1 [[TMP52]], i32 [[TMP50]], i32 [[TMP51]]
+; CHECK-NEXT: [[TMP54:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 18), align 8
+; CHECK-NEXT: [[TMP55:%.*]] = icmp sgt i32 [[TMP53]], [[TMP54]]
+; CHECK-NEXT: [[TMP56:%.*]] = select i1 [[TMP55]], i32 [[TMP53]], i32 [[TMP54]]
+; CHECK-NEXT: [[TMP57:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 19), align 4
+; CHECK-NEXT: [[TMP58:%.*]] = icmp sgt i32 [[TMP56]], [[TMP57]]
+; CHECK-NEXT: [[TMP59:%.*]] = select i1 [[TMP58]], i32 [[TMP56]], i32 [[TMP57]]
+; CHECK-NEXT: [[TMP60:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 20), align 16
+; CHECK-NEXT: [[TMP61:%.*]] = icmp sgt i32 [[TMP59]], [[TMP60]]
+; CHECK-NEXT: [[TMP62:%.*]] = select i1 [[TMP61]], i32 [[TMP59]], i32 [[TMP60]]
+; CHECK-NEXT: [[TMP63:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 21), align 4
+; CHECK-NEXT: [[TMP64:%.*]] = icmp sgt i32 [[TMP62]], [[TMP63]]
+; CHECK-NEXT: [[TMP65:%.*]] = select i1 [[TMP64]], i32 [[TMP62]], i32 [[TMP63]]
+; CHECK-NEXT: [[TMP66:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 22), align 8
+; CHECK-NEXT: [[TMP67:%.*]] = icmp sgt i32 [[TMP65]], [[TMP66]]
+; CHECK-NEXT: [[TMP68:%.*]] = select i1 [[TMP67]], i32 [[TMP65]], i32 [[TMP66]]
+; CHECK-NEXT: [[TMP69:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 23), align 4
+; CHECK-NEXT: [[TMP70:%.*]] = icmp sgt i32 [[TMP68]], [[TMP69]]
+; CHECK-NEXT: [[TMP71:%.*]] = select i1 [[TMP70]], i32 [[TMP68]], i32 [[TMP69]]
+; CHECK-NEXT: [[TMP72:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 24), align 16
+; CHECK-NEXT: [[TMP73:%.*]] = icmp sgt i32 [[TMP71]], [[TMP72]]
+; CHECK-NEXT: [[TMP74:%.*]] = select i1 [[TMP73]], i32 [[TMP71]], i32 [[TMP72]]
+; CHECK-NEXT: [[TMP75:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 25), align 4
+; CHECK-NEXT: [[TMP76:%.*]] = icmp sgt i32 [[TMP74]], [[TMP75]]
+; CHECK-NEXT: [[TMP77:%.*]] = select i1 [[TMP76]], i32 [[TMP74]], i32 [[TMP75]]
+; CHECK-NEXT: [[TMP78:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 26), align 8
+; CHECK-NEXT: [[TMP79:%.*]] = icmp sgt i32 [[TMP77]], [[TMP78]]
+; CHECK-NEXT: [[TMP80:%.*]] = select i1 [[TMP79]], i32 [[TMP77]], i32 [[TMP78]]
+; CHECK-NEXT: [[TMP81:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 27), align 4
+; CHECK-NEXT: [[TMP82:%.*]] = icmp sgt i32 [[TMP80]], [[TMP81]]
+; CHECK-NEXT: [[TMP83:%.*]] = select i1 [[TMP82]], i32 [[TMP80]], i32 [[TMP81]]
+; CHECK-NEXT: [[TMP84:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 28), align 16
+; CHECK-NEXT: [[TMP85:%.*]] = icmp sgt i32 [[TMP83]], [[TMP84]]
+; CHECK-NEXT: [[TMP86:%.*]] = select i1 [[TMP85]], i32 [[TMP83]], i32 [[TMP84]]
+; CHECK-NEXT: [[TMP87:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 29), align 4
+; CHECK-NEXT: [[TMP88:%.*]] = icmp sgt i32 [[TMP86]], [[TMP87]]
+; CHECK-NEXT: [[TMP89:%.*]] = select i1 [[TMP88]], i32 [[TMP86]], i32 [[TMP87]]
+; CHECK-NEXT: [[TMP90:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 30), align 8
+; CHECK-NEXT: [[TMP91:%.*]] = icmp sgt i32 [[TMP89]], [[TMP90]]
+; CHECK-NEXT: [[TMP92:%.*]] = select i1 [[TMP91]], i32 [[TMP89]], i32 [[TMP90]]
+; CHECK-NEXT: [[TMP93:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 31), align 4
+; CHECK-NEXT: [[TMP94:%.*]] = icmp sgt i32 [[TMP92]], [[TMP93]]
+; CHECK-NEXT: [[TMP95:%.*]] = select i1 [[TMP94]], i32 [[TMP92]], i32 [[TMP93]]
+; CHECK-NEXT: ret i32 [[TMP95]]
+;
+; AVX-LABEL: @maxi32(
+; AVX-NEXT: [[TMP2:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 0), align 16
+; AVX-NEXT: [[TMP3:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 1), align 4
+; AVX-NEXT: [[TMP4:%.*]] = icmp sgt i32 [[TMP2]], [[TMP3]]
+; AVX-NEXT: [[TMP5:%.*]] = select i1 [[TMP4]], i32 [[TMP2]], i32 [[TMP3]]
+; AVX-NEXT: [[TMP6:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 2), align 8
+; AVX-NEXT: [[TMP7:%.*]] = icmp sgt i32 [[TMP5]], [[TMP6]]
+; AVX-NEXT: [[TMP8:%.*]] = select i1 [[TMP7]], i32 [[TMP5]], i32 [[TMP6]]
+; AVX-NEXT: [[TMP9:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 3), align 4
+; AVX-NEXT: [[TMP10:%.*]] = icmp sgt i32 [[TMP8]], [[TMP9]]
+; AVX-NEXT: [[TMP11:%.*]] = select i1 [[TMP10]], i32 [[TMP8]], i32 [[TMP9]]
+; AVX-NEXT: [[TMP12:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 4), align 16
+; AVX-NEXT: [[TMP13:%.*]] = icmp sgt i32 [[TMP11]], [[TMP12]]
+; AVX-NEXT: [[TMP14:%.*]] = select i1 [[TMP13]], i32 [[TMP11]], i32 [[TMP12]]
+; AVX-NEXT: [[TMP15:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 5), align 4
+; AVX-NEXT: [[TMP16:%.*]] = icmp sgt i32 [[TMP14]], [[TMP15]]
+; AVX-NEXT: [[TMP17:%.*]] = select i1 [[TMP16]], i32 [[TMP14]], i32 [[TMP15]]
+; AVX-NEXT: [[TMP18:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 6), align 8
+; AVX-NEXT: [[TMP19:%.*]] = icmp sgt i32 [[TMP17]], [[TMP18]]
+; AVX-NEXT: [[TMP20:%.*]] = select i1 [[TMP19]], i32 [[TMP17]], i32 [[TMP18]]
+; AVX-NEXT: [[TMP21:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 7), align 4
+; AVX-NEXT: [[TMP22:%.*]] = icmp sgt i32 [[TMP20]], [[TMP21]]
+; AVX-NEXT: [[TMP23:%.*]] = select i1 [[TMP22]], i32 [[TMP20]], i32 [[TMP21]]
+; AVX-NEXT: [[TMP24:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 8), align 16
+; AVX-NEXT: [[TMP25:%.*]] = icmp sgt i32 [[TMP23]], [[TMP24]]
+; AVX-NEXT: [[TMP26:%.*]] = select i1 [[TMP25]], i32 [[TMP23]], i32 [[TMP24]]
+; AVX-NEXT: [[TMP27:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 9), align 4
+; AVX-NEXT: [[TMP28:%.*]] = icmp sgt i32 [[TMP26]], [[TMP27]]
+; AVX-NEXT: [[TMP29:%.*]] = select i1 [[TMP28]], i32 [[TMP26]], i32 [[TMP27]]
+; AVX-NEXT: [[TMP30:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 10), align 8
+; AVX-NEXT: [[TMP31:%.*]] = icmp sgt i32 [[TMP29]], [[TMP30]]
+; AVX-NEXT: [[TMP32:%.*]] = select i1 [[TMP31]], i32 [[TMP29]], i32 [[TMP30]]
+; AVX-NEXT: [[TMP33:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 11), align 4
+; AVX-NEXT: [[TMP34:%.*]] = icmp sgt i32 [[TMP32]], [[TMP33]]
+; AVX-NEXT: [[TMP35:%.*]] = select i1 [[TMP34]], i32 [[TMP32]], i32 [[TMP33]]
+; AVX-NEXT: [[TMP36:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 12), align 16
+; AVX-NEXT: [[TMP37:%.*]] = icmp sgt i32 [[TMP35]], [[TMP36]]
+; AVX-NEXT: [[TMP38:%.*]] = select i1 [[TMP37]], i32 [[TMP35]], i32 [[TMP36]]
+; AVX-NEXT: [[TMP39:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 13), align 4
+; AVX-NEXT: [[TMP40:%.*]] = icmp sgt i32 [[TMP38]], [[TMP39]]
+; AVX-NEXT: [[TMP41:%.*]] = select i1 [[TMP40]], i32 [[TMP38]], i32 [[TMP39]]
+; AVX-NEXT: [[TMP42:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 14), align 8
+; AVX-NEXT: [[TMP43:%.*]] = icmp sgt i32 [[TMP41]], [[TMP42]]
+; AVX-NEXT: [[TMP44:%.*]] = select i1 [[TMP43]], i32 [[TMP41]], i32 [[TMP42]]
+; AVX-NEXT: [[TMP45:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 15), align 4
+; AVX-NEXT: [[TMP46:%.*]] = icmp sgt i32 [[TMP44]], [[TMP45]]
+; AVX-NEXT: [[TMP47:%.*]] = select i1 [[TMP46]], i32 [[TMP44]], i32 [[TMP45]]
+; AVX-NEXT: [[TMP48:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 16), align 16
+; AVX-NEXT: [[TMP49:%.*]] = icmp sgt i32 [[TMP47]], [[TMP48]]
+; AVX-NEXT: [[TMP50:%.*]] = select i1 [[TMP49]], i32 [[TMP47]], i32 [[TMP48]]
+; AVX-NEXT: [[TMP51:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 17), align 4
+; AVX-NEXT: [[TMP52:%.*]] = icmp sgt i32 [[TMP50]], [[TMP51]]
+; AVX-NEXT: [[TMP53:%.*]] = select i1 [[TMP52]], i32 [[TMP50]], i32 [[TMP51]]
+; AVX-NEXT: [[TMP54:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 18), align 8
+; AVX-NEXT: [[TMP55:%.*]] = icmp sgt i32 [[TMP53]], [[TMP54]]
+; AVX-NEXT: [[TMP56:%.*]] = select i1 [[TMP55]], i32 [[TMP53]], i32 [[TMP54]]
+; AVX-NEXT: [[TMP57:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 19), align 4
+; AVX-NEXT: [[TMP58:%.*]] = icmp sgt i32 [[TMP56]], [[TMP57]]
+; AVX-NEXT: [[TMP59:%.*]] = select i1 [[TMP58]], i32 [[TMP56]], i32 [[TMP57]]
+; AVX-NEXT: [[TMP60:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 20), align 16
+; AVX-NEXT: [[TMP61:%.*]] = icmp sgt i32 [[TMP59]], [[TMP60]]
+; AVX-NEXT: [[TMP62:%.*]] = select i1 [[TMP61]], i32 [[TMP59]], i32 [[TMP60]]
+; AVX-NEXT: [[TMP63:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 21), align 4
+; AVX-NEXT: [[TMP64:%.*]] = icmp sgt i32 [[TMP62]], [[TMP63]]
+; AVX-NEXT: [[TMP65:%.*]] = select i1 [[TMP64]], i32 [[TMP62]], i32 [[TMP63]]
+; AVX-NEXT: [[TMP66:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 22), align 8
+; AVX-NEXT: [[TMP67:%.*]] = icmp sgt i32 [[TMP65]], [[TMP66]]
+; AVX-NEXT: [[TMP68:%.*]] = select i1 [[TMP67]], i32 [[TMP65]], i32 [[TMP66]]
+; AVX-NEXT: [[TMP69:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 23), align 4
+; AVX-NEXT: [[TMP70:%.*]] = icmp sgt i32 [[TMP68]], [[TMP69]]
+; AVX-NEXT: [[TMP71:%.*]] = select i1 [[TMP70]], i32 [[TMP68]], i32 [[TMP69]]
+; AVX-NEXT: [[TMP72:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 24), align 16
+; AVX-NEXT: [[TMP73:%.*]] = icmp sgt i32 [[TMP71]], [[TMP72]]
+; AVX-NEXT: [[TMP74:%.*]] = select i1 [[TMP73]], i32 [[TMP71]], i32 [[TMP72]]
+; AVX-NEXT: [[TMP75:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 25), align 4
+; AVX-NEXT: [[TMP76:%.*]] = icmp sgt i32 [[TMP74]], [[TMP75]]
+; AVX-NEXT: [[TMP77:%.*]] = select i1 [[TMP76]], i32 [[TMP74]], i32 [[TMP75]]
+; AVX-NEXT: [[TMP78:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 26), align 8
+; AVX-NEXT: [[TMP79:%.*]] = icmp sgt i32 [[TMP77]], [[TMP78]]
+; AVX-NEXT: [[TMP80:%.*]] = select i1 [[TMP79]], i32 [[TMP77]], i32 [[TMP78]]
+; AVX-NEXT: [[TMP81:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 27), align 4
+; AVX-NEXT: [[TMP82:%.*]] = icmp sgt i32 [[TMP80]], [[TMP81]]
+; AVX-NEXT: [[TMP83:%.*]] = select i1 [[TMP82]], i32 [[TMP80]], i32 [[TMP81]]
+; AVX-NEXT: [[TMP84:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 28), align 16
+; AVX-NEXT: [[TMP85:%.*]] = icmp sgt i32 [[TMP83]], [[TMP84]]
+; AVX-NEXT: [[TMP86:%.*]] = select i1 [[TMP85]], i32 [[TMP83]], i32 [[TMP84]]
+; AVX-NEXT: [[TMP87:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 29), align 4
+; AVX-NEXT: [[TMP88:%.*]] = icmp sgt i32 [[TMP86]], [[TMP87]]
+; AVX-NEXT: [[TMP89:%.*]] = select i1 [[TMP88]], i32 [[TMP86]], i32 [[TMP87]]
+; AVX-NEXT: [[TMP90:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 30), align 8
+; AVX-NEXT: [[TMP91:%.*]] = icmp sgt i32 [[TMP89]], [[TMP90]]
+; AVX-NEXT: [[TMP92:%.*]] = select i1 [[TMP91]], i32 [[TMP89]], i32 [[TMP90]]
+; AVX-NEXT: [[TMP93:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 31), align 4
+; AVX-NEXT: [[TMP94:%.*]] = icmp sgt i32 [[TMP92]], [[TMP93]]
+; AVX-NEXT: [[TMP95:%.*]] = select i1 [[TMP94]], i32 [[TMP92]], i32 [[TMP93]]
+; AVX-NEXT: ret i32 [[TMP95]]
+;
+; AVX2-LABEL: @maxi32(
+; AVX2-NEXT: [[TMP2:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 0), align 16
+; AVX2-NEXT: [[TMP3:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 1), align 4
+; AVX2-NEXT: [[TMP4:%.*]] = icmp sgt i32 [[TMP2]], [[TMP3]]
+; AVX2-NEXT: [[TMP5:%.*]] = select i1 [[TMP4]], i32 [[TMP2]], i32 [[TMP3]]
+; AVX2-NEXT: [[TMP6:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 2), align 8
+; AVX2-NEXT: [[TMP7:%.*]] = icmp sgt i32 [[TMP5]], [[TMP6]]
+; AVX2-NEXT: [[TMP8:%.*]] = select i1 [[TMP7]], i32 [[TMP5]], i32 [[TMP6]]
+; AVX2-NEXT: [[TMP9:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 3), align 4
+; AVX2-NEXT: [[TMP10:%.*]] = icmp sgt i32 [[TMP8]], [[TMP9]]
+; AVX2-NEXT: [[TMP11:%.*]] = select i1 [[TMP10]], i32 [[TMP8]], i32 [[TMP9]]
