diff --git a/llvm/test/CodeGen/X86/vector-popcnt-128.ll b/llvm/test/CodeGen/X86/vector-popcnt-128.ll
index c91b2e111b66..2faba4aec906 100644
--- a/llvm/test/CodeGen/X86/vector-popcnt-128.ll
+++ b/llvm/test/CodeGen/X86/vector-popcnt-128.ll
@@ -681,6 +681,2685 @@ define <16 x i8> @foldv16i8() nounwind {
   ret <16 x i8> %out
 }
 
+define <2 x i64> @ult_2_v2i64(<2 x i64> %0) {
+; SSE2-LABEL: ult_2_v2i64:
+; SSE2:       # %bb.0:
+; SSE2-NEXT:    movdqa %xmm0, %xmm1
+; SSE2-NEXT:    psrlw $1, %xmm1
+; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE2-NEXT:    psubb %xmm1, %xmm0
+; SSE2-NEXT:    movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
+; SSE2-NEXT:    movdqa %xmm0, %xmm2
+; SSE2-NEXT:    pand %xmm1, %xmm2
+; SSE2-NEXT:    psrlw $2, %xmm0
+; SSE2-NEXT:    pand %xmm1, %xmm0
+; SSE2-NEXT:    paddb %xmm2, %xmm0
+; SSE2-NEXT:    movdqa %xmm0, %xmm1
+; SSE2-NEXT:    psrlw $4, %xmm1
+; SSE2-NEXT:    paddb %xmm0, %xmm1
+; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE2-NEXT:    pxor %xmm0, %xmm0
+; SSE2-NEXT:    psadbw %xmm1, %xmm0
+; SSE2-NEXT:    por {{.*}}(%rip), %xmm0
+; SSE2-NEXT:    movdqa {{.*#+}} xmm1 = [2147483650,2147483650]
+; SSE2-NEXT:    movdqa %xmm1, %xmm2
+; SSE2-NEXT:    pcmpgtd %xmm0, %xmm2
+; SSE2-NEXT:    pshufd {{.*#+}} xmm3 = xmm2[0,0,2,2]
+; SSE2-NEXT:    pcmpeqd %xmm1, %xmm0
+; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[1,1,3,3]
+; SSE2-NEXT:    pand %xmm3, %xmm1
+; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm2[1,1,3,3]
+; SSE2-NEXT:    por %xmm1, %xmm0
+; SSE2-NEXT:    retq
+;
+; SSE3-LABEL: ult_2_v2i64:
+; SSE3:       # %bb.0:
+; SSE3-NEXT:    movdqa %xmm0, %xmm1
+; SSE3-NEXT:    psrlw $1, %xmm1
+; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE3-NEXT:    psubb %xmm1, %xmm0
+; SSE3-NEXT:    movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
+; SSE3-NEXT:    movdqa %xmm0, %xmm2
+; SSE3-NEXT:    pand %xmm1, %xmm2
+; SSE3-NEXT:    psrlw $2, %xmm0
+; SSE3-NEXT:    pand %xmm1, %xmm0
+; SSE3-NEXT:    paddb %xmm2, %xmm0
+; SSE3-NEXT:    movdqa %xmm0, %xmm1
+; SSE3-NEXT:    psrlw $4, %xmm1
+; SSE3-NEXT:    paddb %xmm0, %xmm1
+; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE3-NEXT:    pxor %xmm0, %xmm0
+; SSE3-NEXT:    psadbw %xmm1, %xmm0
+; SSE3-NEXT:    por {{.*}}(%rip), %xmm0
+; SSE3-NEXT:    movdqa {{.*#+}} xmm1 = [2147483650,2147483650]
+; SSE3-NEXT:    movdqa %xmm1, %xmm2
+; SSE3-NEXT:    pcmpgtd %xmm0, %xmm2
+; SSE3-NEXT:    pshufd {{.*#+}} xmm3 = xmm2[0,0,2,2]
+; SSE3-NEXT:    pcmpeqd %xmm1, %xmm0
+; SSE3-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[1,1,3,3]
+; SSE3-NEXT:    pand %xmm3, %xmm1
+; SSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm2[1,1,3,3]
+; SSE3-NEXT:    por %xmm1, %xmm0
+; SSE3-NEXT:    retq
+;
+; SSSE3-LABEL: ult_2_v2i64:
+; SSSE3:       # %bb.0:
+; SSSE3-NEXT:    movdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; SSSE3-NEXT:    movdqa %xmm0, %xmm2
+; SSSE3-NEXT:    pand %xmm1, %xmm2
+; SSSE3-NEXT:    movdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; SSSE3-NEXT:    movdqa %xmm3, %xmm4
+; SSSE3-NEXT:    pshufb %xmm2, %xmm4
+; SSSE3-NEXT:    psrlw $4, %xmm0
+; SSSE3-NEXT:    pand %xmm1, %xmm0
+; SSSE3-NEXT:    pshufb %xmm0, %xmm3
+; SSSE3-NEXT:    paddb %xmm4, %xmm3
+; SSSE3-NEXT:    pxor %xmm0, %xmm0
+; SSSE3-NEXT:    psadbw %xmm3, %xmm0
+; SSSE3-NEXT:    por {{.*}}(%rip), %xmm0
+; SSSE3-NEXT:    movdqa {{.*#+}} xmm1 = [2147483650,2147483650]
+; SSSE3-NEXT:    movdqa %xmm1, %xmm2
+; SSSE3-NEXT:    pcmpgtd %xmm0, %xmm2
+; SSSE3-NEXT:    pshufd {{.*#+}} xmm3 = xmm2[0,0,2,2]
+; SSSE3-NEXT:    pcmpeqd %xmm1, %xmm0
+; SSSE3-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[1,1,3,3]
+; SSSE3-NEXT:    pand %xmm3, %xmm1
+; SSSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm2[1,1,3,3]
+; SSSE3-NEXT:    por %xmm1, %xmm0
+; SSSE3-NEXT:    retq
+;
+; SSE41-LABEL: ult_2_v2i64:
+; SSE41:       # %bb.0:
+; SSE41-NEXT:    movdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; SSE41-NEXT:    movdqa %xmm0, %xmm2
+; SSE41-NEXT:    pand %xmm1, %xmm2
+; SSE41-NEXT:    movdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; SSE41-NEXT:    movdqa %xmm3, %xmm4
+; SSE41-NEXT:    pshufb %xmm2, %xmm4
+; SSE41-NEXT:    psrlw $4, %xmm0
+; SSE41-NEXT:    pand %xmm1, %xmm0
+; SSE41-NEXT:    pshufb %xmm0, %xmm3
+; SSE41-NEXT:    paddb %xmm4, %xmm3
+; SSE41-NEXT:    pxor %xmm0, %xmm0
+; SSE41-NEXT:    psadbw %xmm3, %xmm0
+; SSE41-NEXT:    por {{.*}}(%rip), %xmm0
+; SSE41-NEXT:    movdqa {{.*#+}} xmm1 = [2147483650,2147483650]
+; SSE41-NEXT:    movdqa %xmm1, %xmm2
+; SSE41-NEXT:    pcmpgtd %xmm0, %xmm2
+; SSE41-NEXT:    pshufd {{.*#+}} xmm3 = xmm2[0,0,2,2]
+; SSE41-NEXT:    pcmpeqd %xmm1, %xmm0
+; SSE41-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[1,1,3,3]
+; SSE41-NEXT:    pand %xmm3, %xmm1
+; SSE41-NEXT:    pshufd {{.*#+}} xmm0 = xmm2[1,1,3,3]
+; SSE41-NEXT:    por %xmm1, %xmm0
+; SSE41-NEXT:    retq
+;
+; AVX1-LABEL: ult_2_v2i64:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX1-NEXT:    vpaddb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX1-NEXT:    vpsadbw %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [2,2]
+; AVX1-NEXT:    vpcmpgtq %xmm0, %xmm1, %xmm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: ult_2_v2i64:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX2-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX2-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX2-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX2-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX2-NEXT:    vpaddb %xmm2, %xmm0, %xmm0
+; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX2-NEXT:    vpsadbw %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm1 = [2,2]
+; AVX2-NEXT:    vpcmpgtq %xmm0, %xmm1, %xmm0
+; AVX2-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: ult_2_v2i64:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpopcntq %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    vmovdqa {{.*#+}} xmm1 = [2,2]
+; AVX512VPOPCNTDQ-NEXT:    vpcmpgtq %xmm0, %xmm1, %xmm0
+; AVX512VPOPCNTDQ-NEXT:    vzeroupper
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; AVX512VPOPCNTDQVL-LABEL: ult_2_v2i64:
+; AVX512VPOPCNTDQVL:       # %bb.0:
+; AVX512VPOPCNTDQVL-NEXT:    vpopcntq %xmm0, %xmm0
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpltuq {{.*}}(%rip), %xmm0, %k1
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpeqd %xmm0, %xmm0, %xmm0
+; AVX512VPOPCNTDQVL-NEXT:    vmovdqa64 %xmm0, %xmm0 {%k1} {z}
+; AVX512VPOPCNTDQVL-NEXT:    retq
+;
+; BITALG_NOVLX-LABEL: ult_2_v2i64:
+; BITALG_NOVLX:       # %bb.0:
+; BITALG_NOVLX-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
+; BITALG_NOVLX-NEXT:    vpopcntb %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG_NOVLX-NEXT:    vpsadbw %xmm1, %xmm0, %xmm0
+; BITALG_NOVLX-NEXT:    vmovdqa {{.*#+}} xmm1 = [2,2]
+; BITALG_NOVLX-NEXT:    vpcmpgtq %xmm0, %xmm1, %xmm0
+; BITALG_NOVLX-NEXT:    vzeroupper
+; BITALG_NOVLX-NEXT:    retq
+;
+; BITALG-LABEL: ult_2_v2i64:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntb %xmm0, %xmm0
+; BITALG-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG-NEXT:    vpsadbw %xmm1, %xmm0, %xmm0
+; BITALG-NEXT:    vpcmpltuq {{.*}}(%rip), %xmm0, %k1
+; BITALG-NEXT:    vpcmpeqd %xmm0, %xmm0, %xmm0
+; BITALG-NEXT:    vmovdqa64 %xmm0, %xmm0 {%k1} {z}
+; BITALG-NEXT:    retq
+  %2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
+  %3 = icmp ult <2 x i64> %2, <i64 2, i64 2>
+  %4 = sext <2 x i1> %3 to <2 x i64>
+  ret <2 x i64> %4
+}
+
+define <2 x i64> @ugt_1_v2i64(<2 x i64> %0) {
