[x86] add tests for psubus; NFC

Author: rotateright

llvm/test/CodeGen/X86/psubus.ll

@@ -9,6 +9,8 @@
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw,+avx512vl,+fast-variable-crosslane-shuffle,+fast-variable-perlane-shuffle | FileCheck %s --check-prefixes=AVX,AVX512
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw,+avx512vl,+fast-variable-perlane-shuffle | FileCheck %s --check-prefixes=AVX,AVX512
 
+declare <4 x i32> @llvm.usub.sat.v4i32(<4 x i32>, <4 x i32>)
+
 define <8 x i16> @test1(<8 x i16> %x) nounwind {
 ; SSE-LABEL: test1:
 ; SSE:       # %bb.0: # %vector.ph
@@ -90,7 +92,7 @@ define <16 x i8> @ashr_xor_and_commute_uses(<16 x i8> %x, <16 x i8>* %p1, <16 x
   ret <16 x i8> %res
 }
 
-define <4 x i32> @ashr_xor_and_custom(<4 x i32> %x, <4 x i32>* %p1, <4 x i32>* %p2) nounwind {
+define <4 x i32> @ashr_xor_and_custom(<4 x i32> %x) nounwind {
 ; SSE-LABEL: ashr_xor_and_custom:
 ; SSE:       # %bb.0:
 ; SSE-NEXT:    movdqa %xmm0, %xmm1
@@ -125,6 +127,48 @@ define <4 x i32> @ashr_xor_and_custom(<4 x i32> %x, <4 x i32>* %p1, <4 x i32>* %
   ret <4 x i32> %res
 }
 
+define <4 x i32> @usubsat_custom(<4 x i32> %x) nounwind {
+; SSE2OR3-LABEL: usubsat_custom:
+; SSE2OR3:       # %bb.0:
+; SSE2OR3-NEXT:    movdqa {{.*#+}} xmm1 = [2147483648,2147483648,2147483648,2147483648]
+; SSE2OR3-NEXT:    pxor %xmm0, %xmm1
+; SSE2OR3-NEXT:    pxor %xmm2, %xmm2
+; SSE2OR3-NEXT:    pcmpgtd %xmm2, %xmm1
+; SSE2OR3-NEXT:    psubd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
+; SSE2OR3-NEXT:    pand %xmm1, %xmm0
+; SSE2OR3-NEXT:    retq
+;
+; SSE41-LABEL: usubsat_custom:
+; SSE41:       # %bb.0:
+; SSE41-NEXT:    movdqa {{.*#+}} xmm1 = <2147483648,2147483648,2147483648,u>
+; SSE41-NEXT:    pmaxud %xmm1, %xmm0
+; SSE41-NEXT:    psubd %xmm1, %xmm0
+; SSE41-NEXT:    retq
+;
+; AVX1-LABEL: usubsat_custom:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = <2147483648,2147483648,2147483648,u>
+; AVX1-NEXT:    vpmaxud %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpsubd %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: usubsat_custom:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vpbroadcastd {{.*#+}} xmm1 = [2147483648,2147483648,2147483648,2147483648]
+; AVX2-NEXT:    vpmaxud %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vpsubd %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    retq
+;
+; AVX512-LABEL: usubsat_custom:
+; AVX512:       # %bb.0:
+; AVX512-NEXT:    vpbroadcastd {{.*#+}} xmm1 = [2147483648,2147483648,2147483648,2147483648]
+; AVX512-NEXT:    vpmaxud %xmm1, %xmm0, %xmm0
+; AVX512-NEXT:    vpsubd %xmm1, %xmm0, %xmm0
+; AVX512-NEXT:    retq
+  %res = call <4 x i32> @llvm.usub.sat.v4i32(<4 x i32> %x, <4 x i32> <i32 2147483648, i32 2147483648, i32 2147483648, i32 undef>)
+  ret <4 x i32> %res
+}
+
 define <8 x i16> @test2(<8 x i16> %x) nounwind {
 ; SSE-LABEL: test2:
 ; SSE:       # %bb.0: # %vector.ph
@@ -302,6 +346,47 @@ vector.ph:
   ret <16 x i16> %res
 }
 
+define <16 x i16> @ashr_xor_and_v16i16(<16 x i16> %x) nounwind {
+; SSE-LABEL: ashr_xor_and_v16i16:
+; SSE:       # %bb.0:
+; SSE-NEXT:    movdqa %xmm1, %xmm2
+; SSE-NEXT:    psraw $15, %xmm2
+; SSE-NEXT:    movdqa %xmm0, %xmm3
+; SSE-NEXT:    psraw $15, %xmm3
+; SSE-NEXT:    pxor {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1
+; SSE-NEXT:    pand %xmm2, %xmm1
+; SSE-NEXT:    pxor {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
+; SSE-NEXT:    pand %xmm3, %xmm0
+; SSE-NEXT:    retq
+;
+; AVX1-LABEL: ashr_xor_and_v16i16:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vpsraw $15, %xmm0, %xmm1
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
+; AVX1-NEXT:    vpsraw $15, %xmm2, %xmm2
+; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm1, %ymm1
+; AVX1-NEXT:    vxorps {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %ymm0, %ymm0
+; AVX1-NEXT:    vandps %ymm0, %ymm1, %ymm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: ashr_xor_and_v16i16:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vpsraw $15, %ymm0, %ymm1
+; AVX2-NEXT:    vpxor {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %ymm0, %ymm0
+; AVX2-NEXT:    vpand %ymm0, %ymm1, %ymm0
+; AVX2-NEXT:    retq
+;
+; AVX512-LABEL: ashr_xor_and_v16i16:
+; AVX512:       # %bb.0:
+; AVX512-NEXT:    vpsraw $15, %ymm0, %ymm1
+; AVX512-NEXT:    vpternlogq $72, {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %ymm1, %ymm0
+; AVX512-NEXT:    retq
+  %signsplat = ashr <16 x i16> %x, <i16 15, i16 15, i16 15, i16 15, i16 15, i16 15, i16 15, i16 15, i16 15, i16 15, i16 15, i16 15, i16 15, i16 15, i16 15, i16 15>
+  %flipsign = xor <16 x i16> %x, <i16 undef, i16 32768, i16 32768, i16 32768, i16 32768, i16 32768, i16 32768, i16 32768, i16 32768, i16 32768, i16 32768, i16 32768, i16 32768, i16 32768, i16 32768, i16 32768>
+  %res = and <16 x i16> %signsplat, %flipsign
+  ret <16 x i16> %res
+}
+
 define <16 x i16> @test8(<16 x i16> %x) nounwind {
 ; SSE-LABEL: test8:
 ; SSE:       # %bb.0: # %vector.ph