+; AVX2-NEXT: [[TMP12:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 4), align 16
+; AVX2-NEXT: [[TMP13:%.*]] = icmp sgt i32 [[TMP11]], [[TMP12]]
+; AVX2-NEXT: [[TMP14:%.*]] = select i1 [[TMP13]], i32 [[TMP11]], i32 [[TMP12]]
+; AVX2-NEXT: [[TMP15:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 5), align 4
+; AVX2-NEXT: [[TMP16:%.*]] = icmp sgt i32 [[TMP14]], [[TMP15]]
+; AVX2-NEXT: [[TMP17:%.*]] = select i1 [[TMP16]], i32 [[TMP14]], i32 [[TMP15]]
+; AVX2-NEXT: [[TMP18:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 6), align 8
+; AVX2-NEXT: [[TMP19:%.*]] = icmp sgt i32 [[TMP17]], [[TMP18]]
+; AVX2-NEXT: [[TMP20:%.*]] = select i1 [[TMP19]], i32 [[TMP17]], i32 [[TMP18]]
+; AVX2-NEXT: [[TMP21:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 7), align 4
+; AVX2-NEXT: [[TMP22:%.*]] = icmp sgt i32 [[TMP20]], [[TMP21]]
+; AVX2-NEXT: [[TMP23:%.*]] = select i1 [[TMP22]], i32 [[TMP20]], i32 [[TMP21]]
+; AVX2-NEXT: [[TMP24:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 8), align 16
+; AVX2-NEXT: [[TMP25:%.*]] = icmp sgt i32 [[TMP23]], [[TMP24]]
+; AVX2-NEXT: [[TMP26:%.*]] = select i1 [[TMP25]], i32 [[TMP23]], i32 [[TMP24]]
+; AVX2-NEXT: [[TMP27:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 9), align 4
+; AVX2-NEXT: [[TMP28:%.*]] = icmp sgt i32 [[TMP26]], [[TMP27]]
+; AVX2-NEXT: [[TMP29:%.*]] = select i1 [[TMP28]], i32 [[TMP26]], i32 [[TMP27]]
+; AVX2-NEXT: [[TMP30:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 10), align 8
+; AVX2-NEXT: [[TMP31:%.*]] = icmp sgt i32 [[TMP29]], [[TMP30]]
+; AVX2-NEXT: [[TMP32:%.*]] = select i1 [[TMP31]], i32 [[TMP29]], i32 [[TMP30]]
+; AVX2-NEXT: [[TMP33:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 11), align 4
+; AVX2-NEXT: [[TMP34:%.*]] = icmp sgt i32 [[TMP32]], [[TMP33]]
+; AVX2-NEXT: [[TMP35:%.*]] = select i1 [[TMP34]], i32 [[TMP32]], i32 [[TMP33]]
+; AVX2-NEXT: [[TMP36:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 12), align 16
+; AVX2-NEXT: [[TMP37:%.*]] = icmp sgt i32 [[TMP35]], [[TMP36]]
+; AVX2-NEXT: [[TMP38:%.*]] = select i1 [[TMP37]], i32 [[TMP35]], i32 [[TMP36]]
+; AVX2-NEXT: [[TMP39:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 13), align 4
+; AVX2-NEXT: [[TMP40:%.*]] = icmp sgt i32 [[TMP38]], [[TMP39]]
+; AVX2-NEXT: [[TMP41:%.*]] = select i1 [[TMP40]], i32 [[TMP38]], i32 [[TMP39]]
+; AVX2-NEXT: [[TMP42:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 14), align 8
+; AVX2-NEXT: [[TMP43:%.*]] = icmp sgt i32 [[TMP41]], [[TMP42]]
+; AVX2-NEXT: [[TMP44:%.*]] = select i1 [[TMP43]], i32 [[TMP41]], i32 [[TMP42]]
+; AVX2-NEXT: [[TMP45:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 15), align 4
+; AVX2-NEXT: [[TMP46:%.*]] = icmp sgt i32 [[TMP44]], [[TMP45]]
+; AVX2-NEXT: [[TMP47:%.*]] = select i1 [[TMP46]], i32 [[TMP44]], i32 [[TMP45]]
+; AVX2-NEXT: [[TMP48:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 16), align 16
+; AVX2-NEXT: [[TMP49:%.*]] = icmp sgt i32 [[TMP47]], [[TMP48]]
+; AVX2-NEXT: [[TMP50:%.*]] = select i1 [[TMP49]], i32 [[TMP47]], i32 [[TMP48]]
+; AVX2-NEXT: [[TMP51:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 17), align 4
+; AVX2-NEXT: [[TMP52:%.*]] = icmp sgt i32 [[TMP50]], [[TMP51]]
+; AVX2-NEXT: [[TMP53:%.*]] = select i1 [[TMP52]], i32 [[TMP50]], i32 [[TMP51]]
+; AVX2-NEXT: [[TMP54:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 18), align 8
+; AVX2-NEXT: [[TMP55:%.*]] = icmp sgt i32 [[TMP53]], [[TMP54]]
+; AVX2-NEXT: [[TMP56:%.*]] = select i1 [[TMP55]], i32 [[TMP53]], i32 [[TMP54]]
+; AVX2-NEXT: [[TMP57:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 19), align 4
+; AVX2-NEXT: [[TMP58:%.*]] = icmp sgt i32 [[TMP56]], [[TMP57]]
+; AVX2-NEXT: [[TMP59:%.*]] = select i1 [[TMP58]], i32 [[TMP56]], i32 [[TMP57]]
+; AVX2-NEXT: [[TMP60:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 20), align 16
+; AVX2-NEXT: [[TMP61:%.*]] = icmp sgt i32 [[TMP59]], [[TMP60]]
+; AVX2-NEXT: [[TMP62:%.*]] = select i1 [[TMP61]], i32 [[TMP59]], i32 [[TMP60]]
+; AVX2-NEXT: [[TMP63:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 21), align 4
+; AVX2-NEXT: [[TMP64:%.*]] = icmp sgt i32 [[TMP62]], [[TMP63]]
+; AVX2-NEXT: [[TMP65:%.*]] = select i1 [[TMP64]], i32 [[TMP62]], i32 [[TMP63]]
+; AVX2-NEXT: [[TMP66:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 22), align 8
+; AVX2-NEXT: [[TMP67:%.*]] = icmp sgt i32 [[TMP65]], [[TMP66]]
+; AVX2-NEXT: [[TMP68:%.*]] = select i1 [[TMP67]], i32 [[TMP65]], i32 [[TMP66]]
+; AVX2-NEXT: [[TMP69:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 23), align 4
+; AVX2-NEXT: [[TMP70:%.*]] = icmp sgt i32 [[TMP68]], [[TMP69]]
+; AVX2-NEXT: [[TMP71:%.*]] = select i1 [[TMP70]], i32 [[TMP68]], i32 [[TMP69]]
+; AVX2-NEXT: [[TMP72:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 24), align 16
+; AVX2-NEXT: [[TMP73:%.*]] = icmp sgt i32 [[TMP71]], [[TMP72]]
+; AVX2-NEXT: [[TMP74:%.*]] = select i1 [[TMP73]], i32 [[TMP71]], i32 [[TMP72]]
+; AVX2-NEXT: [[TMP75:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 25), align 4
+; AVX2-NEXT: [[TMP76:%.*]] = icmp sgt i32 [[TMP74]], [[TMP75]]
+; AVX2-NEXT: [[TMP77:%.*]] = select i1 [[TMP76]], i32 [[TMP74]], i32 [[TMP75]]
+; AVX2-NEXT: [[TMP78:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 26), align 8
+; AVX2-NEXT: [[TMP79:%.*]] = icmp sgt i32 [[TMP77]], [[TMP78]]
+; AVX2-NEXT: [[TMP80:%.*]] = select i1 [[TMP79]], i32 [[TMP77]], i32 [[TMP78]]
+; AVX2-NEXT: [[TMP81:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 27), align 4
+; AVX2-NEXT: [[TMP82:%.*]] = icmp sgt i32 [[TMP80]], [[TMP81]]
+; AVX2-NEXT: [[TMP83:%.*]] = select i1 [[TMP82]], i32 [[TMP80]], i32 [[TMP81]]
+; AVX2-NEXT: [[TMP84:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 28), align 16
+; AVX2-NEXT: [[TMP85:%.*]] = icmp sgt i32 [[TMP83]], [[TMP84]]
+; AVX2-NEXT: [[TMP86:%.*]] = select i1 [[TMP85]], i32 [[TMP83]], i32 [[TMP84]]
+; AVX2-NEXT: [[TMP87:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 29), align 4
+; AVX2-NEXT: [[TMP88:%.*]] = icmp sgt i32 [[TMP86]], [[TMP87]]
+; AVX2-NEXT: [[TMP89:%.*]] = select i1 [[TMP88]], i32 [[TMP86]], i32 [[TMP87]]
+; AVX2-NEXT: [[TMP90:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 30), align 8
+; AVX2-NEXT: [[TMP91:%.*]] = icmp sgt i32 [[TMP89]], [[TMP90]]
+; AVX2-NEXT: [[TMP92:%.*]] = select i1 [[TMP91]], i32 [[TMP89]], i32 [[TMP90]]
+; AVX2-NEXT: [[TMP93:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 31), align 4
+; AVX2-NEXT: [[TMP94:%.*]] = icmp sgt i32 [[TMP92]], [[TMP93]]
+; AVX2-NEXT: [[TMP95:%.*]] = select i1 [[TMP94]], i32 [[TMP92]], i32 [[TMP93]]
+; AVX2-NEXT: ret i32 [[TMP95]]
+;
+; SKX-LABEL: @maxi32(
+; SKX-NEXT: [[TMP2:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 0), align 16
+; SKX-NEXT: [[TMP3:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 1), align 4
+; SKX-NEXT: [[TMP4:%.*]] = icmp sgt i32 [[TMP2]], [[TMP3]]
+; SKX-NEXT: [[TMP5:%.*]] = select i1 [[TMP4]], i32 [[TMP2]], i32 [[TMP3]]
+; SKX-NEXT: [[TMP6:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 2), align 8
+; SKX-NEXT: [[TMP7:%.*]] = icmp sgt i32 [[TMP5]], [[TMP6]]
+; SKX-NEXT: [[TMP8:%.*]] = select i1 [[TMP7]], i32 [[TMP5]], i32 [[TMP6]]
+; SKX-NEXT: [[TMP9:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 3), align 4
+; SKX-NEXT: [[TMP10:%.*]] = icmp sgt i32 [[TMP8]], [[TMP9]]
+; SKX-NEXT: [[TMP11:%.*]] = select i1 [[TMP10]], i32 [[TMP8]], i32 [[TMP9]]
+; SKX-NEXT: [[TMP12:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 4), align 16
+; SKX-NEXT: [[TMP13:%.*]] = icmp sgt i32 [[TMP11]], [[TMP12]]
+; SKX-NEXT: [[TMP14:%.*]] = select i1 [[TMP13]], i32 [[TMP11]], i32 [[TMP12]]
+; SKX-NEXT: [[TMP15:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 5), align 4
+; SKX-NEXT: [[TMP16:%.*]] = icmp sgt i32 [[TMP14]], [[TMP15]]
+; SKX-NEXT: [[TMP17:%.*]] = select i1 [[TMP16]], i32 [[TMP14]], i32 [[TMP15]]
+; SKX-NEXT: [[TMP18:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 6), align 8
+; SKX-NEXT: [[TMP19:%.*]] = icmp sgt i32 [[TMP17]], [[TMP18]]
+; SKX-NEXT: [[TMP20:%.*]] = select i1 [[TMP19]], i32 [[TMP17]], i32 [[TMP18]]
+; SKX-NEXT: [[TMP21:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 7), align 4
+; SKX-NEXT: [[TMP22:%.*]] = icmp sgt i32 [[TMP20]], [[TMP21]]
+; SKX-NEXT: [[TMP23:%.*]] = select i1 [[TMP22]], i32 [[TMP20]], i32 [[TMP21]]
+; SKX-NEXT: [[TMP24:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 8), align 16
+; SKX-NEXT: [[TMP25:%.*]] = icmp sgt i32 [[TMP23]], [[TMP24]]
+; SKX-NEXT: [[TMP26:%.*]] = select i1 [[TMP25]], i32 [[TMP23]], i32 [[TMP24]]
+; SKX-NEXT: [[TMP27:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 9), align 4
+; SKX-NEXT: [[TMP28:%.*]] = icmp sgt i32 [[TMP26]], [[TMP27]]
+; SKX-NEXT: [[TMP29:%.*]] = select i1 [[TMP28]], i32 [[TMP26]], i32 [[TMP27]]
+; SKX-NEXT: [[TMP30:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 10), align 8
+; SKX-NEXT: [[TMP31:%.*]] = icmp sgt i32 [[TMP29]], [[TMP30]]
+; SKX-NEXT: [[TMP32:%.*]] = select i1 [[TMP31]], i32 [[TMP29]], i32 [[TMP30]]
+; SKX-NEXT: [[TMP33:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 11), align 4
+; SKX-NEXT: [[TMP34:%.*]] = icmp sgt i32 [[TMP32]], [[TMP33]]
+; SKX-NEXT: [[TMP35:%.*]] = select i1 [[TMP34]], i32 [[TMP32]], i32 [[TMP33]]
+; SKX-NEXT: [[TMP36:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 12), align 16
+; SKX-NEXT: [[TMP37:%.*]] = icmp sgt i32 [[TMP35]], [[TMP36]]
+; SKX-NEXT: [[TMP38:%.*]] = select i1 [[TMP37]], i32 [[TMP35]], i32 [[TMP36]]
+; SKX-NEXT: [[TMP39:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 13), align 4
+; SKX-NEXT: [[TMP40:%.*]] = icmp sgt i32 [[TMP38]], [[TMP39]]
+; SKX-NEXT: [[TMP41:%.*]] = select i1 [[TMP40]], i32 [[TMP38]], i32 [[TMP39]]
+; SKX-NEXT: [[TMP42:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 14), align 8
+; SKX-NEXT: [[TMP43:%.*]] = icmp sgt i32 [[TMP41]], [[TMP42]]
+; SKX-NEXT: [[TMP44:%.*]] = select i1 [[TMP43]], i32 [[TMP41]], i32 [[TMP42]]
+; SKX-NEXT: [[TMP45:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 15), align 4
+; SKX-NEXT: [[TMP46:%.*]] = icmp sgt i32 [[TMP44]], [[TMP45]]
+; SKX-NEXT: [[TMP47:%.*]] = select i1 [[TMP46]], i32 [[TMP44]], i32 [[TMP45]]
+; SKX-NEXT: [[TMP48:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 16), align 16
+; SKX-NEXT: [[TMP49:%.*]] = icmp sgt i32 [[TMP47]], [[TMP48]]
+; SKX-NEXT: [[TMP50:%.*]] = select i1 [[TMP49]], i32 [[TMP47]], i32 [[TMP48]]
+; SKX-NEXT: [[TMP51:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 17), align 4
+; SKX-NEXT: [[TMP52:%.*]] = icmp sgt i32 [[TMP50]], [[TMP51]]
+; SKX-NEXT: [[TMP53:%.*]] = select i1 [[TMP52]], i32 [[TMP50]], i32 [[TMP51]]
+; SKX-NEXT: [[TMP54:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 18), align 8
+; SKX-NEXT: [[TMP55:%.*]] = icmp sgt i32 [[TMP53]], [[TMP54]]
+; SKX-NEXT: [[TMP56:%.*]] = select i1 [[TMP55]], i32 [[TMP53]], i32 [[TMP54]]
+; SKX-NEXT: [[TMP57:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 19), align 4
+; SKX-NEXT: [[TMP58:%.*]] = icmp sgt i32 [[TMP56]], [[TMP57]]
+; SKX-NEXT: [[TMP59:%.*]] = select i1 [[TMP58]], i32 [[TMP56]], i32 [[TMP57]]
+; SKX-NEXT: [[TMP60:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 20), align 16
+; SKX-NEXT: [[TMP61:%.*]] = icmp sgt i32 [[TMP59]], [[TMP60]]
+; SKX-NEXT: [[TMP62:%.*]] = select i1 [[TMP61]], i32 [[TMP59]], i32 [[TMP60]]
+; SKX-NEXT: [[TMP63:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 21), align 4
+; SKX-NEXT: [[TMP64:%.*]] = icmp sgt i32 [[TMP62]], [[TMP63]]