+; SSE2-LABEL: ugt_1_v2i64:
+; SSE2:       # %bb.0:
+; SSE2-NEXT:    movdqa %xmm0, %xmm1
+; SSE2-NEXT:    psrlw $1, %xmm1
+; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE2-NEXT:    psubb %xmm1, %xmm0
+; SSE2-NEXT:    movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
+; SSE2-NEXT:    movdqa %xmm0, %xmm2
+; SSE2-NEXT:    pand %xmm1, %xmm2
+; SSE2-NEXT:    psrlw $2, %xmm0
+; SSE2-NEXT:    pand %xmm1, %xmm0
+; SSE2-NEXT:    paddb %xmm2, %xmm0
+; SSE2-NEXT:    movdqa %xmm0, %xmm1
+; SSE2-NEXT:    psrlw $4, %xmm1
+; SSE2-NEXT:    paddb %xmm0, %xmm1
+; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE2-NEXT:    pxor %xmm0, %xmm0
+; SSE2-NEXT:    psadbw %xmm1, %xmm0
+; SSE2-NEXT:    por {{.*}}(%rip), %xmm0
+; SSE2-NEXT:    movdqa {{.*#+}} xmm1 = [2147483649,2147483649]
+; SSE2-NEXT:    movdqa %xmm0, %xmm2
+; SSE2-NEXT:    pcmpgtd %xmm1, %xmm2
+; SSE2-NEXT:    pshufd {{.*#+}} xmm3 = xmm2[0,0,2,2]
+; SSE2-NEXT:    pcmpeqd %xmm1, %xmm0
+; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[1,1,3,3]
+; SSE2-NEXT:    pand %xmm3, %xmm1
+; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm2[1,1,3,3]
+; SSE2-NEXT:    por %xmm1, %xmm0
+; SSE2-NEXT:    retq
+;
+; SSE3-LABEL: ugt_1_v2i64:
+; SSE3:       # %bb.0:
+; SSE3-NEXT:    movdqa %xmm0, %xmm1
+; SSE3-NEXT:    psrlw $1, %xmm1
+; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE3-NEXT:    psubb %xmm1, %xmm0
+; SSE3-NEXT:    movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
+; SSE3-NEXT:    movdqa %xmm0, %xmm2
+; SSE3-NEXT:    pand %xmm1, %xmm2
+; SSE3-NEXT:    psrlw $2, %xmm0
+; SSE3-NEXT:    pand %xmm1, %xmm0
+; SSE3-NEXT:    paddb %xmm2, %xmm0
+; SSE3-NEXT:    movdqa %xmm0, %xmm1
+; SSE3-NEXT:    psrlw $4, %xmm1
+; SSE3-NEXT:    paddb %xmm0, %xmm1
+; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE3-NEXT:    pxor %xmm0, %xmm0
+; SSE3-NEXT:    psadbw %xmm1, %xmm0
+; SSE3-NEXT:    por {{.*}}(%rip), %xmm0
+; SSE3-NEXT:    movdqa {{.*#+}} xmm1 = [2147483649,2147483649]
+; SSE3-NEXT:    movdqa %xmm0, %xmm2
+; SSE3-NEXT:    pcmpgtd %xmm1, %xmm2
+; SSE3-NEXT:    pshufd {{.*#+}} xmm3 = xmm2[0,0,2,2]
+; SSE3-NEXT:    pcmpeqd %xmm1, %xmm0
+; SSE3-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[1,1,3,3]
+; SSE3-NEXT:    pand %xmm3, %xmm1
+; SSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm2[1,1,3,3]
+; SSE3-NEXT:    por %xmm1, %xmm0
+; SSE3-NEXT:    retq
+;
+; SSSE3-LABEL: ugt_1_v2i64:
+; SSSE3:       # %bb.0:
+; SSSE3-NEXT:    movdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; SSSE3-NEXT:    movdqa %xmm0, %xmm2
+; SSSE3-NEXT:    pand %xmm1, %xmm2
+; SSSE3-NEXT:    movdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; SSSE3-NEXT:    movdqa %xmm3, %xmm4
+; SSSE3-NEXT:    pshufb %xmm2, %xmm4
+; SSSE3-NEXT:    psrlw $4, %xmm0
+; SSSE3-NEXT:    pand %xmm1, %xmm0
+; SSSE3-NEXT:    pshufb %xmm0, %xmm3
+; SSSE3-NEXT:    paddb %xmm4, %xmm3
+; SSSE3-NEXT:    pxor %xmm0, %xmm0
+; SSSE3-NEXT:    psadbw %xmm3, %xmm0
+; SSSE3-NEXT:    por {{.*}}(%rip), %xmm0
+; SSSE3-NEXT:    movdqa {{.*#+}} xmm1 = [2147483649,2147483649]
+; SSSE3-NEXT:    movdqa %xmm0, %xmm2
+; SSSE3-NEXT:    pcmpgtd %xmm1, %xmm2
+; SSSE3-NEXT:    pshufd {{.*#+}} xmm3 = xmm2[0,0,2,2]
+; SSSE3-NEXT:    pcmpeqd %xmm1, %xmm0
+; SSSE3-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[1,1,3,3]
+; SSSE3-NEXT:    pand %xmm3, %xmm1
+; SSSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm2[1,1,3,3]
+; SSSE3-NEXT:    por %xmm1, %xmm0
+; SSSE3-NEXT:    retq
+;
+; SSE41-LABEL: ugt_1_v2i64:
+; SSE41:       # %bb.0:
+; SSE41-NEXT:    movdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; SSE41-NEXT:    movdqa %xmm0, %xmm2
+; SSE41-NEXT:    pand %xmm1, %xmm2
+; SSE41-NEXT:    movdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; SSE41-NEXT:    movdqa %xmm3, %xmm4
+; SSE41-NEXT:    pshufb %xmm2, %xmm4
+; SSE41-NEXT:    psrlw $4, %xmm0
+; SSE41-NEXT:    pand %xmm1, %xmm0
+; SSE41-NEXT:    pshufb %xmm0, %xmm3
+; SSE41-NEXT:    paddb %xmm4, %xmm3
+; SSE41-NEXT:    pxor %xmm0, %xmm0
+; SSE41-NEXT:    psadbw %xmm3, %xmm0
+; SSE41-NEXT:    por {{.*}}(%rip), %xmm0
+; SSE41-NEXT:    movdqa {{.*#+}} xmm1 = [2147483649,2147483649]
+; SSE41-NEXT:    movdqa %xmm0, %xmm2
+; SSE41-NEXT:    pcmpgtd %xmm1, %xmm2
+; SSE41-NEXT:    pshufd {{.*#+}} xmm3 = xmm2[0,0,2,2]
+; SSE41-NEXT:    pcmpeqd %xmm1, %xmm0
+; SSE41-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[1,1,3,3]
+; SSE41-NEXT:    pand %xmm3, %xmm1
+; SSE41-NEXT:    pshufd {{.*#+}} xmm0 = xmm2[1,1,3,3]
+; SSE41-NEXT:    por %xmm1, %xmm0
+; SSE41-NEXT:    retq
+;
+; AVX1-LABEL: ugt_1_v2i64:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX1-NEXT:    vpaddb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX1-NEXT:    vpsadbw %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpcmpgtq {{.*}}(%rip), %xmm0, %xmm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: ugt_1_v2i64:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX2-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX2-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX2-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX2-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX2-NEXT:    vpaddb %xmm2, %xmm0, %xmm0
+; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX2-NEXT:    vpsadbw %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vpcmpgtq {{.*}}(%rip), %xmm0, %xmm0
+; AVX2-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: ugt_1_v2i64:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpopcntq %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpcmpgtq {{.*}}(%rip), %xmm0, %xmm0
+; AVX512VPOPCNTDQ-NEXT:    vzeroupper
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; AVX512VPOPCNTDQVL-LABEL: ugt_1_v2i64:
+; AVX512VPOPCNTDQVL:       # %bb.0:
+; AVX512VPOPCNTDQVL-NEXT:    vpopcntq %xmm0, %xmm0
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpnleuq {{.*}}(%rip), %xmm0, %k1
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpeqd %xmm0, %xmm0, %xmm0
+; AVX512VPOPCNTDQVL-NEXT:    vmovdqa64 %xmm0, %xmm0 {%k1} {z}
+; AVX512VPOPCNTDQVL-NEXT:    retq
+;
+; BITALG_NOVLX-LABEL: ugt_1_v2i64:
+; BITALG_NOVLX:       # %bb.0:
+; BITALG_NOVLX-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
+; BITALG_NOVLX-NEXT:    vpopcntb %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG_NOVLX-NEXT:    vpsadbw %xmm1, %xmm0, %xmm0
+; BITALG_NOVLX-NEXT:    vpcmpgtq {{.*}}(%rip), %xmm0, %xmm0
+; BITALG_NOVLX-NEXT:    vzeroupper
+; BITALG_NOVLX-NEXT:    retq
+;
+; BITALG-LABEL: ugt_1_v2i64:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntb %xmm0, %xmm0
+; BITALG-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG-NEXT:    vpsadbw %xmm1, %xmm0, %xmm0
+; BITALG-NEXT:    vpcmpnleuq {{.*}}(%rip), %xmm0, %k1
+; BITALG-NEXT:    vpcmpeqd %xmm0, %xmm0, %xmm0
+; BITALG-NEXT:    vmovdqa64 %xmm0, %xmm0 {%k1} {z}
+; BITALG-NEXT:    retq
+  %2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
+  %3 = icmp ugt <2 x i64> %2, <i64 1, i64 1>
+  %4 = sext <2 x i1> %3 to <2 x i64>
+  ret <2 x i64> %4
+}
+
+define <2 x i64> @eq_1_v2i64(<2 x i64> %0) {
+; SSE2-LABEL: eq_1_v2i64:
+; SSE2:       # %bb.0:
+; SSE2-NEXT:    movdqa %xmm0, %xmm1
+; SSE2-NEXT:    psrlw $1, %xmm1
+; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE2-NEXT:    psubb %xmm1, %xmm0
+; SSE2-NEXT:    movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
+; SSE2-NEXT:    movdqa %xmm0, %xmm2
+; SSE2-NEXT:    pand %xmm1, %xmm2
+; SSE2-NEXT:    psrlw $2, %xmm0
+; SSE2-NEXT:    pand %xmm1, %xmm0
+; SSE2-NEXT:    paddb %xmm2, %xmm0
+; SSE2-NEXT:    movdqa %xmm0, %xmm1
