llvm-project/llvm/test/CodeGen/X86/vec_minmax_match.ll

253 lines
9.4 KiB
LLVM
Raw Normal View History

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s
; These are actually tests of ValueTracking, and so may have test coverage in InstCombine or other
; IR opt passes, but ValueTracking also affects the backend via SelectionDAGBuilder::visitSelect().
define <4 x i32> @smin_vec1(<4 x i32> %x) {
; CHECK-LABEL: smin_vec1:
; CHECK: # %bb.0:
; CHECK-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
; CHECK-NEXT: vpxor %xmm1, %xmm0, %xmm0
; CHECK-NEXT: vpminsd %xmm1, %xmm0, %xmm0
; CHECK-NEXT: retq
%not_x = xor <4 x i32> %x, <i32 -1, i32 -1, i32 -1, i32 -1>
%cmp = icmp sgt <4 x i32> %x, zeroinitializer
%sel = select <4 x i1> %cmp, <4 x i32> %not_x, <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>
ret <4 x i32> %sel
}
define <4 x i32> @smin_vec2(<4 x i32> %x) {
; CHECK-LABEL: smin_vec2:
; CHECK: # %bb.0:
; CHECK-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
; CHECK-NEXT: vpxor %xmm1, %xmm0, %xmm0
; CHECK-NEXT: vpminsd %xmm1, %xmm0, %xmm0
; CHECK-NEXT: retq
%not_x = xor <4 x i32> %x, <i32 -1, i32 -1, i32 -1, i32 -1>
%cmp = icmp slt <4 x i32> %x, zeroinitializer
%sel = select <4 x i1> %cmp, <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>, <4 x i32> %not_x
ret <4 x i32> %sel
}
; Z = X -nsw Y
; (X >s Y) ? 0 : Z ==> (Z >s 0) ? 0 : Z ==> SMIN(Z, 0)
define <4 x i32> @smin_vec3(<4 x i32> %x, <4 x i32> %y) {
; CHECK-LABEL: smin_vec3:
; CHECK: # %bb.0:
; CHECK-NEXT: vpsubd %xmm1, %xmm0, %xmm0
; CHECK-NEXT: vpxor %xmm1, %xmm1, %xmm1
; CHECK-NEXT: vpminsd %xmm1, %xmm0, %xmm0
; CHECK-NEXT: retq
%sub = sub nsw <4 x i32> %x, %y
%cmp = icmp sgt <4 x i32> %x, %y
%sel = select <4 x i1> %cmp, <4 x i32> zeroinitializer, <4 x i32> %sub
ret <4 x i32> %sel
}
; Z = X -nsw Y
; (X <s Y) ? Z : 0 ==> (Z <s 0) ? Z : 0 ==> SMIN(Z, 0)
define <4 x i32> @smin_vec4(<4 x i32> %x, <4 x i32> %y) {
; CHECK-LABEL: smin_vec4:
; CHECK: # %bb.0:
; CHECK-NEXT: vpsubd %xmm1, %xmm0, %xmm0
; CHECK-NEXT: vpxor %xmm1, %xmm1, %xmm1
; CHECK-NEXT: vpminsd %xmm1, %xmm0, %xmm0
; CHECK-NEXT: retq
%sub = sub nsw <4 x i32> %x, %y
%cmp = icmp slt <4 x i32> %x, %y
%sel = select <4 x i1> %cmp, <4 x i32> %sub, <4 x i32> zeroinitializer
ret <4 x i32> %sel
}
define <4 x i32> @smax_vec1(<4 x i32> %x) {
; CHECK-LABEL: smax_vec1:
; CHECK: # %bb.0:
; CHECK-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
; CHECK-NEXT: vpxor %xmm1, %xmm0, %xmm0
; CHECK-NEXT: vpmaxsd %xmm1, %xmm0, %xmm0
; CHECK-NEXT: retq
%not_x = xor <4 x i32> %x, <i32 -1, i32 -1, i32 -1, i32 -1>
%cmp = icmp slt <4 x i32> %x, zeroinitializer
%sel = select <4 x i1> %cmp, <4 x i32> %not_x, <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>
ret <4 x i32> %sel
}
define <4 x i32> @smax_vec2(<4 x i32> %x) {
; CHECK-LABEL: smax_vec2:
; CHECK: # %bb.0:
; CHECK-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
; CHECK-NEXT: vpxor %xmm1, %xmm0, %xmm0