+; SKX-NEXT: [[TMP65:%.*]] = select i1 [[TMP64]], i32 [[TMP62]], i32 [[TMP63]]
+; SKX-NEXT: [[TMP66:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 22), align 8
+; SKX-NEXT: [[TMP67:%.*]] = icmp sgt i32 [[TMP65]], [[TMP66]]
+; SKX-NEXT: [[TMP68:%.*]] = select i1 [[TMP67]], i32 [[TMP65]], i32 [[TMP66]]
+; SKX-NEXT: [[TMP69:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 23), align 4
+; SKX-NEXT: [[TMP70:%.*]] = icmp sgt i32 [[TMP68]], [[TMP69]]
+; SKX-NEXT: [[TMP71:%.*]] = select i1 [[TMP70]], i32 [[TMP68]], i32 [[TMP69]]
+; SKX-NEXT: [[TMP72:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 24), align 16
+; SKX-NEXT: [[TMP73:%.*]] = icmp sgt i32 [[TMP71]], [[TMP72]]
+; SKX-NEXT: [[TMP74:%.*]] = select i1 [[TMP73]], i32 [[TMP71]], i32 [[TMP72]]
+; SKX-NEXT: [[TMP75:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 25), align 4
+; SKX-NEXT: [[TMP76:%.*]] = icmp sgt i32 [[TMP74]], [[TMP75]]
+; SKX-NEXT: [[TMP77:%.*]] = select i1 [[TMP76]], i32 [[TMP74]], i32 [[TMP75]]
+; SKX-NEXT: [[TMP78:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 26), align 8
+; SKX-NEXT: [[TMP79:%.*]] = icmp sgt i32 [[TMP77]], [[TMP78]]
+; SKX-NEXT: [[TMP80:%.*]] = select i1 [[TMP79]], i32 [[TMP77]], i32 [[TMP78]]
+; SKX-NEXT: [[TMP81:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 27), align 4
+; SKX-NEXT: [[TMP82:%.*]] = icmp sgt i32 [[TMP80]], [[TMP81]]
+; SKX-NEXT: [[TMP83:%.*]] = select i1 [[TMP82]], i32 [[TMP80]], i32 [[TMP81]]
+; SKX-NEXT: [[TMP84:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 28), align 16
+; SKX-NEXT: [[TMP85:%.*]] = icmp sgt i32 [[TMP83]], [[TMP84]]
+; SKX-NEXT: [[TMP86:%.*]] = select i1 [[TMP85]], i32 [[TMP83]], i32 [[TMP84]]
+; SKX-NEXT: [[TMP87:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 29), align 4
+; SKX-NEXT: [[TMP88:%.*]] = icmp sgt i32 [[TMP86]], [[TMP87]]
+; SKX-NEXT: [[TMP89:%.*]] = select i1 [[TMP88]], i32 [[TMP86]], i32 [[TMP87]]
+; SKX-NEXT: [[TMP90:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 30), align 8
+; SKX-NEXT: [[TMP91:%.*]] = icmp sgt i32 [[TMP89]], [[TMP90]]
+; SKX-NEXT: [[TMP92:%.*]] = select i1 [[TMP91]], i32 [[TMP89]], i32 [[TMP90]]
+; SKX-NEXT: [[TMP93:%.*]] = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 31), align 4
+; SKX-NEXT: [[TMP94:%.*]] = icmp sgt i32 [[TMP92]], [[TMP93]]
+; SKX-NEXT: [[TMP95:%.*]] = select i1 [[TMP94]], i32 [[TMP92]], i32 [[TMP93]]
+; SKX-NEXT: ret i32 [[TMP95]]
+;
+ %2 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 0), align 16
+ %3 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 1), align 4
+ %4 = icmp sgt i32 %2, %3
+ %5 = select i1 %4, i32 %2, i32 %3
+ %6 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 2), align 8
+ %7 = icmp sgt i32 %5, %6
+ %8 = select i1 %7, i32 %5, i32 %6
+ %9 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 3), align 4
+ %10 = icmp sgt i32 %8, %9
+ %11 = select i1 %10, i32 %8, i32 %9
+ %12 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 4), align 16
+ %13 = icmp sgt i32 %11, %12
+ %14 = select i1 %13, i32 %11, i32 %12
+ %15 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 5), align 4
+ %16 = icmp sgt i32 %14, %15
+ %17 = select i1 %16, i32 %14, i32 %15
+ %18 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 6), align 8
+ %19 = icmp sgt i32 %17, %18
+ %20 = select i1 %19, i32 %17, i32 %18
+ %21 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 7), align 4
+ %22 = icmp sgt i32 %20, %21
+ %23 = select i1 %22, i32 %20, i32 %21
+ %24 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 8), align 16
+ %25 = icmp sgt i32 %23, %24
+ %26 = select i1 %25, i32 %23, i32 %24
+ %27 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 9), align 4
+ %28 = icmp sgt i32 %26, %27
+ %29 = select i1 %28, i32 %26, i32 %27
+ %30 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 10), align 8
+ %31 = icmp sgt i32 %29, %30
+ %32 = select i1 %31, i32 %29, i32 %30
+ %33 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 11), align 4
+ %34 = icmp sgt i32 %32, %33
+ %35 = select i1 %34, i32 %32, i32 %33
+ %36 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 12), align 16
+ %37 = icmp sgt i32 %35, %36
+ %38 = select i1 %37, i32 %35, i32 %36
+ %39 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 13), align 4
+ %40 = icmp sgt i32 %38, %39
+ %41 = select i1 %40, i32 %38, i32 %39
+ %42 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 14), align 8
+ %43 = icmp sgt i32 %41, %42
+ %44 = select i1 %43, i32 %41, i32 %42
+ %45 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 15), align 4
+ %46 = icmp sgt i32 %44, %45
+ %47 = select i1 %46, i32 %44, i32 %45
+ %48 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 16), align 16
+ %49 = icmp sgt i32 %47, %48
+ %50 = select i1 %49, i32 %47, i32 %48
+ %51 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 17), align 4
+ %52 = icmp sgt i32 %50, %51
+ %53 = select i1 %52, i32 %50, i32 %51
+ %54 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 18), align 8
+ %55 = icmp sgt i32 %53, %54
+ %56 = select i1 %55, i32 %53, i32 %54
+ %57 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 19), align 4
+ %58 = icmp sgt i32 %56, %57
+ %59 = select i1 %58, i32 %56, i32 %57
+ %60 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 20), align 16
+ %61 = icmp sgt i32 %59, %60
+ %62 = select i1 %61, i32 %59, i32 %60
+ %63 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 21), align 4
+ %64 = icmp sgt i32 %62, %63
+ %65 = select i1 %64, i32 %62, i32 %63
+ %66 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 22), align 8
+ %67 = icmp sgt i32 %65, %66
+ %68 = select i1 %67, i32 %65, i32 %66
+ %69 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 23), align 4
+ %70 = icmp sgt i32 %68, %69
+ %71 = select i1 %70, i32 %68, i32 %69
+ %72 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 24), align 16
+ %73 = icmp sgt i32 %71, %72
+ %74 = select i1 %73, i32 %71, i32 %72
+ %75 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 25), align 4
+ %76 = icmp sgt i32 %74, %75
+ %77 = select i1 %76, i32 %74, i32 %75
+ %78 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 26), align 8
+ %79 = icmp sgt i32 %77, %78
+ %80 = select i1 %79, i32 %77, i32 %78
+ %81 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 27), align 4
+ %82 = icmp sgt i32 %80, %81
+ %83 = select i1 %82, i32 %80, i32 %81
+ %84 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 28), align 16
+ %85 = icmp sgt i32 %83, %84
+ %86 = select i1 %85, i32 %83, i32 %84
+ %87 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 29), align 4
+ %88 = icmp sgt i32 %86, %87
+ %89 = select i1 %88, i32 %86, i32 %87
+ %90 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 30), align 8
+ %91 = icmp sgt i32 %89, %90
+ %92 = select i1 %91, i32 %89, i32 %90
+ %93 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 31), align 4
+ %94 = icmp sgt i32 %92, %93
+ %95 = select i1 %94, i32 %92, i32 %93
+ ret i32 %95
+}
+
+define float @maxf8(float) {
+; CHECK-LABEL: @maxf8(
+; CHECK-NEXT: [[TMP2:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 0), align 16
+; CHECK-NEXT: [[TMP3:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 1), align 4
+; CHECK-NEXT: [[TMP4:%.*]] = fcmp fast ogt float [[TMP2]], [[TMP3]]
+; CHECK-NEXT: [[TMP5:%.*]] = select i1 [[TMP4]], float [[TMP2]], float [[TMP3]]
+; CHECK-NEXT: [[TMP6:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 2), align 8
+; CHECK-NEXT: [[TMP7:%.*]] = fcmp fast ogt float [[TMP5]], [[TMP6]]
+; CHECK-NEXT: [[TMP8:%.*]] = select i1 [[TMP7]], float [[TMP5]], float [[TMP6]]
+; CHECK-NEXT: [[TMP9:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 3), align 4
+; CHECK-NEXT: [[TMP10:%.*]] = fcmp fast ogt float [[TMP8]], [[TMP9]]
+; CHECK-NEXT: [[TMP11:%.*]] = select i1 [[TMP10]], float [[TMP8]], float [[TMP9]]
+; CHECK-NEXT: [[TMP12:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 4), align 16
+; CHECK-NEXT: [[TMP13:%.*]] = fcmp fast ogt float [[TMP11]], [[TMP12]]
+; CHECK-NEXT: [[TMP14:%.*]] = select i1 [[TMP13]], float [[TMP11]], float [[TMP12]]
+; CHECK-NEXT: [[TMP15:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 5), align 4
+; CHECK-NEXT: [[TMP16:%.*]] = fcmp fast ogt float [[TMP14]], [[TMP15]]
+; CHECK-NEXT: [[TMP17:%.*]] = select i1 [[TMP16]], float [[TMP14]], float [[TMP15]]
+; CHECK-NEXT: [[TMP18:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 6), align 8
+; CHECK-NEXT: [[TMP19:%.*]] = fcmp fast ogt float [[TMP17]], [[TMP18]]
+; CHECK-NEXT: [[TMP20:%.*]] = select i1 [[TMP19]], float [[TMP17]], float [[TMP18]]
+; CHECK-NEXT: [[TMP21:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 7), align 4
+; CHECK-NEXT: [[TMP22:%.*]] = fcmp fast ogt float [[TMP20]], [[TMP21]]
+; CHECK-NEXT: [[TMP23:%.*]] = select i1 [[TMP22]], float [[TMP20]], float [[TMP21]]
+; CHECK-NEXT: ret float [[TMP23]]
+;
+; AVX-LABEL: @maxf8(
+; AVX-NEXT: [[TMP2:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 0), align 16
+; AVX-NEXT: [[TMP3:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 1), align 4
+; AVX-NEXT: [[TMP4:%.*]] = fcmp fast ogt float [[TMP2]], [[TMP3]]
+; AVX-NEXT: [[TMP5:%.*]] = select i1 [[TMP4]], float [[TMP2]], float [[TMP3]]
+; AVX-NEXT: [[TMP6:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 2), align 8
+; AVX-NEXT: [[TMP7:%.*]] = fcmp fast ogt float [[TMP5]], [[TMP6]]
+; AVX-NEXT: [[TMP8:%.*]] = select i1 [[TMP7]], float [[TMP5]], float [[TMP6]]
+; AVX-NEXT: [[TMP9:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 3), align 4
+; AVX-NEXT: [[TMP10:%.*]] = fcmp fast ogt float [[TMP8]], [[TMP9]]
+; AVX-NEXT: [[TMP11:%.*]] = select i1 [[TMP10]], float [[TMP8]], float [[TMP9]]
+; AVX-NEXT: [[TMP12:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 4), align 16
+; AVX-NEXT: [[TMP13:%.*]] = fcmp fast ogt float [[TMP11]], [[TMP12]]
+; AVX-NEXT: [[TMP14:%.*]] = select i1 [[TMP13]], float [[TMP11]], float [[TMP12]]
+; AVX-NEXT: [[TMP15:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 5), align 4
+; AVX-NEXT: [[TMP16:%.*]] = fcmp fast ogt float [[TMP14]], [[TMP15]]
+; AVX-NEXT: [[TMP17:%.*]] = select i1 [[TMP16]], float [[TMP14]], float [[TMP15]]
+; AVX-NEXT: [[TMP18:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 6), align 8
+; AVX-NEXT: [[TMP19:%.*]] = fcmp fast ogt float [[TMP17]], [[TMP18]]
+; AVX-NEXT: [[TMP20:%.*]] = select i1 [[TMP19]], float [[TMP17]], float [[TMP18]]
+; AVX-NEXT: [[TMP21:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 7), align 4
+; AVX-NEXT: [[TMP22:%.*]] = fcmp fast ogt float [[TMP20]], [[TMP21]]
+; AVX-NEXT: [[TMP23:%.*]] = select i1 [[TMP22]], float [[TMP20]], float [[TMP21]]
+; AVX-NEXT: ret float [[TMP23]]
+;
+; AVX2-LABEL: @maxf8(
+; AVX2-NEXT: [[TMP2:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 0), align 16
+; AVX2-NEXT: [[TMP3:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 1), align 4
+; AVX2-NEXT: [[TMP4:%.*]] = fcmp fast ogt float [[TMP2]], [[TMP3]]
+; AVX2-NEXT: [[TMP5:%.*]] = select i1 [[TMP4]], float [[TMP2]], float [[TMP3]]
+; AVX2-NEXT: [[TMP6:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 2), align 8
+; AVX2-NEXT: [[TMP7:%.*]] = fcmp fast ogt float [[TMP5]], [[TMP6]]
+; AVX2-NEXT: [[TMP8:%.*]] = select i1 [[TMP7]], float [[TMP5]], float [[TMP6]]
+; AVX2-NEXT: [[TMP9:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 3), align 4
+; AVX2-NEXT: [[TMP10:%.*]] = fcmp fast ogt float [[TMP8]], [[TMP9]]
+; AVX2-NEXT: [[TMP11:%.*]] = select i1 [[TMP10]], float [[TMP8]], float [[TMP9]]