+; SSE2-NEXT:    psrlw $4, %xmm1
+; SSE2-NEXT:    paddb %xmm0, %xmm1
+; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE2-NEXT:    pxor %xmm2, %xmm2
+; SSE2-NEXT:    psadbw %xmm1, %xmm2
+; SSE2-NEXT:    pcmpeqd {{.*}}(%rip), %xmm2
+; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm2[1,0,3,2]
+; SSE2-NEXT:    pand %xmm2, %xmm0
+; SSE2-NEXT:    retq
+;
+; SSE3-LABEL: eq_1_v2i64:
+; SSE3:       # %bb.0:
+; SSE3-NEXT:    movdqa %xmm0, %xmm1
+; SSE3-NEXT:    psrlw $1, %xmm1
+; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE3-NEXT:    psubb %xmm1, %xmm0
+; SSE3-NEXT:    movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
+; SSE3-NEXT:    movdqa %xmm0, %xmm2
+; SSE3-NEXT:    pand %xmm1, %xmm2
+; SSE3-NEXT:    psrlw $2, %xmm0
+; SSE3-NEXT:    pand %xmm1, %xmm0
+; SSE3-NEXT:    paddb %xmm2, %xmm0
+; SSE3-NEXT:    movdqa %xmm0, %xmm1
+; SSE3-NEXT:    psrlw $4, %xmm1
+; SSE3-NEXT:    paddb %xmm0, %xmm1
+; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE3-NEXT:    pxor %xmm2, %xmm2
+; SSE3-NEXT:    psadbw %xmm1, %xmm2
+; SSE3-NEXT:    pcmpeqd {{.*}}(%rip), %xmm2
+; SSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm2[1,0,3,2]
+; SSE3-NEXT:    pand %xmm2, %xmm0
+; SSE3-NEXT:    retq
+;
+; SSSE3-LABEL: eq_1_v2i64:
+; SSSE3:       # %bb.0:
+; SSSE3-NEXT:    movdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; SSSE3-NEXT:    movdqa %xmm0, %xmm2
+; SSSE3-NEXT:    pand %xmm1, %xmm2
+; SSSE3-NEXT:    movdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; SSSE3-NEXT:    movdqa %xmm3, %xmm4
+; SSSE3-NEXT:    pshufb %xmm2, %xmm4
+; SSSE3-NEXT:    psrlw $4, %xmm0
+; SSSE3-NEXT:    pand %xmm1, %xmm0
+; SSSE3-NEXT:    pshufb %xmm0, %xmm3
+; SSSE3-NEXT:    paddb %xmm4, %xmm3
+; SSSE3-NEXT:    pxor %xmm1, %xmm1
+; SSSE3-NEXT:    psadbw %xmm3, %xmm1
+; SSSE3-NEXT:    pcmpeqd {{.*}}(%rip), %xmm1
+; SSSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[1,0,3,2]
+; SSSE3-NEXT:    pand %xmm1, %xmm0
+; SSSE3-NEXT:    retq
+;
+; SSE41-LABEL: eq_1_v2i64:
+; SSE41:       # %bb.0:
+; SSE41-NEXT:    movdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; SSE41-NEXT:    movdqa %xmm0, %xmm2
+; SSE41-NEXT:    pand %xmm1, %xmm2
+; SSE41-NEXT:    movdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; SSE41-NEXT:    movdqa %xmm3, %xmm4
+; SSE41-NEXT:    pshufb %xmm2, %xmm4
+; SSE41-NEXT:    psrlw $4, %xmm0
+; SSE41-NEXT:    pand %xmm1, %xmm0
+; SSE41-NEXT:    pshufb %xmm0, %xmm3
+; SSE41-NEXT:    paddb %xmm4, %xmm3
+; SSE41-NEXT:    pxor %xmm0, %xmm0
+; SSE41-NEXT:    psadbw %xmm3, %xmm0
+; SSE41-NEXT:    pcmpeqq {{.*}}(%rip), %xmm0
+; SSE41-NEXT:    retq
+;
+; AVX1-LABEL: eq_1_v2i64:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX1-NEXT:    vpaddb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX1-NEXT:    vpsadbw %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpcmpeqq {{.*}}(%rip), %xmm0, %xmm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: eq_1_v2i64:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX2-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX2-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX2-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX2-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX2-NEXT:    vpaddb %xmm2, %xmm0, %xmm0
+; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX2-NEXT:    vpsadbw %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vpcmpeqq {{.*}}(%rip), %xmm0, %xmm0
+; AVX2-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: eq_1_v2i64:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpopcntq %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpcmpeqq {{.*}}(%rip), %xmm0, %xmm0
+; AVX512VPOPCNTDQ-NEXT:    vzeroupper
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; AVX512VPOPCNTDQVL-LABEL: eq_1_v2i64:
+; AVX512VPOPCNTDQVL:       # %bb.0:
+; AVX512VPOPCNTDQVL-NEXT:    vpopcntq %xmm0, %xmm0
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpeqq {{.*}}(%rip), %xmm0, %xmm0
+; AVX512VPOPCNTDQVL-NEXT:    retq
+;
+; BITALG_NOVLX-LABEL: eq_1_v2i64:
+; BITALG_NOVLX:       # %bb.0:
+; BITALG_NOVLX-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
+; BITALG_NOVLX-NEXT:    vpopcntb %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG_NOVLX-NEXT:    vpsadbw %xmm1, %xmm0, %xmm0
+; BITALG_NOVLX-NEXT:    vpcmpeqq {{.*}}(%rip), %xmm0, %xmm0
+; BITALG_NOVLX-NEXT:    vzeroupper
+; BITALG_NOVLX-NEXT:    retq
+;
+; BITALG-LABEL: eq_1_v2i64:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntb %xmm0, %xmm0
+; BITALG-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG-NEXT:    vpsadbw %xmm1, %xmm0, %xmm0
+; BITALG-NEXT:    vpcmpeqq {{.*}}(%rip), %xmm0, %xmm0
+; BITALG-NEXT:    retq
+  %2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
+  %3 = icmp eq <2 x i64> %2, <i64 1, i64 1>
+  %4 = sext <2 x i1> %3 to <2 x i64>
+  ret <2 x i64> %4
+}
+
+define <2 x i64> @ne_1_v2i64(<2 x i64> %0) {
+; SSE2-LABEL: ne_1_v2i64:
+; SSE2:       # %bb.0:
+; SSE2-NEXT:    movdqa %xmm0, %xmm1
+; SSE2-NEXT:    psrlw $1, %xmm1
+; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE2-NEXT:    psubb %xmm1, %xmm0
+; SSE2-NEXT:    movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
+; SSE2-NEXT:    movdqa %xmm0, %xmm2
+; SSE2-NEXT:    pand %xmm1, %xmm2
+; SSE2-NEXT:    psrlw $2, %xmm0
+; SSE2-NEXT:    pand %xmm1, %xmm0
+; SSE2-NEXT:    paddb %xmm2, %xmm0
+; SSE2-NEXT:    movdqa %xmm0, %xmm1
+; SSE2-NEXT:    psrlw $4, %xmm1
+; SSE2-NEXT:    paddb %xmm0, %xmm1
+; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE2-NEXT:    pxor %xmm0, %xmm0
+; SSE2-NEXT:    psadbw %xmm1, %xmm0
+; SSE2-NEXT:    pcmpeqd {{.*}}(%rip), %xmm0
+; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[1,0,3,2]
+; SSE2-NEXT:    pand %xmm0, %xmm1
+; SSE2-NEXT:    pcmpeqd %xmm0, %xmm0
+; SSE2-NEXT:    pxor %xmm1, %xmm0
+; SSE2-NEXT:    retq
+;
+; SSE3-LABEL: ne_1_v2i64:
+; SSE3:       # %bb.0:
+; SSE3-NEXT:    movdqa %xmm0, %xmm1
+; SSE3-NEXT:    psrlw $1, %xmm1
+; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE3-NEXT:    psubb %xmm1, %xmm0
+; SSE3-NEXT:    movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
+; SSE3-NEXT:    movdqa %xmm0, %xmm2
+; SSE3-NEXT:    pand %xmm1, %xmm2
+; SSE3-NEXT:    psrlw $2, %xmm0
+; SSE3-NEXT:    pand %xmm1, %xmm0
+; SSE3-NEXT:    paddb %xmm2, %xmm0
+; SSE3-NEXT:    movdqa %xmm0, %xmm1
+; SSE3-NEXT:    psrlw $4, %xmm1
+; SSE3-NEXT:    paddb %xmm0, %xmm1
+; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE3-NEXT:    pxor %xmm0, %xmm0
+; SSE3-NEXT:    psadbw %xmm1, %xmm0
+; SSE3-NEXT:    pcmpeqd {{.*}}(%rip), %xmm0
+; SSE3-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[1,0,3,2]
+; SSE3-NEXT:    pand %xmm0, %xmm1
+; SSE3-NEXT:    pcmpeqd %xmm0, %xmm0
+; SSE3-NEXT:    pxor %xmm1, %xmm0
+; SSE3-NEXT:    retq
+;
+; SSSE3-LABEL: ne_1_v2i64:
+; SSSE3:       # %bb.0:
+; SSSE3-NEXT:    movdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; SSSE3-NEXT:    movdqa %xmm0, %xmm2
+; SSSE3-NEXT:    pand %xmm1, %xmm2
+; SSSE3-NEXT:    movdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; SSSE3-NEXT:    movdqa %xmm3, %xmm4
+; SSSE3-NEXT:    pshufb %xmm2, %xmm4
+; SSSE3-NEXT:    psrlw $4, %xmm0
+; SSSE3-NEXT:    pand %xmm1, %xmm0
+; SSSE3-NEXT:    pshufb %xmm0, %xmm3
+; SSSE3-NEXT:    paddb %xmm4, %xmm3
+; SSSE3-NEXT:    pxor %xmm0, %xmm0
+; SSSE3-NEXT:    psadbw %xmm3, %xmm0
+; SSSE3-NEXT:    pcmpeqd {{.*}}(%rip), %xmm0
+; SSSE3-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[1,0,3,2]
+; SSSE3-NEXT:    pand %xmm0, %xmm1
+; SSSE3-NEXT:    pcmpeqd %xmm0, %xmm0
+; SSSE3-NEXT:    pxor %xmm1, %xmm0
+; SSSE3-NEXT:    retq
+;