; CHECK-NEXT: vpmaxsd %xmm1, %xmm0, %xmm0
; CHECK-NEXT: retq
%not_x = xor <4 x i32> %x, <i32 -1, i32 -1, i32 -1, i32 -1>
%cmp = icmp sgt <4 x i32> %x, zeroinitializer
%sel = select <4 x i1> %cmp, <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>, <4 x i32> %not_x
ret <4 x i32> %sel
}
; Z = X -nsw Y
; (X <s Y) ? 0 : Z ==> (Z <s 0) ? 0 : Z ==> SMAX(Z, 0)
define <4 x i32> @smax_vec3(<4 x i32> %x, <4 x i32> %y) {
; CHECK-LABEL: smax_vec3:
; CHECK: # %bb.0:
; CHECK-NEXT: vpsubd %xmm1, %xmm0, %xmm0
; CHECK-NEXT: vpxor %xmm1, %xmm1, %xmm1
; CHECK-NEXT: vpmaxsd %xmm1, %xmm0, %xmm0
; CHECK-NEXT: retq
%sub = sub nsw <4 x i32> %x, %y
%cmp = icmp slt <4 x i32> %x, %y
%sel = select <4 x i1> %cmp, <4 x i32> zeroinitializer, <4 x i32> %sub
ret <4 x i32> %sel
}
; Z = X -nsw Y
; (X >s Y) ? Z : 0 ==> (Z >s 0) ? Z : 0 ==> SMAX(Z, 0)
define <4 x i32> @smax_vec4(<4 x i32> %x, <4 x i32> %y) {
; CHECK-LABEL: smax_vec4:
; CHECK: # %bb.0:
; CHECK-NEXT: vpsubd %xmm1, %xmm0, %xmm0
; CHECK-NEXT: vpxor %xmm1, %xmm1, %xmm1
; CHECK-NEXT: vpmaxsd %xmm1, %xmm0, %xmm0
; CHECK-NEXT: retq
%sub = sub nsw <4 x i32> %x, %y
%cmp = icmp sgt <4 x i32> %x, %y
%sel = select <4 x i1> %cmp, <4 x i32> %sub, <4 x i32> zeroinitializer
ret <4 x i32> %sel
}
define <4 x i32> @umax_vec1(<4 x i32> %x) {
; CHECK-LABEL: umax_vec1:
; CHECK: # %bb.0:
; CHECK-NEXT: vpmaxud {{.*}}(%rip), %xmm0, %xmm0
; CHECK-NEXT: retq
%cmp = icmp slt <4 x i32> %x, zeroinitializer
%sel = select <4 x i1> %cmp, <4 x i32> %x, <4 x i32> <i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647>
ret <4 x i32> %sel
}
define <4 x i32> @umax_vec2(<4 x i32> %x) {
; CHECK-LABEL: umax_vec2:
; CHECK: # %bb.0:
; CHECK-NEXT: vpmaxud {{.*}}(%rip), %xmm0, %xmm0
; CHECK-NEXT: retq
%cmp = icmp sgt <4 x i32> %x, <i32 -1, i32 -1, i32 -1, i32 -1>
%sel = select <4 x i1> %cmp, <4 x i32> <i32 2147483648, i32 2147483648, i32 2147483648, i32 2147483648>, <4 x i32> %x
ret <4 x i32> %sel
}
define <4 x i32> @umin_vec1(<4 x i32> %x) {
; CHECK-LABEL: umin_vec1:
; CHECK: # %bb.0:
; CHECK-NEXT: vpminud {{.*}}(%rip), %xmm0, %xmm0
; CHECK-NEXT: retq
%cmp = icmp slt <4 x i32> %x, zeroinitializer
%sel = select <4 x i1> %cmp, <4 x i32> <i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647>, <4 x i32> %x
ret <4 x i32> %sel
}
define <4 x i32> @umin_vec2(<4 x i32> %x) {
; CHECK-LABEL: umin_vec2:
; CHECK: # %bb.0:
; CHECK-NEXT: vpminud {{.*}}(%rip), %xmm0, %xmm0
; CHECK-NEXT: retq
%cmp = icmp sgt <4 x i32> %x, <i32 -1, i32 -1, i32 -1, i32 -1>
%sel = select <4 x i1> %cmp, <4 x i32> %x, <4 x i32> <i32 2147483648, i32 2147483648, i32 2147483648, i32 2147483648>
ret <4 x i32> %sel
}
; The next 4 tests are value clamping with constants:
; https://llvm.org/bugs/show_bug.cgi?id=31693
; (X <s C1) ? C1 : SMIN(X, C2) ==> SMAX(SMIN(X, C2), C1)
define <4 x i32> @clamp_signed1(<4 x i32> %x) {
; CHECK-LABEL: clamp_signed1:
; CHECK: # %bb.0:
[ValueTracking] recognize variations of 'clamp' to improve codegen (PR31693) By enhancing value tracking, we allow an existing min/max canonicalization to kick in and improve codegen for several targets that have min/max instructions. Unfortunately, recognizing min/max in value tracking may cause us to hit a hack in InstCombiner::visitICmpInst() more often: http://lists.llvm.org/pipermail/llvm-dev/2017-January/109340.html ...but I'm hoping we can remove that soon. Correctness proofs based on Alive: Name: smaxmin Pre: C1 < C2 %cmp2 = icmp slt i8 %x, C2 %min = select i1 %cmp2, i8 %x, i8 C2 %cmp3 = icmp slt i8 %x, C1 %r = select i1 %cmp3, i8 C1, i8 %min => %cmp2 = icmp slt i8 %x, C2 %min = select i1 %cmp2, i8 %x, i8 C2 %cmp1 = icmp sgt i8 %min, C1 %r = select i1 %cmp1, i8 %min, i8 C1 Name: sminmax Pre: C1 > C2 %cmp2 = icmp sgt i8 %x, C2 %max = select i1 %cmp2, i8 %x, i8 C2 %cmp3 = icmp sgt i8 %x, C1 %r = select i1 %cmp3, i8 C1, i8 %max => %cmp2 = icmp sgt i8 %x, C2 %max = select i1 %cmp2, i8 %x, i8 C2 %cmp1 = icmp slt i8 %max, C1 %r = select i1 %cmp1, i8 %max, i8 C1 ---------------------------------------- Optimization: smaxmin Done: 1 Optimization is correct! ---------------------------------------- Optimization: sminmax Done: 1 Optimization is correct! Name: umaxmin Pre: C1 u< C2 %cmp2 = icmp ult i8 %x, C2 %min = select i1 %cmp2, i8 %x, i8 C2 %cmp3 = icmp ult i8 %x, C1 %r = select i1 %cmp3, i8 C1, i8 %min => %cmp2 = icmp ult i8 %x, C2 %min = select i1 %cmp2, i8 %x, i8 C2 %cmp1 = icmp ugt i8 %min, C1 %r = select i1 %cmp1, i8 %min, i8 C1 Name: uminmax Pre: C1 u> C2 %cmp2 = icmp ugt i8 %x, C2 %max = select i1 %cmp2, i8 %x, i8 C2 %cmp3 = icmp ugt i8 %x, C1 %r = select i1 %cmp3, i8 C1, i8 %max => %cmp2 = icmp ugt i8 %x, C2 %max = select i1 %cmp2, i8 %x, i8 C2 %cmp1 = icmp ult i8 %max, C1 %r = select i1 %cmp1, i8 %max, i8 C1 ---------------------------------------- Optimization: umaxmin Done: 1 Optimization is correct! ---------------------------------------- Optimization: uminmax Done: 1 Optimization is correct! llvm-svn: 292660
2017-01-21 06:18:47 +08:00
; CHECK-NEXT: vpminsd {{.*}}(%rip), %xmm0, %xmm0
; CHECK-NEXT: vpmaxsd {{.*}}(%rip), %xmm0, %xmm0
; CHECK-NEXT: retq
%cmp2 = icmp slt <4 x i32> %x, <i32 255, i32 255, i32 255, i32 255>
%min = select <4 x i1> %cmp2, <4 x i32> %x, <4 x i32><i32 255, i32 255, i32 255, i32 255>
%cmp1 = icmp slt <4 x i32> %x, <i32 15, i32 15, i32 15, i32 15>
%r = select <4 x i1> %cmp1, <4 x i32><i32 15, i32 15, i32 15, i32 15>, <4 x i32> %min
ret <4 x i32> %r
}
; (X >s C1) ? C1 : SMAX(X, C2) ==> SMIN(SMAX(X, C2), C1)
define <4 x i32> @clamp_signed2(<4 x i32> %x) {
; CHECK-LABEL: clamp_signed2:
; CHECK: # %bb.0:
[ValueTracking] recognize variations of 'clamp' to improve codegen (PR31693) By enhancing value tracking, we allow an existing min/max canonicalization to kick in and improve codegen for several targets that have min/max instructions. Unfortunately, recognizing min/max in value tracking may cause us to hit a hack in InstCombiner::visitICmpInst() more often: http://lists.llvm.org/pipermail/llvm-dev/2017-January/109340.html ...but I'm hoping we can remove that soon. Correctness proofs based on Alive: Name: smaxmin Pre: C1 < C2 %cmp2 = icmp slt i8 %x, C2 %min = select i1 %cmp2, i8 %x, i8 C2 %cmp3 = icmp slt i8 %x, C1 %r = select i1 %cmp3, i8 C1, i8 %min => %cmp2 = icmp slt i8 %x, C2 %min = select i1 %cmp2, i8 %x, i8 C2 %cmp1 = icmp sgt i8 %min, C1 %r = select i1 %cmp1, i8 %min, i8 C1 Name: sminmax Pre: C1 > C2 %cmp2 = icmp sgt i8 %x, C2 %max = select i1 %cmp2, i8 %x, i8 C2 %cmp3 = icmp sgt i8 %x, C1 %r = select i1 %cmp3, i8 C1, i8 %max => %cmp2 = icmp sgt i8 %x, C2 %max = select i1 %cmp2, i8 %x, i8 C2 %cmp1 = icmp slt i8 %max, C1 %r = select i1 %cmp1, i8 %max, i8 C1 ---------------------------------------- Optimization: smaxmin Done: 1 Optimization is correct! ---------------------------------------- Optimization: sminmax Done: 1 Optimization is correct! Name: umaxmin Pre: C1 u< C2 %cmp2 = icmp ult i8 %x, C2 %min = select i1 %cmp2, i8 %x, i8 C2 %cmp3 = icmp ult i8 %x, C1 %r = select i1 %cmp3, i8 C1, i8 %min => %cmp2 = icmp ult i8 %x, C2 %min = select i1 %cmp2, i8 %x, i8 C2 %cmp1 = icmp ugt i8 %min, C1 %r = select i1 %cmp1, i8 %min, i8 C1 Name: uminmax Pre: C1 u> C2 %cmp2 = icmp ugt i8 %x, C2 %max = select i1 %cmp2, i8 %x, i8 C2 %cmp3 = icmp ugt i8 %x, C1 %r = select i1 %cmp3, i8 C1, i8 %max => %cmp2 = icmp ugt i8 %x, C2 %max = select i1 %cmp2, i8 %x, i8 C2 %cmp1 = icmp ult i8 %max, C1 %r = select i1 %cmp1, i8 %max, i8 C1 ---------------------------------------- Optimization: umaxmin Done: 1 Optimization is correct! ---------------------------------------- Optimization: uminmax Done: 1 Optimization is correct! llvm-svn: 292660
2017-01-21 06:18:47 +08:00
; CHECK-NEXT: vpmaxsd {{.*}}(%rip), %xmm0, %xmm0
; CHECK-NEXT: vpminsd {{.*}}(%rip), %xmm0, %xmm0
; CHECK-NEXT: retq
%cmp2 = icmp sgt <4 x i32> %x, <i32 15, i32 15, i32 15, i32 15>
%max = select <4 x i1> %cmp2, <4 x i32> %x, <4 x i32><i32 15, i32 15, i32 15, i32 15>
%cmp1 = icmp sgt <4 x i32> %x, <i32 255, i32 255, i32 255, i32 255>
%r = select <4 x i1> %cmp1, <4 x i32><i32 255, i32 255, i32 255, i32 255>, <4 x i32> %max
ret <4 x i32> %r
}
; (X <u C1) ? C1 : UMIN(X, C2) ==> UMAX(UMIN(X, C2), C1)
define <4 x i32> @clamp_unsigned1(<4 x i32> %x) {
; CHECK-LABEL: clamp_unsigned1:
; CHECK: # %bb.0:
[ValueTracking] recognize variations of 'clamp' to improve codegen (PR31693) By enhancing value tracking, we allow an existing min/max canonicalization to kick in and improve codegen for several targets that have min/max instructions. Unfortunately, recognizing min/max in value tracking may cause us to hit a hack in InstCombiner::visitICmpInst() more often: http://lists.llvm.org/pipermail/llvm-dev/2017-January/109340.html ...but I'm hoping we can remove that soon. Correctness proofs based on Alive: Name: smaxmin Pre: C1 < C2 %cmp2 = icmp slt i8 %x, C2 %min = select