+; AVX2-NEXT: [[TMP12:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 4), align 16
+; AVX2-NEXT: [[TMP13:%.*]] = fcmp fast ogt float [[TMP11]], [[TMP12]]
+; AVX2-NEXT: [[TMP14:%.*]] = select i1 [[TMP13]], float [[TMP11]], float [[TMP12]]
+; AVX2-NEXT: [[TMP15:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 5), align 4
+; AVX2-NEXT: [[TMP16:%.*]] = fcmp fast ogt float [[TMP14]], [[TMP15]]
+; AVX2-NEXT: [[TMP17:%.*]] = select i1 [[TMP16]], float [[TMP14]], float [[TMP15]]
+; AVX2-NEXT: [[TMP18:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 6), align 8
+; AVX2-NEXT: [[TMP19:%.*]] = fcmp fast ogt float [[TMP17]], [[TMP18]]
+; AVX2-NEXT: [[TMP20:%.*]] = select i1 [[TMP19]], float [[TMP17]], float [[TMP18]]
+; AVX2-NEXT: [[TMP21:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 7), align 4
+; AVX2-NEXT: [[TMP22:%.*]] = fcmp fast ogt float [[TMP20]], [[TMP21]]
+; AVX2-NEXT: [[TMP23:%.*]] = select i1 [[TMP22]], float [[TMP20]], float [[TMP21]]
+; AVX2-NEXT: ret float [[TMP23]]
+;
+; SKX-LABEL: @maxf8(
+; SKX-NEXT: [[TMP2:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 0), align 16
+; SKX-NEXT: [[TMP3:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 1), align 4
+; SKX-NEXT: [[TMP4:%.*]] = fcmp fast ogt float [[TMP2]], [[TMP3]]
+; SKX-NEXT: [[TMP5:%.*]] = select i1 [[TMP4]], float [[TMP2]], float [[TMP3]]
+; SKX-NEXT: [[TMP6:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 2), align 8
+; SKX-NEXT: [[TMP7:%.*]] = fcmp fast ogt float [[TMP5]], [[TMP6]]
+; SKX-NEXT: [[TMP8:%.*]] = select i1 [[TMP7]], float [[TMP5]], float [[TMP6]]
+; SKX-NEXT: [[TMP9:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 3), align 4
+; SKX-NEXT: [[TMP10:%.*]] = fcmp fast ogt float [[TMP8]], [[TMP9]]
+; SKX-NEXT: [[TMP11:%.*]] = select i1 [[TMP10]], float [[TMP8]], float [[TMP9]]
+; SKX-NEXT: [[TMP12:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 4), align 16
+; SKX-NEXT: [[TMP13:%.*]] = fcmp fast ogt float [[TMP11]], [[TMP12]]
+; SKX-NEXT: [[TMP14:%.*]] = select i1 [[TMP13]], float [[TMP11]], float [[TMP12]]
+; SKX-NEXT: [[TMP15:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 5), align 4
+; SKX-NEXT: [[TMP16:%.*]] = fcmp fast ogt float [[TMP14]], [[TMP15]]
+; SKX-NEXT: [[TMP17:%.*]] = select i1 [[TMP16]], float [[TMP14]], float [[TMP15]]
+; SKX-NEXT: [[TMP18:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 6), align 8
+; SKX-NEXT: [[TMP19:%.*]] = fcmp fast ogt float [[TMP17]], [[TMP18]]
+; SKX-NEXT: [[TMP20:%.*]] = select i1 [[TMP19]], float [[TMP17]], float [[TMP18]]
+; SKX-NEXT: [[TMP21:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 7), align 4
+; SKX-NEXT: [[TMP22:%.*]] = fcmp fast ogt float [[TMP20]], [[TMP21]]
+; SKX-NEXT: [[TMP23:%.*]] = select i1 [[TMP22]], float [[TMP20]], float [[TMP21]]
+; SKX-NEXT: ret float [[TMP23]]
+;
+ %2 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 0), align 16
+ %3 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 1), align 4
+ %4 = fcmp fast ogt float %2, %3
+ %5 = select i1 %4, float %2, float %3
+ %6 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 2), align 8
+ %7 = fcmp fast ogt float %5, %6
+ %8 = select i1 %7, float %5, float %6
+ %9 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 3), align 4
+ %10 = fcmp fast ogt float %8, %9
+ %11 = select i1 %10, float %8, float %9
+ %12 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 4), align 16
+ %13 = fcmp fast ogt float %11, %12
+ %14 = select i1 %13, float %11, float %12
+ %15 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 5), align 4
+ %16 = fcmp fast ogt float %14, %15
+ %17 = select i1 %16, float %14, float %15
+ %18 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 6), align 8
+ %19 = fcmp fast ogt float %17, %18
+ %20 = select i1 %19, float %17, float %18
+ %21 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 7), align 4
+ %22 = fcmp fast ogt float %20, %21
+ %23 = select i1 %22, float %20, float %21
+ ret float %23
+}
+
+define float @maxf16(float) {
+; CHECK-LABEL: @maxf16(
+; CHECK-NEXT: [[TMP2:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 0), align 16
+; CHECK-NEXT: [[TMP3:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 1), align 4
+; CHECK-NEXT: [[TMP4:%.*]] = fcmp fast ogt float [[TMP2]], [[TMP3]]
+; CHECK-NEXT: [[TMP5:%.*]] = select i1 [[TMP4]], float [[TMP2]], float [[TMP3]]
+; CHECK-NEXT: [[TMP6:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 2), align 8
+; CHECK-NEXT: [[TMP7:%.*]] = fcmp fast ogt float [[TMP5]], [[TMP6]]
+; CHECK-NEXT: [[TMP8:%.*]] = select i1 [[TMP7]], float [[TMP5]], float [[TMP6]]
+; CHECK-NEXT: [[TMP9:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 3), align 4
+; CHECK-NEXT: [[TMP10:%.*]] = fcmp fast ogt float [[TMP8]], [[TMP9]]
+; CHECK-NEXT: [[TMP11:%.*]] = select i1 [[TMP10]], float [[TMP8]], float [[TMP9]]
+; CHECK-NEXT: [[TMP12:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 4), align 16
+; CHECK-NEXT: [[TMP13:%.*]] = fcmp fast ogt float [[TMP11]], [[TMP12]]
+; CHECK-NEXT: [[TMP14:%.*]] = select i1 [[TMP13]], float [[TMP11]], float [[TMP12]]
+; CHECK-NEXT: [[TMP15:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 5), align 4
+; CHECK-NEXT: [[TMP16:%.*]] = fcmp fast ogt float [[TMP14]], [[TMP15]]
+; CHECK-NEXT: [[TMP17:%.*]] = select i1 [[TMP16]], float [[TMP14]], float [[TMP15]]
+; CHECK-NEXT: [[TMP18:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 6), align 8
+; CHECK-NEXT: [[TMP19:%.*]] = fcmp fast ogt float [[TMP17]], [[TMP18]]
+; CHECK-NEXT: [[TMP20:%.*]] = select i1 [[TMP19]], float [[TMP17]], float [[TMP18]]
+; CHECK-NEXT: [[TMP21:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 7), align 4
+; CHECK-NEXT: [[TMP22:%.*]] = fcmp fast ogt float [[TMP20]], [[TMP21]]
+; CHECK-NEXT: [[TMP23:%.*]] = select i1 [[TMP22]], float [[TMP20]], float [[TMP21]]
+; CHECK-NEXT: [[TMP24:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 8), align 16
+; CHECK-NEXT: [[TMP25:%.*]] = fcmp fast ogt float [[TMP23]], [[TMP24]]
+; CHECK-NEXT: [[TMP26:%.*]] = select i1 [[TMP25]], float [[TMP23]], float [[TMP24]]
+; CHECK-NEXT: [[TMP27:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 9), align 4
+; CHECK-NEXT: [[TMP28:%.*]] = fcmp fast ogt float [[TMP26]], [[TMP27]]
+; CHECK-NEXT: [[TMP29:%.*]] = select i1 [[TMP28]], float [[TMP26]], float [[TMP27]]
+; CHECK-NEXT: [[TMP30:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 10), align 8
+; CHECK-NEXT: [[TMP31:%.*]] = fcmp fast ogt float [[TMP29]], [[TMP30]]
+; CHECK-NEXT: [[TMP32:%.*]] = select i1 [[TMP31]], float [[TMP29]], float [[TMP30]]
+; CHECK-NEXT: [[TMP33:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 11), align 4
+; CHECK-NEXT: [[TMP34:%.*]] = fcmp fast ogt float [[TMP32]], [[TMP33]]
+; CHECK-NEXT: [[TMP35:%.*]] = select i1 [[TMP34]], float [[TMP32]], float [[TMP33]]
+; CHECK-NEXT: [[TMP36:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 12), align 16
+; CHECK-NEXT: [[TMP37:%.*]] = fcmp fast ogt float [[TMP35]], [[TMP36]]
+; CHECK-NEXT: [[TMP38:%.*]] = select i1 [[TMP37]], float [[TMP35]], float [[TMP36]]
+; CHECK-NEXT: [[TMP39:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 13), align 4
+; CHECK-NEXT: [[TMP40:%.*]] = fcmp fast ogt float [[TMP38]], [[TMP39]]
+; CHECK-NEXT: [[TMP41:%.*]] = select i1 [[TMP40]], float [[TMP38]], float [[TMP39]]
+; CHECK-NEXT: [[TMP42:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 14), align 8
+; CHECK-NEXT: [[TMP43:%.*]] = fcmp fast ogt float [[TMP41]], [[TMP42]]
+; CHECK-NEXT: [[TMP44:%.*]] = select i1 [[TMP43]], float [[TMP41]], float [[TMP42]]
+; CHECK-NEXT: [[TMP45:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 15), align 4
+; CHECK-NEXT: [[TMP46:%.*]] = fcmp fast ogt float [[TMP44]], [[TMP45]]
+; CHECK-NEXT: [[TMP47:%.*]] = select i1 [[TMP46]], float [[TMP44]], float [[TMP45]]
+; CHECK-NEXT: ret float [[TMP47]]
+;
+; AVX-LABEL: @maxf16(
+; AVX-NEXT: [[TMP2:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 0), align 16
+; AVX-NEXT: [[TMP3:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 1), align 4
+; AVX-NEXT: [[TMP4:%.*]] = fcmp fast ogt float [[TMP2]], [[TMP3]]
+; AVX-NEXT: [[TMP5:%.*]] = select i1 [[TMP4]], float [[TMP2]], float [[TMP3]]
+; AVX-NEXT: [[TMP6:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 2), align 8
+; AVX-NEXT: [[TMP7:%.*]] = fcmp fast ogt float [[TMP5]], [[TMP6]]
+; AVX-NEXT: [[TMP8:%.*]] = select i1 [[TMP7]], float [[TMP5]], float [[TMP6]]
+; AVX-NEXT: [[TMP9:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 3), align 4
+; AVX-NEXT: [[TMP10:%.*]] = fcmp fast ogt float [[TMP8]], [[TMP9]]
+; AVX-NEXT: [[TMP11:%.*]] = select i1 [[TMP10]], float [[TMP8]], float [[TMP9]]
+; AVX-NEXT: [[TMP12:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 4), align 16
+; AVX-NEXT: [[TMP13:%.*]] = fcmp fast ogt float [[TMP11]], [[TMP12]]
+; AVX-NEXT: [[TMP14:%.*]] = select i1 [[TMP13]], float [[TMP11]], float [[TMP12]]
+; AVX-NEXT: [[TMP15:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 5), align 4
+; AVX-NEXT: [[TMP16:%.*]] = fcmp fast ogt float [[TMP14]], [[TMP15]]
+; AVX-NEXT: [[TMP17:%.*]] = select i1 [[TMP16]], float [[TMP14]], float [[TMP15]]
+; AVX-NEXT: [[TMP18:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 6), align 8
+; AVX-NEXT: [[TMP19:%.*]] = fcmp fast ogt float [[TMP17]], [[TMP18]]
+; AVX-NEXT: [[TMP20:%.*]] = select i1 [[TMP19]], float [[TMP17]], float [[TMP18]]
+; AVX-NEXT: [[TMP21:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 7), align 4
+; AVX-NEXT: [[TMP22:%.*]] = fcmp fast ogt float [[TMP20]], [[TMP21]]
+; AVX-NEXT: [[TMP23:%.*]] = select i1 [[TMP22]], float [[TMP20]], float [[TMP21]]
+; AVX-NEXT: [[TMP24:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 8), align 16
+; AVX-NEXT: [[TMP25:%.*]] = fcmp fast ogt float [[TMP23]], [[TMP24]]
+; AVX-NEXT: [[TMP26:%.*]] = select i1 [[TMP25]], float [[TMP23]], float [[TMP24]]
+; AVX-NEXT: [[TMP27:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 9), align 4
+; AVX-NEXT: [[TMP28:%.*]] = fcmp fast ogt float [[TMP26]], [[TMP27]]
+; AVX-NEXT: [[TMP29:%.*]] = select i1 [[TMP28]], float [[TMP26]], float [[TMP27]]
+; AVX-NEXT: [[TMP30:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 10), align 8
+; AVX-NEXT: [[TMP31:%.*]] = fcmp fast ogt float [[TMP29]], [[TMP30]]
+; AVX-NEXT: [[TMP32:%.*]] = select i1 [[TMP31]], float [[TMP29]], float [[TMP30]]
+; AVX-NEXT: [[TMP33:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 11), align 4
+; AVX-NEXT: [[TMP34:%.*]] = fcmp fast ogt float [[TMP32]], [[TMP33]]
+; AVX-NEXT: [[TMP35:%.*]] = select i1 [[TMP34]], float [[TMP32]], float [[TMP33]]
+; AVX-NEXT: [[TMP36:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 12), align 16
+; AVX-NEXT: [[TMP37:%.*]] = fcmp fast ogt float [[TMP35]], [[TMP36]]
+; AVX-NEXT: [[TMP38:%.*]] = select i1 [[TMP37]], float [[TMP35]], float [[TMP36]]
+; AVX-NEXT: [[TMP39:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 13), align 4
+; AVX-NEXT: [[TMP40:%.*]] = fcmp fast ogt float [[TMP38]], [[TMP39]]
+; AVX-NEXT: [[TMP41:%.*]] = select i1 [[TMP40]], float [[TMP38]], float [[TMP39]]
+; AVX-NEXT: [[TMP42:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 14), align 8
+; AVX-NEXT: [[TMP43:%.*]] = fcmp fast ogt float [[TMP41]], [[TMP42]]
+; AVX-NEXT: [[TMP44:%.*]] = select i1 [[TMP43]], float [[TMP41]], float [[TMP42]]
+; AVX-NEXT: [[TMP45:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 15), align 4
+; AVX-NEXT: [[TMP46:%.*]] = fcmp fast ogt float [[TMP44]], [[TMP45]]