+; SSE41-LABEL: ne_1_v2i64:
+; SSE41:       # %bb.0:
+; SSE41-NEXT:    movdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; SSE41-NEXT:    movdqa %xmm0, %xmm2
+; SSE41-NEXT:    pand %xmm1, %xmm2
+; SSE41-NEXT:    movdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; SSE41-NEXT:    movdqa %xmm3, %xmm4
+; SSE41-NEXT:    pshufb %xmm2, %xmm4
+; SSE41-NEXT:    psrlw $4, %xmm0
+; SSE41-NEXT:    pand %xmm1, %xmm0
+; SSE41-NEXT:    pshufb %xmm0, %xmm3
+; SSE41-NEXT:    paddb %xmm4, %xmm3
+; SSE41-NEXT:    pxor %xmm1, %xmm1
+; SSE41-NEXT:    psadbw %xmm3, %xmm1
+; SSE41-NEXT:    pcmpeqq {{.*}}(%rip), %xmm1
+; SSE41-NEXT:    pcmpeqd %xmm0, %xmm0
+; SSE41-NEXT:    pxor %xmm1, %xmm0
+; SSE41-NEXT:    retq
+;
+; AVX1-LABEL: ne_1_v2i64:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX1-NEXT:    vpaddb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX1-NEXT:    vpsadbw %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpcmpeqq {{.*}}(%rip), %xmm0, %xmm0
+; AVX1-NEXT:    vpcmpeqd %xmm1, %xmm1, %xmm1
+; AVX1-NEXT:    vpxor %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: ne_1_v2i64:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX2-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX2-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX2-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX2-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX2-NEXT:    vpaddb %xmm2, %xmm0, %xmm0
+; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX2-NEXT:    vpsadbw %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vpcmpeqq {{.*}}(%rip), %xmm0, %xmm0
+; AVX2-NEXT:    vpcmpeqd %xmm1, %xmm1, %xmm1
+; AVX2-NEXT:    vpxor %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: ne_1_v2i64:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpopcntq %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpcmpeqq {{.*}}(%rip), %xmm0, %xmm0
+; AVX512VPOPCNTDQ-NEXT:    vpternlogq $15, %zmm0, %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    # kill: def $xmm0 killed $xmm0 killed $zmm0
+; AVX512VPOPCNTDQ-NEXT:    vzeroupper
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; AVX512VPOPCNTDQVL-LABEL: ne_1_v2i64:
+; AVX512VPOPCNTDQVL:       # %bb.0:
+; AVX512VPOPCNTDQVL-NEXT:    vpopcntq %xmm0, %xmm0
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpeqq {{.*}}(%rip), %xmm0, %xmm0
+; AVX512VPOPCNTDQVL-NEXT:    vpternlogq $15, %xmm0, %xmm0, %xmm0
+; AVX512VPOPCNTDQVL-NEXT:    retq
+;
+; BITALG_NOVLX-LABEL: ne_1_v2i64:
+; BITALG_NOVLX:       # %bb.0:
+; BITALG_NOVLX-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
+; BITALG_NOVLX-NEXT:    vpopcntb %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG_NOVLX-NEXT:    vpsadbw %xmm1, %xmm0, %xmm0
+; BITALG_NOVLX-NEXT:    vpcmpeqq {{.*}}(%rip), %xmm0, %xmm0
+; BITALG_NOVLX-NEXT:    vpternlogq $15, %zmm0, %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    # kill: def $xmm0 killed $xmm0 killed $zmm0
+; BITALG_NOVLX-NEXT:    vzeroupper
+; BITALG_NOVLX-NEXT:    retq
+;
+; BITALG-LABEL: ne_1_v2i64:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntb %xmm0, %xmm0
+; BITALG-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG-NEXT:    vpsadbw %xmm1, %xmm0, %xmm0
+; BITALG-NEXT:    vpcmpeqq {{.*}}(%rip), %xmm0, %xmm0
+; BITALG-NEXT:    vpternlogq $15, %xmm0, %xmm0, %xmm0
+; BITALG-NEXT:    retq
+  %2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
+  %3 = icmp ne <2 x i64> %2, <i64 1, i64 1>
+  %4 = sext <2 x i1> %3 to <2 x i64>
+  ret <2 x i64> %4
+}
+
+define <4 x i32> @ult_2_v4i32(<4 x i32> %0) {
+; SSE2-LABEL: ult_2_v4i32:
+; SSE2:       # %bb.0:
+; SSE2-NEXT:    movdqa %xmm0, %xmm1
+; SSE2-NEXT:    psrlw $1, %xmm1
+; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE2-NEXT:    psubb %xmm1, %xmm0
+; SSE2-NEXT:    movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
+; SSE2-NEXT:    movdqa %xmm0, %xmm2
+; SSE2-NEXT:    pand %xmm1, %xmm2
+; SSE2-NEXT:    psrlw $2, %xmm0
+; SSE2-NEXT:    pand %xmm1, %xmm0
+; SSE2-NEXT:    paddb %xmm2, %xmm0
+; SSE2-NEXT:    movdqa %xmm0, %xmm1
+; SSE2-NEXT:    psrlw $4, %xmm1
+; SSE2-NEXT:    paddb %xmm0, %xmm1
+; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE2-NEXT:    pxor %xmm0, %xmm0
+; SSE2-NEXT:    movdqa %xmm1, %xmm2
+; SSE2-NEXT:    punpckhdq {{.*#+}} xmm2 = xmm2[2],xmm0[2],xmm2[3],xmm0[3]
+; SSE2-NEXT:    psadbw %xmm0, %xmm2
+; SSE2-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
+; SSE2-NEXT:    psadbw %xmm0, %xmm1
+; SSE2-NEXT:    packuswb %xmm2, %xmm1
+; SSE2-NEXT:    movdqa {{.*#+}} xmm0 = [2,2,2,2]
+; SSE2-NEXT:    pcmpgtd %xmm1, %xmm0
+; SSE2-NEXT:    retq
+;
+; SSE3-LABEL: ult_2_v4i32:
+; SSE3:       # %bb.0:
+; SSE3-NEXT:    movdqa %xmm0, %xmm1
+; SSE3-NEXT:    psrlw $1, %xmm1
+; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE3-NEXT:    psubb %xmm1, %xmm0
+; SSE3-NEXT:    movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
+; SSE3-NEXT:    movdqa %xmm0, %xmm2
+; SSE3-NEXT:    pand %xmm1, %xmm2
+; SSE3-NEXT:    psrlw $2, %xmm0
+; SSE3-NEXT:    pand %xmm1, %xmm0
+; SSE3-NEXT:    paddb %xmm2, %xmm0
+; SSE3-NEXT:    movdqa %xmm0, %xmm1
+; SSE3-NEXT:    psrlw $4, %xmm1
+; SSE3-NEXT:    paddb %xmm0, %xmm1
+; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE3-NEXT:    pxor %xmm0, %xmm0
+; SSE3-NEXT:    movdqa %xmm1, %xmm2
+; SSE3-NEXT:    punpckhdq {{.*#+}} xmm2 = xmm2[2],xmm0[2],xmm2[3],xmm0[3]
+; SSE3-NEXT:    psadbw %xmm0, %xmm2
+; SSE3-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
+; SSE3-NEXT:    psadbw %xmm0, %xmm1
+; SSE3-NEXT:    packuswb %xmm2, %xmm1
+; SSE3-NEXT:    movdqa {{.*#+}} xmm0 = [2,2,2,2]
+; SSE3-NEXT:    pcmpgtd %xmm1, %xmm0
+; SSE3-NEXT:    retq
+;
+; SSSE3-LABEL: ult_2_v4i32:
+; SSSE3:       # %bb.0:
+; SSSE3-NEXT:    movdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; SSSE3-NEXT:    movdqa %xmm0, %xmm2
+; SSSE3-NEXT:    pand %xmm1, %xmm2
+; SSSE3-NEXT:    movdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; SSSE3-NEXT:    movdqa %xmm3, %xmm4
+; SSSE3-NEXT:    pshufb %xmm2, %xmm4
+; SSSE3-NEXT:    psrlw $4, %xmm0
+; SSSE3-NEXT:    pand %xmm1, %xmm0
+; SSSE3-NEXT:    pshufb %xmm0, %xmm3
+; SSSE3-NEXT:    paddb %xmm4, %xmm3
+; SSSE3-NEXT:    pxor %xmm0, %xmm0
+; SSSE3-NEXT:    movdqa %xmm3, %xmm1
+; SSSE3-NEXT:    punpckhdq {{.*#+}} xmm1 = xmm1[2],xmm0[2],xmm1[3],xmm0[3]
+; SSSE3-NEXT:    psadbw %xmm0, %xmm1
+; SSSE3-NEXT:    punpckldq {{.*#+}} xmm3 = xmm3[0],xmm0[0],xmm3[1],xmm0[1]
+; SSSE3-NEXT:    psadbw %xmm0, %xmm3
+; SSSE3-NEXT:    packuswb %xmm1, %xmm3
+; SSSE3-NEXT:    movdqa {{.*#+}} xmm0 = [2,2,2,2]
+; SSSE3-NEXT:    pcmpgtd %xmm3, %xmm0
+; SSSE3-NEXT:    retq
+;
+; SSE41-LABEL: ult_2_v4i32:
+; SSE41:       # %bb.0:
+; SSE41-NEXT:    movdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; SSE41-NEXT:    movdqa %xmm0, %xmm2
+; SSE41-NEXT:    pand %xmm1, %xmm2
+; SSE41-NEXT:    movdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; SSE41-NEXT:    movdqa %xmm3, %xmm4
+; SSE41-NEXT:    pshufb %xmm2, %xmm4
+; SSE41-NEXT:    psrlw $4, %xmm0
+; SSE41-NEXT:    pand %xmm1, %xmm0
+; SSE41-NEXT:    pshufb %xmm0, %xmm3
+; SSE41-NEXT:    paddb %xmm4, %xmm3
+; SSE41-NEXT:    pxor %xmm0, %xmm0
+; SSE41-NEXT:    pmovzxdq {{.*#+}} xmm1 = xmm3[0],zero,xmm3[1],zero
+; SSE41-NEXT:    punpckhdq {{.*#+}} xmm3 = xmm3[2],xmm0[2],xmm3[3],xmm0[3]
+; SSE41-NEXT:    psadbw %xmm0, %xmm3
+; SSE41-NEXT:    psadbw %xmm0, %xmm1
+; SSE41-NEXT:    packuswb %xmm3, %xmm1
+; SSE41-NEXT:    movdqa {{.*#+}} xmm0 = [2,2,2,2]
+; SSE41-NEXT:    pcmpgtd %xmm1, %xmm0
+; SSE41-NEXT:    retq
+;