i1 %cmp2, i8 %x, i8 C2 %cmp3 = icmp slt i8 %x, C1 %r = select i1 %cmp3, i8 C1, i8 %min => %cmp2 = icmp slt i8 %x, C2 %min = select i1 %cmp2, i8 %x, i8 C2 %cmp1 = icmp sgt i8 %min, C1 %r = select i1 %cmp1, i8 %min, i8 C1 Name: sminmax Pre: C1 > C2 %cmp2 = icmp sgt i8 %x, C2 %max = select i1 %cmp2, i8 %x, i8 C2 %cmp3 = icmp sgt i8 %x, C1 %r = select i1 %cmp3, i8 C1, i8 %max => %cmp2 = icmp sgt i8 %x, C2 %max = select i1 %cmp2, i8 %x, i8 C2 %cmp1 = icmp slt i8 %max, C1 %r = select i1 %cmp1, i8 %max, i8 C1 ---------------------------------------- Optimization: smaxmin Done: 1 Optimization is correct! ---------------------------------------- Optimization: sminmax Done: 1 Optimization is correct! Name: umaxmin Pre: C1 u< C2 %cmp2 = icmp ult i8 %x, C2 %min = select i1 %cmp2, i8 %x, i8 C2 %cmp3 = icmp ult i8 %x, C1 %r = select i1 %cmp3, i8 C1, i8 %min => %cmp2 = icmp ult i8 %x, C2 %min = select i1 %cmp2, i8 %x, i8 C2 %cmp1 = icmp ugt i8 %min, C1 %r = select i1 %cmp1, i8 %min, i8 C1 Name: uminmax Pre: C1 u> C2 %cmp2 = icmp ugt i8 %x, C2 %max = select i1 %cmp2, i8 %x, i8 C2 %cmp3 = icmp ugt i8 %x, C1 %r = select i1 %cmp3, i8 C1, i8 %max => %cmp2 = icmp ugt i8 %x, C2 %max = select i1 %cmp2, i8 %x, i8 C2 %cmp1 = icmp ult i8 %max, C1 %r = select i1 %cmp1, i8 %max, i8 C1 ---------------------------------------- Optimization: umaxmin Done: 1 Optimization is correct! ---------------------------------------- Optimization: uminmax Done: 1 Optimization is correct! llvm-svn: 292660
2017-01-21 06:18:47 +08:00
; CHECK-NEXT: vpminud {{.*}}(%rip), %xmm0, %xmm0
; CHECK-NEXT: vpmaxud {{.*}}(%rip), %xmm0, %xmm0
; CHECK-NEXT: retq
%cmp2 = icmp ult <4 x i32> %x, <i32 255, i32 255, i32 255, i32 255>
%min = select <4 x i1> %cmp2, <4 x i32> %x, <4 x i32><i32 255, i32 255, i32 255, i32 255>
%cmp1 = icmp ult <4 x i32> %x, <i32 15, i32 15, i32 15, i32 15>
%r = select <4 x i1> %cmp1, <4 x i32><i32 15, i32 15, i32 15, i32 15>, <4 x i32> %min
ret <4 x i32> %r
}
; (X >u C1) ? C1 : UMAX(X, C2) ==> UMIN(UMAX(X, C2), C1)
define <4 x i32> @clamp_unsigned2(<4 x i32> %x) {
; CHECK-LABEL: clamp_unsigned2:
; CHECK: # %bb.0:
[ValueTracking] recognize variations of 'clamp' to improve codegen (PR31693) By enhancing value tracking, we allow an existing min/max canonicalization to kick in and improve codegen for several targets that have min/max instructions. Unfortunately, recognizing min/max in value tracking may cause us to hit a hack in InstCombiner::visitICmpInst() more often: http://lists.llvm.org/pipermail/llvm-dev/2017-January/109340.html ...but I'm hoping we can remove that soon. Correctness proofs based on Alive: Name: smaxmin Pre: C1 < C2 %cmp2 = icmp slt i8 %x, C2 %min = select i1 %cmp2, i8 %x, i8 C2 %cmp3 = icmp slt i8 %x, C1 %r = select i1 %cmp3, i8 C1, i8 %min => %cmp2 = icmp slt i8 %x, C2 %min = select i1 %cmp2, i8 %x, i8 C2 %cmp1 = icmp sgt i8 %min, C1 %r = select i1 %cmp1, i8 %min, i8 C1 Name: sminmax Pre: C1 > C2 %cmp2 = icmp sgt i8 %x, C2 %max = select i1 %cmp2, i8 %x, i8 C2 %cmp3 = icmp sgt i8 %x, C1 %r = select i1 %cmp3, i8 C1, i8 %max => %cmp2 = icmp sgt i8 %x, C2 %max = select i1 %cmp2, i8 %x, i8 C2 %cmp1 = icmp slt i8 %max, C1 %r = select i1 %cmp1, i8 %max, i8 C1 ---------------------------------------- Optimization: smaxmin Done: 1 Optimization is correct! ---------------------------------------- Optimization: sminmax Done: 1 Optimization is correct! Name: umaxmin Pre: C1 u< C2 %cmp2 = icmp ult i8 %x, C2 %min = select i1 %cmp2, i8 %x, i8 C2 %cmp3 = icmp ult i8 %x, C1 %r = select i1 %cmp3, i8 C1, i8 %min => %cmp2 = icmp ult i8 %x, C2 %min = select i1 %cmp2, i8 %x, i8 C2 %cmp1 = icmp ugt i8 %min, C1 %r = select i1 %cmp1, i8 %min, i8 C1 Name: uminmax Pre: C1 u> C2 %cmp2 = icmp ugt i8 %x, C2 %max = select i1 %cmp2, i8 %x, i8 C2 %cmp3 = icmp ugt i8 %x, C1 %r = select i1 %cmp3, i8 C1, i8 %max => %cmp2 = icmp ugt i8 %x, C2 %max = select i1 %cmp2, i8 %x, i8 C2 %cmp1 = icmp ult i8 %max, C1 %r = select i1 %cmp1, i8 %max, i8 C1 ---------------------------------------- Optimization: umaxmin Done: 1 Optimization is correct! ---------------------------------------- Optimization: uminmax Done: 1 Optimization is correct! llvm-svn: 292660
2017-01-21 06:18:47 +08:00
; CHECK-NEXT: vpmaxud {{.*}}(%rip), %xmm0, %xmm0
; CHECK-NEXT: vpminud {{.*}}(%rip), %xmm0, %xmm0
; CHECK-NEXT: retq
%cmp2 = icmp ugt <4 x i32> %x, <i32 15, i32 15, i32 15, i32 15>
%max = select <4 x i1> %cmp2, <4 x i32> %x, <4 x i32><i32 15, i32 15, i32 15, i32 15>
%cmp1 = icmp ugt <4 x i32> %x, <i32 255, i32 255, i32 255, i32 255>
%r = select <4 x i1> %cmp1, <4 x i32><i32 255, i32 255, i32 255, i32 255>, <4 x i32> %max
ret <4 x i32> %r
}
define <4 x i32> @wrong_pred_for_smin_with_not(<4 x i32> %x) {
; CHECK-LABEL: wrong_pred_for_smin_with_not:
; CHECK: # %bb.0:
; CHECK-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
; CHECK-NEXT: vpxor %xmm1, %xmm0, %xmm2
; CHECK-NEXT: vpminud {{.*}}(%rip), %xmm0, %xmm3
; CHECK-NEXT: vpcmpeqd %xmm3, %xmm0, %xmm0
; CHECK-NEXT: vpxor %xmm1, %xmm0, %xmm0
; CHECK-NEXT: vmovaps {{.*#+}} xmm1 = [4294967291,4294967291,4294967291,4294967291]
; CHECK-NEXT: vblendvps %xmm0, %xmm2, %xmm1, %xmm0
; CHECK-NEXT: retq
%not_x = xor <4 x i32> %x, <i32 -1, i32 -1, i32 -1, i32 -1>
%cmp = icmp ugt <4 x i32> %x, <i32 4, i32 4, i32 4, i32 4>
%sel = select <4 x i1> %cmp, <4 x i32> %not_x, <4 x i32> <i32 -5, i32 -5, i32 -5, i32 -5>
ret <4 x i32> %sel
}
define <4 x i32> @wrong_pred_for_smin_with_subnsw(<4 x i32> %x, <4 x i32> %y) {
; CHECK-LABEL: wrong_pred_for_smin_with_subnsw:
; CHECK: # %bb.0:
; CHECK-NEXT: vpsubd %xmm1, %xmm0, %xmm2
; CHECK-NEXT: vpminud %xmm1, %xmm0, %xmm1
; CHECK-NEXT: vpcmpeqd %xmm1, %xmm0, %xmm0
; CHECK-NEXT: vpand %xmm2, %xmm0, %xmm0
; CHECK-NEXT: retq
%sub = sub nsw <4 x i32> %x, %y
%cmp = icmp ugt <4 x i32> %x, %y
%sel = select <4 x i1> %cmp, <4 x i32> zeroinitializer, <4 x i32> %sub
ret <4 x i32> %sel
}