+; AVX-NEXT: [[TMP47:%.*]] = select i1 [[TMP46]], float [[TMP44]], float [[TMP45]]
+; AVX-NEXT: ret float [[TMP47]]
+;
+; AVX2-LABEL: @maxf16(
+; AVX2-NEXT: [[TMP2:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 0), align 16
+; AVX2-NEXT: [[TMP3:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 1), align 4
+; AVX2-NEXT: [[TMP4:%.*]] = fcmp fast ogt float [[TMP2]], [[TMP3]]
+; AVX2-NEXT: [[TMP5:%.*]] = select i1 [[TMP4]], float [[TMP2]], float [[TMP3]]
+; AVX2-NEXT: [[TMP6:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 2), align 8
+; AVX2-NEXT: [[TMP7:%.*]] = fcmp fast ogt float [[TMP5]], [[TMP6]]
+; AVX2-NEXT: [[TMP8:%.*]] = select i1 [[TMP7]], float [[TMP5]], float [[TMP6]]
+; AVX2-NEXT: [[TMP9:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 3), align 4
+; AVX2-NEXT: [[TMP10:%.*]] = fcmp fast ogt float [[TMP8]], [[TMP9]]
+; AVX2-NEXT: [[TMP11:%.*]] = select i1 [[TMP10]], float [[TMP8]], float [[TMP9]]
+; AVX2-NEXT: [[TMP12:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 4), align 16
+; AVX2-NEXT: [[TMP13:%.*]] = fcmp fast ogt float [[TMP11]], [[TMP12]]
+; AVX2-NEXT: [[TMP14:%.*]] = select i1 [[TMP13]], float [[TMP11]], float [[TMP12]]
+; AVX2-NEXT: [[TMP15:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 5), align 4
+; AVX2-NEXT: [[TMP16:%.*]] = fcmp fast ogt float [[TMP14]], [[TMP15]]
+; AVX2-NEXT: [[TMP17:%.*]] = select i1 [[TMP16]], float [[TMP14]], float [[TMP15]]
+; AVX2-NEXT: [[TMP18:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 6), align 8
+; AVX2-NEXT: [[TMP19:%.*]] = fcmp fast ogt float [[TMP17]], [[TMP18]]
+; AVX2-NEXT: [[TMP20:%.*]] = select i1 [[TMP19]], float [[TMP17]], float [[TMP18]]
+; AVX2-NEXT: [[TMP21:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 7), align 4
+; AVX2-NEXT: [[TMP22:%.*]] = fcmp fast ogt float [[TMP20]], [[TMP21]]
+; AVX2-NEXT: [[TMP23:%.*]] = select i1 [[TMP22]], float [[TMP20]], float [[TMP21]]
+; AVX2-NEXT: [[TMP24:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 8), align 16
+; AVX2-NEXT: [[TMP25:%.*]] = fcmp fast ogt float [[TMP23]], [[TMP24]]
+; AVX2-NEXT: [[TMP26:%.*]] = select i1 [[TMP25]], float [[TMP23]], float [[TMP24]]
+; AVX2-NEXT: [[TMP27:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 9), align 4
+; AVX2-NEXT: [[TMP28:%.*]] = fcmp fast ogt float [[TMP26]], [[TMP27]]
+; AVX2-NEXT: [[TMP29:%.*]] = select i1 [[TMP28]], float [[TMP26]], float [[TMP27]]
+; AVX2-NEXT: [[TMP30:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 10), align 8
+; AVX2-NEXT: [[TMP31:%.*]] = fcmp fast ogt float [[TMP29]], [[TMP30]]
+; AVX2-NEXT: [[TMP32:%.*]] = select i1 [[TMP31]], float [[TMP29]], float [[TMP30]]
+; AVX2-NEXT: [[TMP33:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 11), align 4
+; AVX2-NEXT: [[TMP34:%.*]] = fcmp fast ogt float [[TMP32]], [[TMP33]]
+; AVX2-NEXT: [[TMP35:%.*]] = select i1 [[TMP34]], float [[TMP32]], float [[TMP33]]
+; AVX2-NEXT: [[TMP36:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 12), align 16
+; AVX2-NEXT: [[TMP37:%.*]] = fcmp fast ogt float [[TMP35]], [[TMP36]]
+; AVX2-NEXT: [[TMP38:%.*]] = select i1 [[TMP37]], float [[TMP35]], float [[TMP36]]
+; AVX2-NEXT: [[TMP39:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 13), align 4
+; AVX2-NEXT: [[TMP40:%.*]] = fcmp fast ogt float [[TMP38]], [[TMP39]]
+; AVX2-NEXT: [[TMP41:%.*]] = select i1 [[TMP40]], float [[TMP38]], float [[TMP39]]
+; AVX2-NEXT: [[TMP42:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 14), align 8
+; AVX2-NEXT: [[TMP43:%.*]] = fcmp fast ogt float [[TMP41]], [[TMP42]]
+; AVX2-NEXT: [[TMP44:%.*]] = select i1 [[TMP43]], float [[TMP41]], float [[TMP42]]
+; AVX2-NEXT: [[TMP45:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 15), align 4
+; AVX2-NEXT: [[TMP46:%.*]] = fcmp fast ogt float [[TMP44]], [[TMP45]]
+; AVX2-NEXT: [[TMP47:%.*]] = select i1 [[TMP46]], float [[TMP44]], float [[TMP45]]
+; AVX2-NEXT: ret float [[TMP47]]
+;
+; SKX-LABEL: @maxf16(
+; SKX-NEXT: [[TMP2:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 0), align 16
+; SKX-NEXT: [[TMP3:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 1), align 4
+; SKX-NEXT: [[TMP4:%.*]] = fcmp fast ogt float [[TMP2]], [[TMP3]]
+; SKX-NEXT: [[TMP5:%.*]] = select i1 [[TMP4]], float [[TMP2]], float [[TMP3]]
+; SKX-NEXT: [[TMP6:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 2), align 8
+; SKX-NEXT: [[TMP7:%.*]] = fcmp fast ogt float [[TMP5]], [[TMP6]]
+; SKX-NEXT: [[TMP8:%.*]] = select i1 [[TMP7]], float [[TMP5]], float [[TMP6]]
+; SKX-NEXT: [[TMP9:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 3), align 4
+; SKX-NEXT: [[TMP10:%.*]] = fcmp fast ogt float [[TMP8]], [[TMP9]]
+; SKX-NEXT: [[TMP11:%.*]] = select i1 [[TMP10]], float [[TMP8]], float [[TMP9]]
+; SKX-NEXT: [[TMP12:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 4), align 16
+; SKX-NEXT: [[TMP13:%.*]] = fcmp fast ogt float [[TMP11]], [[TMP12]]
+; SKX-NEXT: [[TMP14:%.*]] = select i1 [[TMP13]], float [[TMP11]], float [[TMP12]]
+; SKX-NEXT: [[TMP15:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 5), align 4
+; SKX-NEXT: [[TMP16:%.*]] = fcmp fast ogt float [[TMP14]], [[TMP15]]
+; SKX-NEXT: [[TMP17:%.*]] = select i1 [[TMP16]], float [[TMP14]], float [[TMP15]]
+; SKX-NEXT: [[TMP18:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 6), align 8
+; SKX-NEXT: [[TMP19:%.*]] = fcmp fast ogt float [[TMP17]], [[TMP18]]
+; SKX-NEXT: [[TMP20:%.*]] = select i1 [[TMP19]], float [[TMP17]], float [[TMP18]]
+; SKX-NEXT: [[TMP21:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 7), align 4
+; SKX-NEXT: [[TMP22:%.*]] = fcmp fast ogt float [[TMP20]], [[TMP21]]
+; SKX-NEXT: [[TMP23:%.*]] = select i1 [[TMP22]], float [[TMP20]], float [[TMP21]]
+; SKX-NEXT: [[TMP24:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 8), align 16
+; SKX-NEXT: [[TMP25:%.*]] = fcmp fast ogt float [[TMP23]], [[TMP24]]
+; SKX-NEXT: [[TMP26:%.*]] = select i1 [[TMP25]], float [[TMP23]], float [[TMP24]]
+; SKX-NEXT: [[TMP27:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 9), align 4
+; SKX-NEXT: [[TMP28:%.*]] = fcmp fast ogt float [[TMP26]], [[TMP27]]
+; SKX-NEXT: [[TMP29:%.*]] = select i1 [[TMP28]], float [[TMP26]], float [[TMP27]]
+; SKX-NEXT: [[TMP30:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 10), align 8
+; SKX-NEXT: [[TMP31:%.*]] = fcmp fast ogt float [[TMP29]], [[TMP30]]
+; SKX-NEXT: [[TMP32:%.*]] = select i1 [[TMP31]], float [[TMP29]], float [[TMP30]]
+; SKX-NEXT: [[TMP33:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 11), align 4
+; SKX-NEXT: [[TMP34:%.*]] = fcmp fast ogt float [[TMP32]], [[TMP33]]
+; SKX-NEXT: [[TMP35:%.*]] = select i1 [[TMP34]], float [[TMP32]], float [[TMP33]]
+; SKX-NEXT: [[TMP36:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 12), align 16
+; SKX-NEXT: [[TMP37:%.*]] = fcmp fast ogt float [[TMP35]], [[TMP36]]
+; SKX-NEXT: [[TMP38:%.*]] = select i1 [[TMP37]], float [[TMP35]], float [[TMP36]]
+; SKX-NEXT: [[TMP39:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 13), align 4
+; SKX-NEXT: [[TMP40:%.*]] = fcmp fast ogt float [[TMP38]], [[TMP39]]
+; SKX-NEXT: [[TMP41:%.*]] = select i1 [[TMP40]], float [[TMP38]], float [[TMP39]]
+; SKX-NEXT: [[TMP42:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 14), align 8
+; SKX-NEXT: [[TMP43:%.*]] = fcmp fast ogt float [[TMP41]], [[TMP42]]
+; SKX-NEXT: [[TMP44:%.*]] = select i1 [[TMP43]], float [[TMP41]], float [[TMP42]]
+; SKX-NEXT: [[TMP45:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 15), align 4
+; SKX-NEXT: [[TMP46:%.*]] = fcmp fast ogt float [[TMP44]], [[TMP45]]
+; SKX-NEXT: [[TMP47:%.*]] = select i1 [[TMP46]], float [[TMP44]], float [[TMP45]]
+; SKX-NEXT: ret float [[TMP47]]
+;
+ %2 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 0), align 16
+ %3 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 1), align 4
+ %4 = fcmp fast ogt float %2, %3
+ %5 = select i1 %4, float %2, float %3
+ %6 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 2), align 8
+ %7 = fcmp fast ogt float %5, %6
+ %8 = select i1 %7, float %5, float %6
+ %9 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 3), align 4
+ %10 = fcmp fast ogt float %8, %9
+ %11 = select i1 %10, float %8, float %9
+ %12 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 4), align 16
+ %13 = fcmp fast ogt float %11, %12
+ %14 = select i1 %13, float %11, float %12
+ %15 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 5), align 4
+ %16 = fcmp fast ogt float %14, %15
+ %17 = select i1 %16, float %14, float %15
+ %18 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 6), align 8
+ %19 = fcmp fast ogt float %17, %18
+ %20 = select i1 %19, float %17, float %18
+ %21 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 7), align 4
+ %22 = fcmp fast ogt float %20, %21
+ %23 = select i1 %22, float %20, float %21
+ %24 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 8), align 16
+ %25 = fcmp fast ogt float %23, %24
+ %26 = select i1 %25, float %23, float %24
+ %27 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 9), align 4
+ %28 = fcmp fast ogt float %26, %27
+ %29 = select i1 %28, float %26, float %27
+ %30 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 10), align 8
+ %31 = fcmp fast ogt float %29, %30
+ %32 = select i1 %31, float %29, float %30
+ %33 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 11), align 4
+ %34 = fcmp fast ogt float %32, %33
+ %35 = select i1 %34, float %32, float %33
+ %36 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 12), align 16
+ %37 = fcmp fast ogt float %35, %36
+ %38 = select i1 %37, float %35, float %36
+ %39 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 13), align 4
+ %40 = fcmp fast ogt float %38, %39
+ %41 = select i1 %40, float %38, float %39
+ %42 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 14), align 8
+ %43 = fcmp fast ogt float %41, %42
+ %44 = select i1 %43, float %41, float %42
+ %45 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 15), align 4
+ %46 = fcmp fast ogt float %44, %45
+ %47 = select i1 %46, float %44, float %45
+ ret float %47
+}
+
+define float @maxf32(float) {
+; CHECK-LABEL: @maxf32(
+; CHECK-NEXT: [[TMP2:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 0), align 16
+; CHECK-NEXT: [[TMP3:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 1), align 4
+; CHECK-NEXT: [[TMP4:%.*]] = fcmp fast ogt float [[TMP2]], [[TMP3]]
+; CHECK-NEXT: [[TMP5:%.*]] = select i1 [[TMP4]], float [[TMP2]], float [[TMP3]]
+; CHECK-NEXT: [[TMP6:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 2), align 8
+; CHECK-NEXT: [[TMP7:%.*]] = fcmp fast ogt float [[TMP5]], [[TMP6]]
+; CHECK-NEXT: [[TMP8:%.*]] = select i1 [[TMP7]], float [[TMP5]], float [[TMP6]]
+; CHECK-NEXT: [[TMP9:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 3), align 4
+; CHECK-NEXT: [[TMP10:%.*]] = fcmp fast ogt float [[TMP8]], [[TMP9]]
+; CHECK-NEXT: [[TMP11:%.*]] = select i1 [[TMP10]], float [[TMP8]], float [[TMP9]]
+; CHECK-NEXT: [[TMP12:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 4), align 16
+; CHECK-NEXT: [[TMP13:%.*]] = fcmp fast ogt float [[TMP11]], [[TMP12]]
+; CHECK-NEXT: [[TMP14:%.*]] = select i1 [[TMP13]], float [[TMP11]], float [[TMP12]]
+; CHECK-NEXT: [[TMP15:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 5), align 4
+; CHECK-NEXT: [[TMP16:%.*]] = fcmp fast ogt float [[TMP14]], [[TMP15]]
+; CHECK-NEXT: [[TMP17:%.*]] = select i1 [[TMP16]], float [[TMP14]], float [[TMP15]]