+; AVX1-LABEL: ult_2_v4i32:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX1-NEXT:    vpaddb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX1-NEXT:    vpunpckhdq {{.*#+}} xmm2 = xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX1-NEXT:    vpsadbw %xmm1, %xmm2, %xmm2
+; AVX1-NEXT:    vpmovzxdq {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero
+; AVX1-NEXT:    vpsadbw %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpackuswb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [2,2,2,2]
+; AVX1-NEXT:    vpcmpgtd %xmm0, %xmm1, %xmm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: ult_2_v4i32:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX2-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX2-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX2-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX2-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX2-NEXT:    vpaddb %xmm2, %xmm0, %xmm0
+; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX2-NEXT:    vpunpckhdq {{.*#+}} xmm2 = xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX2-NEXT:    vpsadbw %xmm1, %xmm2, %xmm2
+; AVX2-NEXT:    vpmovzxdq {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero
+; AVX2-NEXT:    vpsadbw %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vpackuswb %xmm2, %xmm0, %xmm0
+; AVX2-NEXT:    vpbroadcastd {{.*#+}} xmm1 = [2,2,2,2]
+; AVX2-NEXT:    vpcmpgtd %xmm0, %xmm1, %xmm0
+; AVX2-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: ult_2_v4i32:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpopcntd %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpbroadcastd {{.*#+}} xmm1 = [2,2,2,2]
+; AVX512VPOPCNTDQ-NEXT:    vpcmpgtd %xmm0, %xmm1, %xmm0
+; AVX512VPOPCNTDQ-NEXT:    vzeroupper
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; AVX512VPOPCNTDQVL-LABEL: ult_2_v4i32:
+; AVX512VPOPCNTDQVL:       # %bb.0:
+; AVX512VPOPCNTDQVL-NEXT:    vpopcntd %xmm0, %xmm0
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpltud {{.*}}(%rip){1to4}, %xmm0, %k1
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpeqd %xmm0, %xmm0, %xmm0
+; AVX512VPOPCNTDQVL-NEXT:    vmovdqa32 %xmm0, %xmm0 {%k1} {z}
+; AVX512VPOPCNTDQVL-NEXT:    retq
+;
+; BITALG_NOVLX-LABEL: ult_2_v4i32:
+; BITALG_NOVLX:       # %bb.0:
+; BITALG_NOVLX-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
+; BITALG_NOVLX-NEXT:    vpopcntb %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG_NOVLX-NEXT:    vpunpckhdq {{.*#+}} xmm2 = xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; BITALG_NOVLX-NEXT:    vpsadbw %xmm1, %xmm2, %xmm2
+; BITALG_NOVLX-NEXT:    vpmovzxdq {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero
+; BITALG_NOVLX-NEXT:    vpsadbw %xmm1, %xmm0, %xmm0
+; BITALG_NOVLX-NEXT:    vpackuswb %xmm2, %xmm0, %xmm0
+; BITALG_NOVLX-NEXT:    vpbroadcastd {{.*#+}} xmm1 = [2,2,2,2]
+; BITALG_NOVLX-NEXT:    vpcmpgtd %xmm0, %xmm1, %xmm0
+; BITALG_NOVLX-NEXT:    vzeroupper
+; BITALG_NOVLX-NEXT:    retq
+;
+; BITALG-LABEL: ult_2_v4i32:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntb %xmm0, %xmm0
+; BITALG-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG-NEXT:    vpunpckhdq {{.*#+}} xmm2 = xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; BITALG-NEXT:    vpsadbw %xmm1, %xmm2, %xmm2
+; BITALG-NEXT:    vpmovzxdq {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero
+; BITALG-NEXT:    vpsadbw %xmm1, %xmm0, %xmm0
+; BITALG-NEXT:    vpackuswb %xmm2, %xmm0, %xmm0
+; BITALG-NEXT:    vpcmpltud {{.*}}(%rip){1to4}, %xmm0, %k1
+; BITALG-NEXT:    vpcmpeqd %xmm0, %xmm0, %xmm0
+; BITALG-NEXT:    vmovdqa32 %xmm0, %xmm0 {%k1} {z}
+; BITALG-NEXT:    retq
+  %2 = tail call <4 x i32> @llvm.ctpop.v4i32(<4 x i32> %0)
+  %3 = icmp ult <4 x i32> %2, <i32 2, i32 2, i32 2, i32 2>
+  %4 = sext <4 x i1> %3 to <4 x i32>
+  ret <4 x i32> %4
+}
+
+define <4 x i32> @ugt_1_v4i32(<4 x i32> %0) {
+; SSE2-LABEL: ugt_1_v4i32:
+; SSE2:       # %bb.0:
+; SSE2-NEXT:    movdqa %xmm0, %xmm1
+; SSE2-NEXT:    psrlw $1, %xmm1
+; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE2-NEXT:    psubb %xmm1, %xmm0
+; SSE2-NEXT:    movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
+; SSE2-NEXT:    movdqa %xmm0, %xmm2
+; SSE2-NEXT:    pand %xmm1, %xmm2
+; SSE2-NEXT:    psrlw $2, %xmm0
+; SSE2-NEXT:    pand %xmm1, %xmm0
+; SSE2-NEXT:    paddb %xmm2, %xmm0
+; SSE2-NEXT:    movdqa %xmm0, %xmm1
+; SSE2-NEXT:    psrlw $4, %xmm1
+; SSE2-NEXT:    paddb %xmm0, %xmm1
+; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE2-NEXT:    pxor %xmm0, %xmm0
+; SSE2-NEXT:    movdqa %xmm1, %xmm2
+; SSE2-NEXT:    punpckhdq {{.*#+}} xmm2 = xmm2[2],xmm0[2],xmm2[3],xmm0[3]
+; SSE2-NEXT:    psadbw %xmm0, %xmm2
+; SSE2-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
+; SSE2-NEXT:    psadbw %xmm0, %xmm1
+; SSE2-NEXT:    packuswb %xmm2, %xmm1
+; SSE2-NEXT:    pcmpgtd {{.*}}(%rip), %xmm1
+; SSE2-NEXT:    movdqa %xmm1, %xmm0
+; SSE2-NEXT:    retq
+;
+; SSE3-LABEL: ugt_1_v4i32:
+; SSE3:       # %bb.0:
+; SSE3-NEXT:    movdqa %xmm0, %xmm1
+; SSE3-NEXT:    psrlw $1, %xmm1
+; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE3-NEXT:    psubb %xmm1, %xmm0
+; SSE3-NEXT:    movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
+; SSE3-NEXT:    movdqa %xmm0, %xmm2
+; SSE3-NEXT:    pand %xmm1, %xmm2
+; SSE3-NEXT:    psrlw $2, %xmm0
+; SSE3-NEXT:    pand %xmm1, %xmm0
+; SSE3-NEXT:    paddb %xmm2, %xmm0
+; SSE3-NEXT:    movdqa %xmm0, %xmm1
+; SSE3-NEXT:    psrlw $4, %xmm1
+; SSE3-NEXT:    paddb %xmm0, %xmm1
+; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE3-NEXT:    pxor %xmm0, %xmm0
+; SSE3-NEXT:    movdqa %xmm1, %xmm2
+; SSE3-NEXT:    punpckhdq {{.*#+}} xmm2 = xmm2[2],xmm0[2],xmm2[3],xmm0[3]
+; SSE3-NEXT:    psadbw %xmm0, %xmm2
+; SSE3-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
+; SSE3-NEXT:    psadbw %xmm0, %xmm1
+; SSE3-NEXT:    packuswb %xmm2, %xmm1
+; SSE3-NEXT:    pcmpgtd {{.*}}(%rip), %xmm1
+; SSE3-NEXT:    movdqa %xmm1, %xmm0
+; SSE3-NEXT:    retq
+;
+; SSSE3-LABEL: ugt_1_v4i32:
+; SSSE3:       # %bb.0:
+; SSSE3-NEXT:    movdqa {{.*#+}} xmm2 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; SSSE3-NEXT:    movdqa %xmm0, %xmm3
+; SSSE3-NEXT:    pand %xmm2, %xmm3
+; SSSE3-NEXT:    movdqa {{.*#+}} xmm1 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; SSSE3-NEXT:    movdqa %xmm1, %xmm4
+; SSSE3-NEXT:    pshufb %xmm3, %xmm4
+; SSSE3-NEXT:    psrlw $4, %xmm0
+; SSSE3-NEXT:    pand %xmm2, %xmm0
+; SSSE3-NEXT:    pshufb %xmm0, %xmm1
+; SSSE3-NEXT:    paddb %xmm4, %xmm1
+; SSSE3-NEXT:    pxor %xmm0, %xmm0
+; SSSE3-NEXT:    movdqa %xmm1, %xmm2
+; SSSE3-NEXT:    punpckhdq {{.*#+}} xmm2 = xmm2[2],xmm0[2],xmm2[3],xmm0[3]
+; SSSE3-NEXT:    psadbw %xmm0, %xmm2
+; SSSE3-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
+; SSSE3-NEXT:    psadbw %xmm0, %xmm1
+; SSSE3-NEXT:    packuswb %xmm2, %xmm1
+; SSSE3-NEXT:    pcmpgtd {{.*}}(%rip), %xmm1
+; SSSE3-NEXT:    movdqa %xmm1, %xmm0
+; SSSE3-NEXT:    retq
+;
+; SSE41-LABEL: ugt_1_v4i32:
+; SSE41:       # %bb.0:
+; SSE41-NEXT:    movdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; SSE41-NEXT:    movdqa %xmm0, %xmm2
+; SSE41-NEXT:    pand %xmm1, %xmm2
+; SSE41-NEXT:    movdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; SSE41-NEXT:    movdqa %xmm3, %xmm4
+; SSE41-NEXT:    pshufb %xmm2, %xmm4
+; SSE41-NEXT:    psrlw $4, %xmm0
+; SSE41-NEXT:    pand %xmm1, %xmm0
+; SSE41-NEXT:    pshufb %xmm0, %xmm3
+; SSE41-NEXT:    paddb %xmm4, %xmm3
+; SSE41-NEXT:    pxor %xmm1, %xmm1
+; SSE41-NEXT:    pmovzxdq {{.*#+}} xmm0 = xmm3[0],zero,xmm3[1],zero
+; SSE41-NEXT:    punpckhdq {{.*#+}} xmm3 = xmm3[2],xmm1[2],xmm3[3],xmm1[3]
+; SSE41-NEXT:    psadbw %xmm1, %xmm3