+; CHECK-NEXT: [[TMP18:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 6), align 8
+; CHECK-NEXT: [[TMP19:%.*]] = fcmp fast ogt float [[TMP17]], [[TMP18]]
+; CHECK-NEXT: [[TMP20:%.*]] = select i1 [[TMP19]], float [[TMP17]], float [[TMP18]]
+; CHECK-NEXT: [[TMP21:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 7), align 4
+; CHECK-NEXT: [[TMP22:%.*]] = fcmp fast ogt float [[TMP20]], [[TMP21]]
+; CHECK-NEXT: [[TMP23:%.*]] = select i1 [[TMP22]], float [[TMP20]], float [[TMP21]]
+; CHECK-NEXT: [[TMP24:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 8), align 16
+; CHECK-NEXT: [[TMP25:%.*]] = fcmp fast ogt float [[TMP23]], [[TMP24]]
+; CHECK-NEXT: [[TMP26:%.*]] = select i1 [[TMP25]], float [[TMP23]], float [[TMP24]]
+; CHECK-NEXT: [[TMP27:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 9), align 4
+; CHECK-NEXT: [[TMP28:%.*]] = fcmp fast ogt float [[TMP26]], [[TMP27]]
+; CHECK-NEXT: [[TMP29:%.*]] = select i1 [[TMP28]], float [[TMP26]], float [[TMP27]]
+; CHECK-NEXT: [[TMP30:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 10), align 8
+; CHECK-NEXT: [[TMP31:%.*]] = fcmp fast ogt float [[TMP29]], [[TMP30]]
+; CHECK-NEXT: [[TMP32:%.*]] = select i1 [[TMP31]], float [[TMP29]], float [[TMP30]]
+; CHECK-NEXT: [[TMP33:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 11), align 4
+; CHECK-NEXT: [[TMP34:%.*]] = fcmp fast ogt float [[TMP32]], [[TMP33]]
+; CHECK-NEXT: [[TMP35:%.*]] = select i1 [[TMP34]], float [[TMP32]], float [[TMP33]]
+; CHECK-NEXT: [[TMP36:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 12), align 16
+; CHECK-NEXT: [[TMP37:%.*]] = fcmp fast ogt float [[TMP35]], [[TMP36]]
+; CHECK-NEXT: [[TMP38:%.*]] = select i1 [[TMP37]], float [[TMP35]], float [[TMP36]]
+; CHECK-NEXT: [[TMP39:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 13), align 4
+; CHECK-NEXT: [[TMP40:%.*]] = fcmp fast ogt float [[TMP38]], [[TMP39]]
+; CHECK-NEXT: [[TMP41:%.*]] = select i1 [[TMP40]], float [[TMP38]], float [[TMP39]]
+; CHECK-NEXT: [[TMP42:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 14), align 8
+; CHECK-NEXT: [[TMP43:%.*]] = fcmp fast ogt float [[TMP41]], [[TMP42]]
+; CHECK-NEXT: [[TMP44:%.*]] = select i1 [[TMP43]], float [[TMP41]], float [[TMP42]]
+; CHECK-NEXT: [[TMP45:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 15), align 4
+; CHECK-NEXT: [[TMP46:%.*]] = fcmp fast ogt float [[TMP44]], [[TMP45]]
+; CHECK-NEXT: [[TMP47:%.*]] = select i1 [[TMP46]], float [[TMP44]], float [[TMP45]]
+; CHECK-NEXT: [[TMP48:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 16), align 16
+; CHECK-NEXT: [[TMP49:%.*]] = fcmp fast ogt float [[TMP47]], [[TMP48]]
+; CHECK-NEXT: [[TMP50:%.*]] = select i1 [[TMP49]], float [[TMP47]], float [[TMP48]]
+; CHECK-NEXT: [[TMP51:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 17), align 4
+; CHECK-NEXT: [[TMP52:%.*]] = fcmp fast ogt float [[TMP50]], [[TMP51]]
+; CHECK-NEXT: [[TMP53:%.*]] = select i1 [[TMP52]], float [[TMP50]], float [[TMP51]]
+; CHECK-NEXT: [[TMP54:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 18), align 8
+; CHECK-NEXT: [[TMP55:%.*]] = fcmp fast ogt float [[TMP53]], [[TMP54]]
+; CHECK-NEXT: [[TMP56:%.*]] = select i1 [[TMP55]], float [[TMP53]], float [[TMP54]]
+; CHECK-NEXT: [[TMP57:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 19), align 4
+; CHECK-NEXT: [[TMP58:%.*]] = fcmp fast ogt float [[TMP56]], [[TMP57]]
+; CHECK-NEXT: [[TMP59:%.*]] = select i1 [[TMP58]], float [[TMP56]], float [[TMP57]]
+; CHECK-NEXT: [[TMP60:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 20), align 16
+; CHECK-NEXT: [[TMP61:%.*]] = fcmp fast ogt float [[TMP59]], [[TMP60]]
+; CHECK-NEXT: [[TMP62:%.*]] = select i1 [[TMP61]], float [[TMP59]], float [[TMP60]]
+; CHECK-NEXT: [[TMP63:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 21), align 4
+; CHECK-NEXT: [[TMP64:%.*]] = fcmp fast ogt float [[TMP62]], [[TMP63]]
+; CHECK-NEXT: [[TMP65:%.*]] = select i1 [[TMP64]], float [[TMP62]], float [[TMP63]]
+; CHECK-NEXT: [[TMP66:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 22), align 8
+; CHECK-NEXT: [[TMP67:%.*]] = fcmp fast ogt float [[TMP65]], [[TMP66]]
+; CHECK-NEXT: [[TMP68:%.*]] = select i1 [[TMP67]], float [[TMP65]], float [[TMP66]]
+; CHECK-NEXT: [[TMP69:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 23), align 4
+; CHECK-NEXT: [[TMP70:%.*]] = fcmp fast ogt float [[TMP68]], [[TMP69]]
+; CHECK-NEXT: [[TMP71:%.*]] = select i1 [[TMP70]], float [[TMP68]], float [[TMP69]]
+; CHECK-NEXT: [[TMP72:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 24), align 16
+; CHECK-NEXT: [[TMP73:%.*]] = fcmp fast ogt float [[TMP71]], [[TMP72]]
+; CHECK-NEXT: [[TMP74:%.*]] = select i1 [[TMP73]], float [[TMP71]], float [[TMP72]]
+; CHECK-NEXT: [[TMP75:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 25), align 4
+; CHECK-NEXT: [[TMP76:%.*]] = fcmp fast ogt float [[TMP74]], [[TMP75]]
+; CHECK-NEXT: [[TMP77:%.*]] = select i1 [[TMP76]], float [[TMP74]], float [[TMP75]]
+; CHECK-NEXT: [[TMP78:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 26), align 8
+; CHECK-NEXT: [[TMP79:%.*]] = fcmp fast ogt float [[TMP77]], [[TMP78]]
+; CHECK-NEXT: [[TMP80:%.*]] = select i1 [[TMP79]], float [[TMP77]], float [[TMP78]]
+; CHECK-NEXT: [[TMP81:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 27), align 4
+; CHECK-NEXT: [[TMP82:%.*]] = fcmp fast ogt float [[TMP80]], [[TMP81]]
+; CHECK-NEXT: [[TMP83:%.*]] = select i1 [[TMP82]], float [[TMP80]], float [[TMP81]]
+; CHECK-NEXT: [[TMP84:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 28), align 16
+; CHECK-NEXT: [[TMP85:%.*]] = fcmp fast ogt float [[TMP83]], [[TMP84]]
+; CHECK-NEXT: [[TMP86:%.*]] = select i1 [[TMP85]], float [[TMP83]], float [[TMP84]]
+; CHECK-NEXT: [[TMP87:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 29), align 4
+; CHECK-NEXT: [[TMP88:%.*]] = fcmp fast ogt float [[TMP86]], [[TMP87]]
+; CHECK-NEXT: [[TMP89:%.*]] = select i1 [[TMP88]], float [[TMP86]], float [[TMP87]]
+; CHECK-NEXT: [[TMP90:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 30), align 8
+; CHECK-NEXT: [[TMP91:%.*]] = fcmp fast ogt float [[TMP89]], [[TMP90]]
+; CHECK-NEXT: [[TMP92:%.*]] = select i1 [[TMP91]], float [[TMP89]], float [[TMP90]]
+; CHECK-NEXT: [[TMP93:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 31), align 4
+; CHECK-NEXT: [[TMP94:%.*]] = fcmp fast ogt float [[TMP92]], [[TMP93]]
+; CHECK-NEXT: [[TMP95:%.*]] = select i1 [[TMP94]], float [[TMP92]], float [[TMP93]]
+; CHECK-NEXT: ret float [[TMP95]]
+;
+; AVX-LABEL: @maxf32(
+; AVX-NEXT: [[TMP2:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 0), align 16
+; AVX-NEXT: [[TMP3:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 1), align 4
+; AVX-NEXT: [[TMP4:%.*]] = fcmp fast ogt float [[TMP2]], [[TMP3]]
+; AVX-NEXT: [[TMP5:%.*]] = select i1 [[TMP4]], float [[TMP2]], float [[TMP3]]
+; AVX-NEXT: [[TMP6:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 2), align 8
+; AVX-NEXT: [[TMP7:%.*]] = fcmp fast ogt float [[TMP5]], [[TMP6]]
+; AVX-NEXT: [[TMP8:%.*]] = select i1 [[TMP7]], float [[TMP5]], float [[TMP6]]
+; AVX-NEXT: [[TMP9:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 3), align 4
+; AVX-NEXT: [[TMP10:%.*]] = fcmp fast ogt float [[TMP8]], [[TMP9]]
+; AVX-NEXT: [[TMP11:%.*]] = select i1 [[TMP10]], float [[TMP8]], float [[TMP9]]
+; AVX-NEXT: [[TMP12:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 4), align 16
+; AVX-NEXT: [[TMP13:%.*]] = fcmp fast ogt float [[TMP11]], [[TMP12]]
+; AVX-NEXT: [[TMP14:%.*]] = select i1 [[TMP13]], float [[TMP11]], float [[TMP12]]
+; AVX-NEXT: [[TMP15:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 5), align 4
+; AVX-NEXT: [[TMP16:%.*]] = fcmp fast ogt float [[TMP14]], [[TMP15]]
+; AVX-NEXT: [[TMP17:%.*]] = select i1 [[TMP16]], float [[TMP14]], float [[TMP15]]
+; AVX-NEXT: [[TMP18:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 6), align 8
+; AVX-NEXT: [[TMP19:%.*]] = fcmp fast ogt float [[TMP17]], [[TMP18]]
+; AVX-NEXT: [[TMP20:%.*]] = select i1 [[TMP19]], float [[TMP17]], float [[TMP18]]
+; AVX-NEXT: [[TMP21:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 7), align 4
+; AVX-NEXT: [[TMP22:%.*]] = fcmp fast ogt float [[TMP20]], [[TMP21]]
+; AVX-NEXT: [[TMP23:%.*]] = select i1 [[TMP22]], float [[TMP20]], float [[TMP21]]
+; AVX-NEXT: [[TMP24:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 8), align 16
+; AVX-NEXT: [[TMP25:%.*]] = fcmp fast ogt float [[TMP23]], [[TMP24]]
+; AVX-NEXT: [[TMP26:%.*]] = select i1 [[TMP25]], float [[TMP23]], float [[TMP24]]
+; AVX-NEXT: [[TMP27:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 9), align 4
+; AVX-NEXT: [[TMP28:%.*]] = fcmp fast ogt float [[TMP26]], [[TMP27]]
+; AVX-NEXT: [[TMP29:%.*]] = select i1 [[TMP28]], float [[TMP26]], float [[TMP27]]
+; AVX-NEXT: [[TMP30:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 10), align 8
+; AVX-NEXT: [[TMP31:%.*]] = fcmp fast ogt float [[TMP29]], [[TMP30]]
+; AVX-NEXT: [[TMP32:%.*]] = select i1 [[TMP31]], float [[TMP29]], float [[TMP30]]
+; AVX-NEXT: [[TMP33:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 11), align 4
+; AVX-NEXT: [[TMP34:%.*]] = fcmp fast ogt float [[TMP32]], [[TMP33]]
+; AVX-NEXT: [[TMP35:%.*]] = select i1 [[TMP34]], float [[TMP32]], float [[TMP33]]
+; AVX-NEXT: [[TMP36:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 12), align 16
+; AVX-NEXT: [[TMP37:%.*]] = fcmp fast ogt float [[TMP35]], [[TMP36]]
+; AVX-NEXT: [[TMP38:%.*]] = select i1 [[TMP37]], float [[TMP35]], float [[TMP36]]
+; AVX-NEXT: [[TMP39:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 13), align 4
+; AVX-NEXT: [[TMP40:%.*]] = fcmp fast ogt float [[TMP38]], [[TMP39]]
+; AVX-NEXT: [[TMP41:%.*]] = select i1 [[TMP40]], float [[TMP38]], float [[TMP39]]
+; AVX-NEXT: [[TMP42:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 14), align 8
+; AVX-NEXT: [[TMP43:%.*]] = fcmp fast ogt float [[TMP41]], [[TMP42]]
+; AVX-NEXT: [[TMP44:%.*]] = select i1 [[TMP43]], float [[TMP41]], float [[TMP42]]
+; AVX-NEXT: [[TMP45:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 15), align 4
+; AVX-NEXT: [[TMP46:%.*]] = fcmp fast ogt float [[TMP44]], [[TMP45]]
+; AVX-NEXT: [[TMP47:%.*]] = select i1 [[TMP46]], float [[TMP44]], float [[TMP45]]
+; AVX-NEXT: [[TMP48:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 16), align 16
+; AVX-NEXT: [[TMP49:%.*]] = fcmp fast ogt float [[TMP47]], [[TMP48]]
+; AVX-NEXT: [[TMP50:%.*]] = select i1 [[TMP49]], float [[TMP47]], float [[TMP48]]
+; AVX-NEXT: [[TMP51:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 17), align 4
+; AVX-NEXT: [[TMP52:%.*]] = fcmp fast ogt float [[TMP50]], [[TMP51]]
+; AVX-NEXT: [[TMP53:%.*]] = select i1 [[TMP52]], float [[TMP50]], float [[TMP51]]
+; AVX-NEXT: [[TMP54:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 18), align 8
+; AVX-NEXT: [[TMP55:%.*]] = fcmp fast ogt float [[TMP53]], [[TMP54]]
+; AVX-NEXT: [[TMP56:%.*]] = select i1 [[TMP55]], float [[TMP53]], float [[TMP54]]
+; AVX-NEXT: [[TMP57:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 19), align 4
+; AVX-NEXT: [[TMP58:%.*]] = fcmp fast ogt float [[TMP56]], [[TMP57]]
+; AVX-NEXT: [[TMP59:%.*]] = select i1 [[TMP58]], float [[TMP56]], float [[TMP57]]
+; AVX-NEXT: [[TMP60:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 20), align 16
+; AVX-NEXT: [[TMP61:%.*]] = fcmp fast ogt float [[TMP59]], [[TMP60]]
+; AVX-NEXT: [[TMP62:%.*]] = select i1 [[TMP61]], float [[TMP59]], float [[TMP60]]
+; AVX-NEXT: [[TMP63:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 21), align 4
+; AVX-NEXT: [[TMP64:%.*]] = fcmp fast ogt float [[TMP62]], [[TMP63]]
+; AVX-NEXT: [[TMP65:%.*]] = select i1 [[TMP64]], float [[TMP62]], float [[TMP63]]
+; AVX-NEXT: [[TMP66:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 22), align 8
+; AVX-NEXT: [[TMP67:%.*]] = fcmp fast ogt float [[TMP65]], [[TMP66]]
+; AVX-NEXT: [[TMP68:%.*]] = select i1 [[TMP67]], float [[TMP65]], float [[TMP66]]
+; AVX-NEXT: [[TMP69:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 23), align 4
+; AVX-NEXT: [[TMP70:%.*]] = fcmp fast ogt float [[TMP68]], [[TMP69]]
+; AVX-NEXT: [[TMP71:%.*]] = select i1 [[TMP70]], float [[TMP68]], float [[TMP69]]
+; AVX-NEXT: [[TMP72:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 24), align 16
+; AVX-NEXT: [[TMP73:%.*]] = fcmp fast ogt float [[TMP71]], [[TMP72]]
+; AVX-NEXT: [[TMP74:%.*]] = select i1 [[TMP73]], float [[TMP71]], float [[TMP72]]
+; AVX-NEXT: [[TMP75:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 25), align 4
+; AVX-NEXT: [[TMP76:%.*]] = fcmp fast ogt float [[TMP74]], [[TMP75]]
+; AVX-NEXT: [[TMP77:%.*]] = select i1 [[TMP76]], float [[TMP74]], float [[TMP75]]
+; AVX-NEXT: [[TMP78:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 26), align 8
+; AVX-NEXT: [[TMP79:%.*]] = fcmp fast ogt float [[TMP77]], [[TMP78]]
+; AVX-NEXT: [[TMP80:%.*]] = select i1 [[TMP79]], float [[TMP77]], float [[TMP78]]
+; AVX-NEXT: [[TMP81:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 27), align 4
+; AVX-NEXT: [[TMP82:%.*]] = fcmp fast ogt float [[TMP80]], [[TMP81]]
+; AVX-NEXT: [[TMP83:%.*]] = select i1 [[TMP82]], float [[TMP80]], float [[TMP81]]
+; AVX-NEXT: [[TMP84:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 28), align 16
+; AVX-NEXT: [[TMP85:%.*]] = fcmp fast ogt float [[TMP83]], [[TMP84]]
+; AVX-NEXT: [[TMP86:%.*]] = select i1 [[TMP85]], float [[TMP83]], float [[TMP84]]
+; AVX-NEXT: [[TMP87:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 29), align 4
+; AVX-NEXT: [[TMP88:%.*]] = fcmp fast ogt float [[TMP86]], [[TMP87]]
+; AVX-NEXT: [[TMP89:%.*]] = select i1 [[TMP88]], float [[TMP86]], float [[TMP87]]
+; AVX-NEXT: [[TMP90:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 30), align 8
+; AVX-NEXT: [[TMP91:%.*]] = fcmp fast ogt float [[TMP89]], [[TMP90]]
+; AVX-NEXT: [[TMP92:%.*]] = select i1 [[TMP91]], float [[TMP89]], float [[TMP90]]
+; AVX-NEXT: [[TMP93:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 31), align 4
+; AVX-NEXT: [[TMP94:%.*]] = fcmp fast ogt float [[TMP92]], [[TMP93]]
+; AVX-NEXT: [[TMP95:%.*]] = select i1 [[TMP94]], float [[TMP92]], float [[TMP93]]
+; AVX-NEXT: ret float [[TMP95]]
+;
+; AVX2-LABEL: @maxf32(
+; AVX2-NEXT: [[TMP2:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 0), align 16
+; AVX2-NEXT: [[TMP3:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 1), align 4
+; AVX2-NEXT: [[TMP4:%.*]] = fcmp fast ogt float [[TMP2]], [[TMP3]]
+; AVX2-NEXT: [[TMP5:%.*]] = select i1 [[TMP4]], float [[TMP2]], float [[TMP3]]
+; AVX2-NEXT: [[TMP6:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 2), align 8
+; AVX2-NEXT: [[TMP7:%.*]] = fcmp fast ogt float [[TMP5]], [[TMP6]]
+; AVX2-NEXT: [[TMP8:%.*]] = select i1 [[TMP7]], float [[TMP5]], float [[TMP6]]
+; AVX2-NEXT: [[TMP9:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 3), align 4
+; AVX2-NEXT: [[TMP10:%.*]] = fcmp fast ogt float [[TMP8]], [[TMP9]]
+; AVX2-NEXT: [[TMP11:%.*]] = select i1 [[TMP10]], float [[TMP8]], float [[TMP9]]
+; AVX2-NEXT: [[TMP12:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 4), align 16
+; AVX2-NEXT: [[TMP13:%.*]] = fcmp fast ogt float [[TMP11]], [[TMP12]]
+; AVX2-NEXT: [[TMP14:%.*]] = select i1 [[TMP13]], float [[TMP11]], float [[TMP12]]
+; AVX2-NEXT: [[TMP15:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 5), align 4
+; AVX2-NEXT: [[TMP16:%.*]] = fcmp fast ogt float [[TMP14]], [[TMP15]]
+; AVX2-NEXT: [[TMP17:%.*]] = select i1 [[TMP16]], float [[TMP14]], float [[TMP15]]
+; AVX2-NEXT: [[TMP18:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 6), align 8
+; AVX2-NEXT: [[TMP19:%.*]] = fcmp fast ogt float [[TMP17]], [[TMP18]]
+; AVX2-NEXT: [[TMP20:%.*]] = select i1 [[TMP19]], float [[TMP17]], float [[TMP18]]
+; AVX2-NEXT: [[TMP21:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 7), align 4
+; AVX2-NEXT: [[TMP22:%.*]] = fcmp fast ogt float [[TMP20]], [[TMP21]]
+; AVX2-NEXT: [[TMP23:%.*]] = select i1 [[TMP22]], float [[TMP20]], float [[TMP21]]
+; AVX2-NEXT: [[TMP24:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 8), align 16
+; AVX2-NEXT: [[TMP25:%.*]] = fcmp fast ogt float [[TMP23]], [[TMP24]]
+; AVX2-NEXT: [[TMP26:%.*]] = select i1 [[TMP25]], float [[TMP23]], float [[TMP24]]
+; AVX2-NEXT: [[TMP27:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 9), align 4
+; AVX2-NEXT: [[TMP28:%.*]] = fcmp fast ogt float [[TMP26]], [[TMP27]]
+; AVX2-NEXT: [[TMP29:%.*]] = select i1 [[TMP28]], float [[TMP26]], float [[TMP27]]
+; AVX2-NEXT: [[TMP30:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 10), align 8
+; AVX2-NEXT: [[TMP31:%.*]] = fcmp fast ogt float [[TMP29]], [[TMP30]]
+; AVX2-NEXT: [[TMP32:%.*]] = select i1 [[TMP31]], float [[TMP29]], float [[TMP30]]
+; AVX2-NEXT: [[TMP33:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 11), align 4
+; AVX2-NEXT: [[TMP34:%.*]] = fcmp fast ogt float [[TMP32]], [[TMP33]]
+; AVX2-NEXT: [[TMP35:%.*]] = select i1 [[TMP34]], float [[TMP32]], float [[TMP33]]
+; AVX2-NEXT: [[TMP36:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 12), align 16
+; AVX2-NEXT: [[TMP37:%.*]] = fcmp fast ogt float [[TMP35]], [[TMP36]]
+; AVX2-NEXT: [[TMP38:%.*]] = select i1 [[TMP37]], float [[TMP35]], float [[TMP36]]
+; AVX2-NEXT: [[TMP39:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 13), align 4
+; AVX2-NEXT: [[TMP40:%.*]] = fcmp fast ogt float [[TMP38]], [[TMP39]]
+; AVX2-NEXT: [[TMP41:%.*]] = select i1 [[TMP40]], float [[TMP38]], float [[TMP39]]
+; AVX2-NEXT: [[TMP42:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 14), align 8
+; AVX2-NEXT: [[TMP43:%.*]] = fcmp fast ogt float [[TMP41]], [[TMP42]]
+; AVX2-NEXT: [[TMP44:%.*]] = select i1 [[TMP43]], float [[TMP41]], float [[TMP42]]
+; AVX2-NEXT: [[TMP45:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 15), align 4
+; AVX2-NEXT: [[TMP46:%.*]] = fcmp fast ogt float [[TMP44]], [[TMP45]]
+; AVX2-NEXT: [[TMP47:%.*]] = select i1 [[TMP46]], float [[TMP44]], float [[TMP45]]
+; AVX2-NEXT: [[TMP48:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 16), align 16
+; AVX2-NEXT: [[TMP49:%.*]] = fcmp fast ogt float [[TMP47]], [[TMP48]]
+; AVX2-NEXT: [[TMP50:%.*]] = select i1 [[TMP49]], float [[TMP47]], float [[TMP48]]
+; AVX2-NEXT: [[TMP51:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 17), align 4
+; AVX2-NEXT: [[TMP52:%.*]] = fcmp fast ogt float [[TMP50]], [[TMP51]]
+; AVX2-NEXT: [[TMP53:%.*]] = select i1 [[TMP52]], float [[TMP50]], float [[TMP51]]
+; AVX2-NEXT: [[TMP54:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 18), align 8
+; AVX2-NEXT: [[TMP55:%.*]] = fcmp fast ogt float [[TMP53]], [[TMP54]]
+; AVX2-NEXT: [[TMP56:%.*]] = select i1 [[TMP55]], float [[TMP53]], float [[TMP54]]
+; AVX2-NEXT: [[TMP57:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 19), align 4
+; AVX2-NEXT: [[TMP58:%.*]] = fcmp fast ogt float [[TMP56]], [[TMP57]]
+; AVX2-NEXT: [[TMP59:%.*]] = select i1 [[TMP58]], float [[TMP56]], float [[TMP57]]
+; AVX2-NEXT: [[TMP60:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 20), align 16
+; AVX2-NEXT: [[TMP61:%.*]] = fcmp fast ogt float [[TMP59]], [[TMP60]]
+; AVX2-NEXT: [[TMP62:%.*]] = select i1 [[TMP61]], float [[TMP59]], float [[TMP60]]
+; AVX2-NEXT: [[TMP63:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 21), align 4
+; AVX2-NEXT: [[TMP64:%.*]] = fcmp fast ogt float [[TMP62]], [[TMP63]]
+; AVX2-NEXT: [[TMP65:%.*]] = select i1 [[TMP64]], float [[TMP62]], float [[TMP63]]
+; AVX2-NEXT: [[TMP66:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 22), align 8
+; AVX2-NEXT: [[TMP67:%.*]] = fcmp fast ogt float [[TMP65]], [[TMP66]]
+; AVX2-NEXT: [[TMP68:%.*]] = select i1 [[TMP67]], float [[TMP65]], float [[TMP66]]
+; AVX2-NEXT: [[TMP69:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 23), align 4
+; AVX2-NEXT: [[TMP70:%.*]] = fcmp fast ogt float [[TMP68]], [[TMP69]]
+; AVX2-NEXT: [[TMP71:%.*]] = select i1 [[TMP70]], float [[TMP68]], float [[TMP69]]
+; AVX2-NEXT: [[TMP72:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 24), align 16
+; AVX2-NEXT: [[TMP73:%.*]] = fcmp fast ogt float [[TMP71]], [[TMP72]]
+; AVX2-NEXT: [[TMP74:%.*]] = select i1 [[TMP73]], float [[TMP71]], float [[TMP72]]
+; AVX2-NEXT: [[TMP75:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 25), align 4
+; AVX2-NEXT: [[TMP76:%.*]] = fcmp fast ogt float [[TMP74]], [[TMP75]]
+; AVX2-NEXT: [[TMP77:%.*]] = select i1 [[TMP76]], float [[TMP74]], float [[TMP75]]
+; AVX2-NEXT: [[TMP78:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 26), align 8
+; AVX2-NEXT: [[TMP79:%.*]] = fcmp fast ogt float [[TMP77]], [[TMP78]]
+; AVX2-NEXT: [[TMP80:%.*]] = select i1 [[TMP79]], float [[TMP77]], float [[TMP78]]
+; AVX2-NEXT: [[TMP81:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 27), align 4
+; AVX2-NEXT: [[TMP82:%.*]] = fcmp fast ogt float [[TMP80]], [[TMP81]]
+; AVX2-NEXT: [[TMP83:%.*]] = select i1 [[TMP82]], float [[TMP80]], float [[TMP81]]
+; AVX2-NEXT: [[TMP84:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 28), align 16
+; AVX2-NEXT: [[TMP85:%.*]] = fcmp fast ogt float [[TMP83]], [[TMP84]]
+; AVX2-NEXT: [[TMP86:%.*]] = select i1 [[TMP85]], float [[TMP83]], float [[TMP84]]
+; AVX2-NEXT: [[TMP87:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 29), align 4
+; AVX2-NEXT: [[TMP88:%.*]] = fcmp fast ogt float [[TMP86]], [[TMP87]]
+; AVX2-NEXT: [[TMP89:%.*]] = select i1 [[TMP88]], float [[TMP86]], float [[TMP87]]
+; AVX2-NEXT: [[TMP90:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 30), align 8
+; AVX2-NEXT: [[TMP91:%.*]] = fcmp fast ogt float [[TMP89]], [[TMP90]]
+; AVX2-NEXT: [[TMP92:%.*]] = select i1 [[TMP91]], float [[TMP89]], float [[TMP90]]
+; AVX2-NEXT: [[TMP93:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 31), align 4
+; AVX2-NEXT: [[TMP94:%.*]] = fcmp fast ogt float [[TMP92]], [[TMP93]]
+; AVX2-NEXT: [[TMP95:%.*]] = select i1 [[TMP94]], float [[TMP92]], float [[TMP93]]
+; AVX2-NEXT: ret float [[TMP95]]
+;
+; SKX-LABEL: @maxf32(
+; SKX-NEXT: [[TMP2:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 0), align 16
+; SKX-NEXT: [[TMP3:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 1), align 4
+; SKX-NEXT: [[TMP4:%.*]] = fcmp fast ogt float [[TMP2]], [[TMP3]]
+; SKX-NEXT: [[TMP5:%.*]] = select i1 [[TMP4]], float [[TMP2]], float [[TMP3]]
+; SKX-NEXT: [[TMP6:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 2), align 8
+; SKX-NEXT: [[TMP7:%.*]] = fcmp fast ogt float [[TMP5]], [[TMP6]]
+; SKX-NEXT: [[TMP8:%.*]] = select i1 [[TMP7]], float [[TMP5]], float [[TMP6]]
+; SKX-NEXT: [[TMP9:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 3), align 4
+; SKX-NEXT: [[TMP10:%.*]] = fcmp fast ogt float [[TMP8]], [[TMP9]]
+; SKX-NEXT: [[TMP11:%.*]] = select i1 [[TMP10]], float [[TMP8]], float [[TMP9]]
+; SKX-NEXT: [[TMP12:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 4), align 16
+; SKX-NEXT: [[TMP13:%.*]] = fcmp fast ogt float [[TMP11]], [[TMP12]]
+; SKX-NEXT: [[TMP14:%.*]] = select i1 [[TMP13]], float [[TMP11]], float [[TMP12]]
+; SKX-NEXT: [[TMP15:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 5), align 4