+; SSE41-NEXT:    psadbw %xmm1, %xmm0
+; SSE41-NEXT:    packuswb %xmm3, %xmm0
+; SSE41-NEXT:    pcmpgtd {{.*}}(%rip), %xmm0
+; SSE41-NEXT:    retq
+;
+; AVX1-LABEL: ugt_1_v4i32:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX1-NEXT:    vpaddb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX1-NEXT:    vpunpckhdq {{.*#+}} xmm2 = xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX1-NEXT:    vpsadbw %xmm1, %xmm2, %xmm2
+; AVX1-NEXT:    vpmovzxdq {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero
+; AVX1-NEXT:    vpsadbw %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpackuswb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpcmpgtd {{.*}}(%rip), %xmm0, %xmm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: ugt_1_v4i32:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX2-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX2-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX2-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX2-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX2-NEXT:    vpaddb %xmm2, %xmm0, %xmm0
+; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX2-NEXT:    vpunpckhdq {{.*#+}} xmm2 = xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX2-NEXT:    vpsadbw %xmm1, %xmm2, %xmm2
+; AVX2-NEXT:    vpmovzxdq {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero
+; AVX2-NEXT:    vpsadbw %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vpackuswb %xmm2, %xmm0, %xmm0
+; AVX2-NEXT:    vpbroadcastd {{.*#+}} xmm1 = [1,1,1,1]
+; AVX2-NEXT:    vpcmpgtd %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: ugt_1_v4i32:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpopcntd %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpbroadcastd {{.*#+}} xmm1 = [1,1,1,1]
+; AVX512VPOPCNTDQ-NEXT:    vpcmpgtd %xmm1, %xmm0, %xmm0
+; AVX512VPOPCNTDQ-NEXT:    vzeroupper
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; AVX512VPOPCNTDQVL-LABEL: ugt_1_v4i32:
+; AVX512VPOPCNTDQVL:       # %bb.0:
+; AVX512VPOPCNTDQVL-NEXT:    vpopcntd %xmm0, %xmm0
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpnleud {{.*}}(%rip){1to4}, %xmm0, %k1
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpeqd %xmm0, %xmm0, %xmm0
+; AVX512VPOPCNTDQVL-NEXT:    vmovdqa32 %xmm0, %xmm0 {%k1} {z}
+; AVX512VPOPCNTDQVL-NEXT:    retq
+;
+; BITALG_NOVLX-LABEL: ugt_1_v4i32:
+; BITALG_NOVLX:       # %bb.0:
+; BITALG_NOVLX-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
+; BITALG_NOVLX-NEXT:    vpopcntb %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG_NOVLX-NEXT:    vpunpckhdq {{.*#+}} xmm2 = xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; BITALG_NOVLX-NEXT:    vpsadbw %xmm1, %xmm2, %xmm2
+; BITALG_NOVLX-NEXT:    vpmovzxdq {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero
+; BITALG_NOVLX-NEXT:    vpsadbw %xmm1, %xmm0, %xmm0
+; BITALG_NOVLX-NEXT:    vpackuswb %xmm2, %xmm0, %xmm0
+; BITALG_NOVLX-NEXT:    vpbroadcastd {{.*#+}} xmm1 = [1,1,1,1]
+; BITALG_NOVLX-NEXT:    vpcmpgtd %xmm1, %xmm0, %xmm0
+; BITALG_NOVLX-NEXT:    vzeroupper
+; BITALG_NOVLX-NEXT:    retq
+;
+; BITALG-LABEL: ugt_1_v4i32:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntb %xmm0, %xmm0
+; BITALG-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG-NEXT:    vpunpckhdq {{.*#+}} xmm2 = xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; BITALG-NEXT:    vpsadbw %xmm1, %xmm2, %xmm2
+; BITALG-NEXT:    vpmovzxdq {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero
+; BITALG-NEXT:    vpsadbw %xmm1, %xmm0, %xmm0
+; BITALG-NEXT:    vpackuswb %xmm2, %xmm0, %xmm0
+; BITALG-NEXT:    vpcmpnleud {{.*}}(%rip){1to4}, %xmm0, %k1
+; BITALG-NEXT:    vpcmpeqd %xmm0, %xmm0, %xmm0
+; BITALG-NEXT:    vmovdqa32 %xmm0, %xmm0 {%k1} {z}
+; BITALG-NEXT:    retq
+  %2 = tail call <4 x i32> @llvm.ctpop.v4i32(<4 x i32> %0)
+  %3 = icmp ugt <4 x i32> %2, <i32 1, i32 1, i32 1, i32 1>
+  %4 = sext <4 x i1> %3 to <4 x i32>
+  ret <4 x i32> %4
+}
+
+define <4 x i32> @eq_1_v4i32(<4 x i32> %0) {
+; SSE2-LABEL: eq_1_v4i32:
+; SSE2:       # %bb.0:
+; SSE2-NEXT:    movdqa %xmm0, %xmm1
+; SSE2-NEXT:    psrlw $1, %xmm1
+; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE2-NEXT:    psubb %xmm1, %xmm0
+; SSE2-NEXT:    movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
+; SSE2-NEXT:    movdqa %xmm0, %xmm2
+; SSE2-NEXT:    pand %xmm1, %xmm2
+; SSE2-NEXT:    psrlw $2, %xmm0
+; SSE2-NEXT:    pand %xmm1, %xmm0
+; SSE2-NEXT:    paddb %xmm2, %xmm0
+; SSE2-NEXT:    movdqa %xmm0, %xmm1
+; SSE2-NEXT:    psrlw $4, %xmm1
+; SSE2-NEXT:    paddb %xmm0, %xmm1
+; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE2-NEXT:    pxor %xmm0, %xmm0
+; SSE2-NEXT:    movdqa %xmm1, %xmm2
+; SSE2-NEXT:    punpckhdq {{.*#+}} xmm2 = xmm2[2],xmm0[2],xmm2[3],xmm0[3]
+; SSE2-NEXT:    psadbw %xmm0, %xmm2
+; SSE2-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
+; SSE2-NEXT:    psadbw %xmm0, %xmm1
+; SSE2-NEXT:    packuswb %xmm2, %xmm1
+; SSE2-NEXT:    pcmpeqd {{.*}}(%rip), %xmm1
+; SSE2-NEXT:    movdqa %xmm1, %xmm0
+; SSE2-NEXT:    retq
+;
+; SSE3-LABEL: eq_1_v4i32:
+; SSE3:       # %bb.0:
+; SSE3-NEXT:    movdqa %xmm0, %xmm1
+; SSE3-NEXT:    psrlw $1, %xmm1
+; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE3-NEXT:    psubb %xmm1, %xmm0
+; SSE3-NEXT:    movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
+; SSE3-NEXT:    movdqa %xmm0, %xmm2
+; SSE3-NEXT:    pand %xmm1, %xmm2
+; SSE3-NEXT:    psrlw $2, %xmm0
+; SSE3-NEXT:    pand %xmm1, %xmm0
+; SSE3-NEXT:    paddb %xmm2, %xmm0
+; SSE3-NEXT:    movdqa %xmm0, %xmm1
+; SSE3-NEXT:    psrlw $4, %xmm1
+; SSE3-NEXT:    paddb %xmm0, %xmm1
+; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE3-NEXT:    pxor %xmm0, %xmm0
+; SSE3-NEXT:    movdqa %xmm1, %xmm2
+; SSE3-NEXT:    punpckhdq {{.*#+}} xmm2 = xmm2[2],xmm0[2],xmm2[3],xmm0[3]
+; SSE3-NEXT:    psadbw %xmm0, %xmm2
+; SSE3-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
+; SSE3-NEXT:    psadbw %xmm0, %xmm1
+; SSE3-NEXT:    packuswb %xmm2, %xmm1
+; SSE3-NEXT:    pcmpeqd {{.*}}(%rip), %xmm1
+; SSE3-NEXT:    movdqa %xmm1, %xmm0
+; SSE3-NEXT:    retq
+;
+; SSSE3-LABEL: eq_1_v4i32:
+; SSSE3:       # %bb.0:
+; SSSE3-NEXT:    movdqa {{.*#+}} xmm2 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; SSSE3-NEXT:    movdqa %xmm0, %xmm3
+; SSSE3-NEXT:    pand %xmm2, %xmm3
+; SSSE3-NEXT:    movdqa {{.*#+}} xmm1 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; SSSE3-NEXT:    movdqa %xmm1, %xmm4
+; SSSE3-NEXT:    pshufb %xmm3, %xmm4
+; SSSE3-NEXT:    psrlw $4, %xmm0
+; SSSE3-NEXT:    pand %xmm2, %xmm0
+; SSSE3-NEXT:    pshufb %xmm0, %xmm1
+; SSSE3-NEXT:    paddb %xmm4, %xmm1
+; SSSE3-NEXT:    pxor %xmm0, %xmm0
+; SSSE3-NEXT:    movdqa %xmm1, %xmm2
+; SSSE3-NEXT:    punpckhdq {{.*#+}} xmm2 = xmm2[2],xmm0[2],xmm2[3],xmm0[3]
+; SSSE3-NEXT:    psadbw %xmm0, %xmm2
+; SSSE3-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
+; SSSE3-NEXT:    psadbw %xmm0, %xmm1
+; SSSE3-NEXT:    packuswb %xmm2, %xmm1
+; SSSE3-NEXT:    pcmpeqd {{.*}}(%rip), %xmm1
+; SSSE3-NEXT:    movdqa %xmm1, %xmm0
+; SSSE3-NEXT:    retq
+;
+; SSE41-LABEL: eq_1_v4i32:
+; SSE41:       # %bb.0:
+; SSE41-NEXT:    movdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; SSE41-NEXT:    movdqa %xmm0, %xmm2
+; SSE41-NEXT:    pand %xmm1, %xmm2
+; SSE41-NEXT:    movdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; SSE41-NEXT:    movdqa %xmm3, %xmm4
+; SSE41-NEXT:    pshufb %xmm2, %xmm4
+; SSE41-NEXT:    psrlw $4, %xmm0
+; SSE41-NEXT:    pand %xmm1, %xmm0
+; SSE41-NEXT:    pshufb %xmm0, %xmm3
+; SSE41-NEXT:    paddb %xmm4, %xmm3
+; SSE41-NEXT:    pxor %xmm1, %xmm1
+; SSE41-NEXT:    pmovzxdq {{.*#+}} xmm0 = xmm3[0],zero,xmm3[1],zero
+; SSE41-NEXT:    punpckhdq {{.*#+}} xmm3 = xmm3[2],xmm1[2],xmm3[3],xmm1[3]
+; SSE41-NEXT:    psadbw %xmm1, %xmm3
+; SSE41-NEXT:    psadbw %xmm1, %xmm0
+; SSE41-NEXT:    packuswb %xmm3, %xmm0
+; SSE41-NEXT:    pcmpeqd {{.*}}(%rip), %xmm0
+; SSE41-NEXT:    retq
+;
+; AVX1-LABEL: eq_1_v4i32:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX1-NEXT:    vpaddb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX1-NEXT:    vpunpckhdq {{.*#+}} xmm2 = xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX1-NEXT:    vpsadbw %xmm1, %xmm2, %xmm2
+; AVX1-NEXT:    vpmovzxdq {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero
+; AVX1-NEXT:    vpsadbw %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpackuswb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpcmpeqd {{.*}}(%rip), %xmm0, %xmm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: eq_1_v4i32:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX2-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX2-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX2-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX2-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX2-NEXT:    vpaddb %xmm2, %xmm0, %xmm0
+; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX2-NEXT:    vpunpckhdq {{.*#+}} xmm2 = xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX2-NEXT:    vpsadbw %xmm1, %xmm2, %xmm2
+; AVX2-NEXT:    vpmovzxdq {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero
+; AVX2-NEXT:    vpsadbw %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vpackuswb %xmm2, %xmm0, %xmm0
+; AVX2-NEXT:    vpbroadcastd {{.*#+}} xmm1 = [1,1,1,1]
+; AVX2-NEXT:    vpcmpeqd %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: eq_1_v4i32:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpopcntd %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpbroadcastd {{.*#+}} xmm1 = [1,1,1,1]
+; AVX512VPOPCNTDQ-NEXT:    vpcmpeqd %xmm1, %xmm0, %xmm0
+; AVX512VPOPCNTDQ-NEXT:    vzeroupper
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; AVX512VPOPCNTDQVL-LABEL: eq_1_v4i32:
+; AVX512VPOPCNTDQVL:       # %bb.0:
+; AVX512VPOPCNTDQVL-NEXT:    vpopcntd %xmm0, %xmm0
+; AVX512VPOPCNTDQVL-NEXT:    vpbroadcastd {{.*#+}} xmm1 = [1,1,1,1]
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpeqd %xmm1, %xmm0, %xmm0
+; AVX512VPOPCNTDQVL-NEXT:    retq
+;
+; BITALG_NOVLX-LABEL: eq_1_v4i32:
+; BITALG_NOVLX:       # %bb.0:
+; BITALG_NOVLX-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
+; BITALG_NOVLX-NEXT:    vpopcntb %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG_NOVLX-NEXT:    vpunpckhdq {{.*#+}} xmm2 = xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; BITALG_NOVLX-NEXT:    vpsadbw %xmm1, %xmm2, %xmm2
+; BITALG_NOVLX-NEXT:    vpmovzxdq {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero
+; BITALG_NOVLX-NEXT:    vpsadbw %xmm1, %xmm0, %xmm0
+; BITALG_NOVLX-NEXT:    vpackuswb %xmm2, %xmm0, %xmm0
+; BITALG_NOVLX-NEXT:    vpbroadcastd {{.*#+}} xmm1 = [1,1,1,1]
+; BITALG_NOVLX-NEXT:    vpcmpeqd %xmm1, %xmm0, %xmm0
+; BITALG_NOVLX-NEXT:    vzeroupper
+; BITALG_NOVLX-NEXT:    retq
+;
+; BITALG-LABEL: eq_1_v4i32:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntb %xmm0, %xmm0
+; BITALG-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG-NEXT:    vpunpckhdq {{.*#+}} xmm2 = xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; BITALG-NEXT:    vpsadbw %xmm1, %xmm2, %xmm2
+; BITALG-NEXT:    vpmovzxdq {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero
+; BITALG-NEXT:    vpsadbw %xmm1, %xmm0, %xmm0
+; BITALG-NEXT:    vpackuswb %xmm2, %xmm0, %xmm0
+; BITALG-NEXT:    vpbroadcastd {{.*#+}} xmm1 = [1,1,1,1]
+; BITALG-NEXT:    vpcmpeqd %xmm1, %xmm0, %xmm0
+; BITALG-NEXT:    retq
+  %2 = tail call <4 x i32> @llvm.ctpop.v4i32(<4 x i32> %0)
+  %3 = icmp eq <4 x i32> %2, <i32 1, i32 1, i32 1, i32 1>
+  %4 = sext <4 x i1> %3 to <4 x i32>
+  ret <4 x i32> %4
+}
+
+define <4 x i32> @ne_1_v4i32(<4 x i32> %0) {
+; SSE2-LABEL: ne_1_v4i32:
+; SSE2:       # %bb.0:
+; SSE2-NEXT:    movdqa %xmm0, %xmm1
+; SSE2-NEXT:    psrlw $1, %xmm1
+; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE2-NEXT:    psubb %xmm1, %xmm0
+; SSE2-NEXT:    movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
+; SSE2-NEXT:    movdqa %xmm0, %xmm2
+; SSE2-NEXT:    pand %xmm1, %xmm2
+; SSE2-NEXT:    psrlw $2, %xmm0
+; SSE2-NEXT:    pand %xmm1, %xmm0
+; SSE2-NEXT:    paddb %xmm2, %xmm0
+; SSE2-NEXT:    movdqa %xmm0, %xmm1
+; SSE2-NEXT:    psrlw $4, %xmm1
+; SSE2-NEXT:    paddb %xmm0, %xmm1
+; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE2-NEXT:    pxor %xmm0, %xmm0
+; SSE2-NEXT:    movdqa %xmm1, %xmm2
+; SSE2-NEXT:    punpckhdq {{.*#+}} xmm2 = xmm2[2],xmm0[2],xmm2[3],xmm0[3]
+; SSE2-NEXT:    psadbw %xmm0, %xmm2
+; SSE2-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
+; SSE2-NEXT:    psadbw %xmm0, %xmm1
+; SSE2-NEXT:    packuswb %xmm2, %xmm1
+; SSE2-NEXT:    pcmpeqd {{.*}}(%rip), %xmm1
+; SSE2-NEXT:    pcmpeqd %xmm0, %xmm0
+; SSE2-NEXT:    pxor %xmm0, %xmm1
+; SSE2-NEXT:    movdqa %xmm1, %xmm0
+; SSE2-NEXT:    retq
+;
+; SSE3-LABEL: ne_1_v4i32:
+; SSE3:       # %bb.0:
+; SSE3-NEXT:    movdqa %xmm0, %xmm1
+; SSE3-NEXT:    psrlw $1, %xmm1
+; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE3-NEXT:    psubb %xmm1, %xmm0
+; SSE3-NEXT:    movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
+; SSE3-NEXT:    movdqa %xmm0, %xmm2
+; SSE3-NEXT:    pand %xmm1, %xmm2
+; SSE3-NEXT:    psrlw $2, %xmm0
+; SSE3-NEXT:    pand %xmm1, %xmm0
+; SSE3-NEXT:    paddb %xmm2, %xmm0
+; SSE3-NEXT:    movdqa %xmm0, %xmm1
+; SSE3-NEXT:    psrlw $4, %xmm1
+; SSE3-NEXT:    paddb %xmm0, %xmm1
+; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE3-NEXT:    pxor %xmm0, %xmm0
+; SSE3-NEXT:    movdqa %xmm1, %xmm2
+; SSE3-NEXT:    punpckhdq {{.*#+}} xmm2 = xmm2[2],xmm0[2],xmm2[3],xmm0[3]
+; SSE3-NEXT:    psadbw %xmm0, %xmm2
+; SSE3-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
+; SSE3-NEXT:    psadbw %xmm0, %xmm1
+; SSE3-NEXT:    packuswb %xmm2, %xmm1
+; SSE3-NEXT:    pcmpeqd {{.*}}(%rip), %xmm1
+; SSE3-NEXT:    pcmpeqd %xmm0, %xmm0
+; SSE3-NEXT:    pxor %xmm0, %xmm1
+; SSE3-NEXT:    movdqa %xmm1, %xmm0
+; SSE3-NEXT:    retq
+;
+; SSSE3-LABEL: ne_1_v4i32:
+; SSSE3:       # %bb.0:
+; SSSE3-NEXT:    movdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; SSSE3-NEXT:    movdqa %xmm0, %xmm2
+; SSSE3-NEXT:    pand %xmm1, %xmm2
+; SSSE3-NEXT:    movdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; SSSE3-NEXT:    movdqa %xmm3, %xmm4
+; SSSE3-NEXT:    pshufb %xmm2, %xmm4
+; SSSE3-NEXT:    psrlw $4, %xmm0
+; SSSE3-NEXT:    pand %xmm1, %xmm0
+; SSSE3-NEXT:    pshufb %xmm0, %xmm3
+; SSSE3-NEXT:    paddb %xmm4, %xmm3
+; SSSE3-NEXT:    pxor %xmm0, %xmm0
+; SSSE3-NEXT:    movdqa %xmm3, %xmm1
+; SSSE3-NEXT:    punpckhdq {{.*#+}} xmm1 = xmm1[2],xmm0[2],xmm1[3],xmm0[3]
+; SSSE3-NEXT:    psadbw %xmm0, %xmm1
+; SSSE3-NEXT:    punpckldq {{.*#+}} xmm3 = xmm3[0],xmm0[0],xmm3[1],xmm0[1]
+; SSSE3-NEXT:    psadbw %xmm0, %xmm3
+; SSSE3-NEXT:    packuswb %xmm1, %xmm3
+; SSSE3-NEXT:    pcmpeqd {{.*}}(%rip), %xmm3
+; SSSE3-NEXT:    pcmpeqd %xmm0, %xmm0
+; SSSE3-NEXT:    pxor %xmm3, %xmm0
+; SSSE3-NEXT:    retq
+;
+; SSE41-LABEL: ne_1_v4i32:
+; SSE41:       # %bb.0:
+; SSE41-NEXT:    movdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; SSE41-NEXT:    movdqa %xmm0, %xmm2
+; SSE41-NEXT:    pand %xmm1, %xmm2
+; SSE41-NEXT:    movdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; SSE41-NEXT:    movdqa %xmm3, %xmm4
+; SSE41-NEXT:    pshufb %xmm2, %xmm4