+; SKX-NEXT: [[TMP16:%.*]] = fcmp fast ogt float [[TMP14]], [[TMP15]]
+; SKX-NEXT: [[TMP17:%.*]] = select i1 [[TMP16]], float [[TMP14]], float [[TMP15]]
+; SKX-NEXT: [[TMP18:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 6), align 8
+; SKX-NEXT: [[TMP19:%.*]] = fcmp fast ogt float [[TMP17]], [[TMP18]]
+; SKX-NEXT: [[TMP20:%.*]] = select i1 [[TMP19]], float [[TMP17]], float [[TMP18]]
+; SKX-NEXT: [[TMP21:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 7), align 4
+; SKX-NEXT: [[TMP22:%.*]] = fcmp fast ogt float [[TMP20]], [[TMP21]]
+; SKX-NEXT: [[TMP23:%.*]] = select i1 [[TMP22]], float [[TMP20]], float [[TMP21]]
+; SKX-NEXT: [[TMP24:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 8), align 16
+; SKX-NEXT: [[TMP25:%.*]] = fcmp fast ogt float [[TMP23]], [[TMP24]]
+; SKX-NEXT: [[TMP26:%.*]] = select i1 [[TMP25]], float [[TMP23]], float [[TMP24]]
+; SKX-NEXT: [[TMP27:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 9), align 4
+; SKX-NEXT: [[TMP28:%.*]] = fcmp fast ogt float [[TMP26]], [[TMP27]]
+; SKX-NEXT: [[TMP29:%.*]] = select i1 [[TMP28]], float [[TMP26]], float [[TMP27]]
+; SKX-NEXT: [[TMP30:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 10), align 8
+; SKX-NEXT: [[TMP31:%.*]] = fcmp fast ogt float [[TMP29]], [[TMP30]]
+; SKX-NEXT: [[TMP32:%.*]] = select i1 [[TMP31]], float [[TMP29]], float [[TMP30]]
+; SKX-NEXT: [[TMP33:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 11), align 4
+; SKX-NEXT: [[TMP34:%.*]] = fcmp fast ogt float [[TMP32]], [[TMP33]]
+; SKX-NEXT: [[TMP35:%.*]] = select i1 [[TMP34]], float [[TMP32]], float [[TMP33]]
+; SKX-NEXT: [[TMP36:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 12), align 16
+; SKX-NEXT: [[TMP37:%.*]] = fcmp fast ogt float [[TMP35]], [[TMP36]]
+; SKX-NEXT: [[TMP38:%.*]] = select i1 [[TMP37]], float [[TMP35]], float [[TMP36]]
+; SKX-NEXT: [[TMP39:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 13), align 4
+; SKX-NEXT: [[TMP40:%.*]] = fcmp fast ogt float [[TMP38]], [[TMP39]]
+; SKX-NEXT: [[TMP41:%.*]] = select i1 [[TMP40]], float [[TMP38]], float [[TMP39]]
+; SKX-NEXT: [[TMP42:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 14), align 8
+; SKX-NEXT: [[TMP43:%.*]] = fcmp fast ogt float [[TMP41]], [[TMP42]]
+; SKX-NEXT: [[TMP44:%.*]] = select i1 [[TMP43]], float [[TMP41]], float [[TMP42]]
+; SKX-NEXT: [[TMP45:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 15), align 4
+; SKX-NEXT: [[TMP46:%.*]] = fcmp fast ogt float [[TMP44]], [[TMP45]]
+; SKX-NEXT: [[TMP47:%.*]] = select i1 [[TMP46]], float [[TMP44]], float [[TMP45]]
+; SKX-NEXT: [[TMP48:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 16), align 16
+; SKX-NEXT: [[TMP49:%.*]] = fcmp fast ogt float [[TMP47]], [[TMP48]]
+; SKX-NEXT: [[TMP50:%.*]] = select i1 [[TMP49]], float [[TMP47]], float [[TMP48]]
+; SKX-NEXT: [[TMP51:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 17), align 4
+; SKX-NEXT: [[TMP52:%.*]] = fcmp fast ogt float [[TMP50]], [[TMP51]]
+; SKX-NEXT: [[TMP53:%.*]] = select i1 [[TMP52]], float [[TMP50]], float [[TMP51]]
+; SKX-NEXT: [[TMP54:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 18), align 8
+; SKX-NEXT: [[TMP55:%.*]] = fcmp fast ogt float [[TMP53]], [[TMP54]]
+; SKX-NEXT: [[TMP56:%.*]] = select i1 [[TMP55]], float [[TMP53]], float [[TMP54]]
+; SKX-NEXT: [[TMP57:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 19), align 4
+; SKX-NEXT: [[TMP58:%.*]] = fcmp fast ogt float [[TMP56]], [[TMP57]]
+; SKX-NEXT: [[TMP59:%.*]] = select i1 [[TMP58]], float [[TMP56]], float [[TMP57]]
+; SKX-NEXT: [[TMP60:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 20), align 16
+; SKX-NEXT: [[TMP61:%.*]] = fcmp fast ogt float [[TMP59]], [[TMP60]]
+; SKX-NEXT: [[TMP62:%.*]] = select i1 [[TMP61]], float [[TMP59]], float [[TMP60]]
+; SKX-NEXT: [[TMP63:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 21), align 4
+; SKX-NEXT: [[TMP64:%.*]] = fcmp fast ogt float [[TMP62]], [[TMP63]]
+; SKX-NEXT: [[TMP65:%.*]] = select i1 [[TMP64]], float [[TMP62]], float [[TMP63]]
+; SKX-NEXT: [[TMP66:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 22), align 8
+; SKX-NEXT: [[TMP67:%.*]] = fcmp fast ogt float [[TMP65]], [[TMP66]]
+; SKX-NEXT: [[TMP68:%.*]] = select i1 [[TMP67]], float [[TMP65]], float [[TMP66]]
+; SKX-NEXT: [[TMP69:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 23), align 4
+; SKX-NEXT: [[TMP70:%.*]] = fcmp fast ogt float [[TMP68]], [[TMP69]]
+; SKX-NEXT: [[TMP71:%.*]] = select i1 [[TMP70]], float [[TMP68]], float [[TMP69]]
+; SKX-NEXT: [[TMP72:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 24), align 16
+; SKX-NEXT: [[TMP73:%.*]] = fcmp fast ogt float [[TMP71]], [[TMP72]]
+; SKX-NEXT: [[TMP74:%.*]] = select i1 [[TMP73]], float [[TMP71]], float [[TMP72]]
+; SKX-NEXT: [[TMP75:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 25), align 4
+; SKX-NEXT: [[TMP76:%.*]] = fcmp fast ogt float [[TMP74]], [[TMP75]]
+; SKX-NEXT: [[TMP77:%.*]] = select i1 [[TMP76]], float [[TMP74]], float [[TMP75]]
+; SKX-NEXT: [[TMP78:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 26), align 8
+; SKX-NEXT: [[TMP79:%.*]] = fcmp fast ogt float [[TMP77]], [[TMP78]]
+; SKX-NEXT: [[TMP80:%.*]] = select i1 [[TMP79]], float [[TMP77]], float [[TMP78]]
+; SKX-NEXT: [[TMP81:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 27), align 4
+; SKX-NEXT: [[TMP82:%.*]] = fcmp fast ogt float [[TMP80]], [[TMP81]]
+; SKX-NEXT: [[TMP83:%.*]] = select i1 [[TMP82]], float [[TMP80]], float [[TMP81]]
+; SKX-NEXT: [[TMP84:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 28), align 16
+; SKX-NEXT: [[TMP85:%.*]] = fcmp fast ogt float [[TMP83]], [[TMP84]]
+; SKX-NEXT: [[TMP86:%.*]] = select i1 [[TMP85]], float [[TMP83]], float [[TMP84]]
+; SKX-NEXT: [[TMP87:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 29), align 4
+; SKX-NEXT: [[TMP88:%.*]] = fcmp fast ogt float [[TMP86]], [[TMP87]]
+; SKX-NEXT: [[TMP89:%.*]] = select i1 [[TMP88]], float [[TMP86]], float [[TMP87]]
+; SKX-NEXT: [[TMP90:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 30), align 8
+; SKX-NEXT: [[TMP91:%.*]] = fcmp fast ogt float [[TMP89]], [[TMP90]]
+; SKX-NEXT: [[TMP92:%.*]] = select i1 [[TMP91]], float [[TMP89]], float [[TMP90]]
+; SKX-NEXT: [[TMP93:%.*]] = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 31), align 4
+; SKX-NEXT: [[TMP94:%.*]] = fcmp fast ogt float [[TMP92]], [[TMP93]]
+; SKX-NEXT: [[TMP95:%.*]] = select i1 [[TMP94]], float [[TMP92]], float [[TMP93]]
+; SKX-NEXT: ret float [[TMP95]]
+;
+ %2 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 0), align 16
+ %3 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 1), align 4
+ %4 = fcmp fast ogt float %2, %3
+ %5 = select i1 %4, float %2, float %3
+ %6 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 2), align 8
+ %7 = fcmp fast ogt float %5, %6
+ %8 = select i1 %7, float %5, float %6
+ %9 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 3), align 4
+ %10 = fcmp fast ogt float %8, %9
+ %11 = select i1 %10, float %8, float %9
+ %12 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 4), align 16
+ %13 = fcmp fast ogt float %11, %12
+ %14 = select i1 %13, float %11, float %12
+ %15 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 5), align 4
+ %16 = fcmp fast ogt float %14, %15
+ %17 = select i1 %16, float %14, float %15
+ %18 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 6), align 8
+ %19 = fcmp fast ogt float %17, %18
+ %20 = select i1 %19, float %17, float %18
+ %21 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 7), align 4
+ %22 = fcmp fast ogt float %20, %21
+ %23 = select i1 %22, float %20, float %21
+ %24 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 8), align 16
+ %25 = fcmp fast ogt float %23, %24
+ %26 = select i1 %25, float %23, float %24
+ %27 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 9), align 4
+ %28 = fcmp fast ogt float %26, %27
+ %29 = select i1 %28, float %26, float %27
+ %30 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 10), align 8
+ %31 = fcmp fast ogt float %29, %30
+ %32 = select i1 %31, float %29, float %30
+ %33 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 11), align 4
+ %34 = fcmp fast ogt float %32, %33
+ %35 = select i1 %34, float %32, float %33
+ %36 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 12), align 16
+ %37 = fcmp fast ogt float %35, %36
+ %38 = select i1 %37, float %35, float %36
+ %39 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 13), align 4
+ %40 = fcmp fast ogt float %38, %39
+ %41 = select i1 %40, float %38, float %39
+ %42 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 14), align 8
+ %43 = fcmp fast ogt float %41, %42
+ %44 = select i1 %43, float %41, float %42
+ %45 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 15), align 4
+ %46 = fcmp fast ogt float %44, %45
+ %47 = select i1 %46, float %44, float %45
+ %48 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 16), align 16
+ %49 = fcmp fast ogt float %47, %48
+ %50 = select i1 %49, float %47, float %48
+ %51 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 17), align 4
+ %52 = fcmp fast ogt float %50, %51
+ %53 = select i1 %52, float %50, float %51
+ %54 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 18), align 8
+ %55 = fcmp fast ogt float %53, %54
+ %56 = select i1 %55, float %53, float %54
+ %57 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 19), align 4
+ %58 = fcmp fast ogt float %56, %57
+ %59 = select i1 %58, float %56, float %57
+ %60 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 20), align 16
+ %61 = fcmp fast ogt float %59, %60
+ %62 = select i1 %61, float %59, float %60
+ %63 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 21), align 4
+ %64 = fcmp fast ogt float %62, %63
+ %65 = select i1 %64, float %62, float %63
+ %66 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 22), align 8
+ %67 = fcmp fast ogt float %65, %66
+ %68 = select i1 %67, float %65, float %66
+ %69 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 23), align 4
+ %70 = fcmp fast ogt float %68, %69
+ %71 = select i1 %70, float %68, float %69
+ %72 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 24), align 16
+ %73 = fcmp fast ogt float %71, %72
+ %74 = select i1 %73, float %71, float %72
+ %75 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 25), align 4
+ %76 = fcmp fast ogt float %74, %75
+ %77 = select i1 %76, float %74, float %75
+ %78 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 26), align 8
+ %79 = fcmp fast ogt float %77, %78
+ %80 = select i1 %79, float %77, float %78
+ %81 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 27), align 4
+ %82 = fcmp fast ogt float %80, %81
+ %83 = select i1 %82, float %80, float %81
+ %84 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 28), align 16
+ %85 = fcmp fast ogt float %83, %84
+ %86 = select i1 %85, float %83, float %84
+ %87 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 29), align 4
+ %88 = fcmp fast ogt float %86, %87
+ %89 = select i1 %88, float %86, float %87
+ %90 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 30), align 8
+ %91 = fcmp fast ogt float %89, %90
+ %92 = select i1 %91, float %89, float %90
+ %93 = load float, float* getelementptr inbounds ([32 x float], [32 x float]* @arr1, i64 0, i64 31), align 4
+ %94 = fcmp fast ogt float %92, %93
+ %95 = select i1 %94, float %92, float %93
+ ret float %95
+}
+
More information about the llvm-commits
mailing list