+; SSE41-NEXT:    psrlw $4, %xmm0
+; SSE41-NEXT:    pand %xmm1, %xmm0
+; SSE41-NEXT:    pshufb %xmm0, %xmm3
+; SSE41-NEXT:    paddb %xmm4, %xmm3
+; SSE41-NEXT:    pxor %xmm0, %xmm0
+; SSE41-NEXT:    pmovzxdq {{.*#+}} xmm1 = xmm3[0],zero,xmm3[1],zero
+; SSE41-NEXT:    punpckhdq {{.*#+}} xmm3 = xmm3[2],xmm0[2],xmm3[3],xmm0[3]
+; SSE41-NEXT:    psadbw %xmm0, %xmm3
+; SSE41-NEXT:    psadbw %xmm0, %xmm1
+; SSE41-NEXT:    packuswb %xmm3, %xmm1
+; SSE41-NEXT:    pcmpeqd {{.*}}(%rip), %xmm1
+; SSE41-NEXT:    pcmpeqd %xmm0, %xmm0
+; SSE41-NEXT:    pxor %xmm1, %xmm0
+; SSE41-NEXT:    retq
+;
+; AVX1-LABEL: ne_1_v4i32:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX1-NEXT:    vpaddb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX1-NEXT:    vpunpckhdq {{.*#+}} xmm2 = xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX1-NEXT:    vpsadbw %xmm1, %xmm2, %xmm2
+; AVX1-NEXT:    vpmovzxdq {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero
+; AVX1-NEXT:    vpsadbw %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpackuswb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpcmpeqd {{.*}}(%rip), %xmm0, %xmm0
+; AVX1-NEXT:    vpcmpeqd %xmm1, %xmm1, %xmm1
+; AVX1-NEXT:    vpxor %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: ne_1_v4i32:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX2-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX2-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX2-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX2-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX2-NEXT:    vpaddb %xmm2, %xmm0, %xmm0
+; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX2-NEXT:    vpunpckhdq {{.*#+}} xmm2 = xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX2-NEXT:    vpsadbw %xmm1, %xmm2, %xmm2
+; AVX2-NEXT:    vpmovzxdq {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero
+; AVX2-NEXT:    vpsadbw %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vpackuswb %xmm2, %xmm0, %xmm0
+; AVX2-NEXT:    vpbroadcastd {{.*#+}} xmm1 = [1,1,1,1]
+; AVX2-NEXT:    vpcmpeqd %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vpcmpeqd %xmm1, %xmm1, %xmm1
+; AVX2-NEXT:    vpxor %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: ne_1_v4i32:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpopcntd %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpbroadcastd {{.*#+}} xmm1 = [1,1,1,1]
+; AVX512VPOPCNTDQ-NEXT:    vpcmpeqd %xmm1, %xmm0, %xmm0
+; AVX512VPOPCNTDQ-NEXT:    vpternlogq $15, %zmm0, %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    # kill: def $xmm0 killed $xmm0 killed $zmm0
+; AVX512VPOPCNTDQ-NEXT:    vzeroupper
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; AVX512VPOPCNTDQVL-LABEL: ne_1_v4i32:
+; AVX512VPOPCNTDQVL:       # %bb.0:
+; AVX512VPOPCNTDQVL-NEXT:    vpopcntd %xmm0, %xmm0
+; AVX512VPOPCNTDQVL-NEXT:    vpbroadcastd {{.*#+}} xmm1 = [1,1,1,1]
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpeqd %xmm1, %xmm0, %xmm0
+; AVX512VPOPCNTDQVL-NEXT:    vpternlogq $15, %xmm0, %xmm0, %xmm0
+; AVX512VPOPCNTDQVL-NEXT:    retq
+;
+; BITALG_NOVLX-LABEL: ne_1_v4i32:
+; BITALG_NOVLX:       # %bb.0:
+; BITALG_NOVLX-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
+; BITALG_NOVLX-NEXT:    vpopcntb %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG_NOVLX-NEXT:    vpunpckhdq {{.*#+}} xmm2 = xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; BITALG_NOVLX-NEXT:    vpsadbw %xmm1, %xmm2, %xmm2
+; BITALG_NOVLX-NEXT:    vpmovzxdq {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero
+; BITALG_NOVLX-NEXT:    vpsadbw %xmm1, %xmm0, %xmm0
+; BITALG_NOVLX-NEXT:    vpackuswb %xmm2, %xmm0, %xmm0
+; BITALG_NOVLX-NEXT:    vpbroadcastd {{.*#+}} xmm1 = [1,1,1,1]
+; BITALG_NOVLX-NEXT:    vpcmpeqd %xmm1, %xmm0, %xmm0
+; BITALG_NOVLX-NEXT:    vpternlogq $15, %zmm0, %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    # kill: def $xmm0 killed $xmm0 killed $zmm0
+; BITALG_NOVLX-NEXT:    vzeroupper
+; BITALG_NOVLX-NEXT:    retq
+;
+; BITALG-LABEL: ne_1_v4i32:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntb %xmm0, %xmm0
+; BITALG-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG-NEXT:    vpunpckhdq {{.*#+}} xmm2 = xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; BITALG-NEXT:    vpsadbw %xmm1, %xmm2, %xmm2
+; BITALG-NEXT:    vpmovzxdq {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero
+; BITALG-NEXT:    vpsadbw %xmm1, %xmm0, %xmm0
+; BITALG-NEXT:    vpackuswb %xmm2, %xmm0, %xmm0
+; BITALG-NEXT:    vpbroadcastd {{.*#+}} xmm1 = [1,1,1,1]
+; BITALG-NEXT:    vpcmpeqd %xmm1, %xmm0, %xmm0
+; BITALG-NEXT:    vpternlogq $15, %xmm0, %xmm0, %xmm0
+; BITALG-NEXT:    retq
+  %2 = tail call <4 x i32> @llvm.ctpop.v4i32(<4 x i32> %0)
+  %3 = icmp ne <4 x i32> %2, <i32 1, i32 1, i32 1, i32 1>
+  %4 = sext <4 x i1> %3 to <4 x i32>
+  ret <4 x i32> %4
+}
+
+define <8 x i16> @ult_2_v8i16(<8 x i16> %0) {
+; SSE2-LABEL: ult_2_v8i16:
+; SSE2:       # %bb.0:
+; SSE2-NEXT:    movdqa %xmm0, %xmm1
+; SSE2-NEXT:    psrlw $1, %xmm1
+; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE2-NEXT:    psubb %xmm1, %xmm0
+; SSE2-NEXT:    movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
+; SSE2-NEXT:    movdqa %xmm0, %xmm2
+; SSE2-NEXT:    pand %xmm1, %xmm2
+; SSE2-NEXT:    psrlw $2, %xmm0
+; SSE2-NEXT:    pand %xmm1, %xmm0
+; SSE2-NEXT:    paddb %xmm2, %xmm0
+; SSE2-NEXT:    movdqa %xmm0, %xmm1
+; SSE2-NEXT:    psrlw $4, %xmm1
+; SSE2-NEXT:    paddb %xmm0, %xmm1
+; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE2-NEXT:    movdqa %xmm1, %xmm2
+; SSE2-NEXT:    psllw $8, %xmm2
+; SSE2-NEXT:    paddb %xmm1, %xmm2
+; SSE2-NEXT:    psrlw $8, %xmm2
+; SSE2-NEXT:    movdqa {{.*#+}} xmm0 = [2,2,2,2,2,2,2,2]
+; SSE2-NEXT:    pcmpgtw %xmm2, %xmm0
+; SSE2-NEXT:    retq
+;
+; SSE3-LABEL: ult_2_v8i16:
+; SSE3:       # %bb.0:
+; SSE3-NEXT:    movdqa %xmm0, %xmm1
+; SSE3-NEXT:    psrlw $1, %xmm1
+; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE3-NEXT:    psubb %xmm1, %xmm0
+; SSE3-NEXT:    movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
+; SSE3-NEXT:    movdqa %xmm0, %xmm2
+; SSE3-NEXT:    pand %xmm1, %xmm2
+; SSE3-NEXT:    psrlw $2, %xmm0
+; SSE3-NEXT:    pand %xmm1, %xmm0
+; SSE3-NEXT:    paddb %xmm2, %xmm0
+; SSE3-NEXT:    movdqa %xmm0, %xmm1
+; SSE3-NEXT:    psrlw $4, %xmm1
+; SSE3-NEXT:    paddb %xmm0, %xmm1
+; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE3-NEXT:    movdqa %xmm1, %xmm2
+; SSE3-NEXT:    psllw $8, %xmm2
+; SSE3-NEXT:    paddb %xmm1, %xmm2
+; SSE3-NEXT:    psrlw $8, %xmm2
+; SSE3-NEXT:    movdqa {{.*#+}} xmm0 = [2,2,2,2,2,2,2,2]
+; SSE3-NEXT:    pcmpgtw %xmm2, %xmm0
+; SSE3-NEXT:    retq
+;
+; SSSE3-LABEL: ult_2_v8i16:
+; SSSE3:       # %bb.0:
+; SSSE3-NEXT:    movdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; SSSE3-NEXT:    movdqa %xmm0, %xmm2
+; SSSE3-NEXT:    pand %xmm1, %xmm2
+; SSSE3-NEXT:    movdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; SSSE3-NEXT:    movdqa %xmm3, %xmm4
+; SSSE3-NEXT:    pshufb %xmm2, %xmm4
+; SSSE3-NEXT:    psrlw $4, %xmm0
+; SSSE3-NEXT:    pand %xmm1, %xmm0
+; SSSE3-NEXT:    pshufb %xmm0, %xmm3
+; SSSE3-NEXT:    paddb %xmm4, %xmm3
+; SSSE3-NEXT:    movdqa %xmm3, %xmm1
+; SSSE3-NEXT:    psllw $8, %xmm1
+; SSSE3-NEXT:    paddb %xmm3, %xmm1
+; SSSE3-NEXT:    psrlw $8, %xmm1
+; SSSE3-NEXT:    movdqa {{.*#+}} xmm0 = [2,2,2,2,2,2,2,2]
+; SSSE3-NEXT:    pcmpgtw %xmm1, %xmm0
+; SSSE3-NEXT:    retq
+;
+; SSE41-LABEL: ult_2_v8i16:
+; SSE41:       # %bb.0:
+; SSE41-NEXT:    movdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; SSE41-NEXT:    movdqa %xmm0, %xmm2
+; SSE41-NEXT:    pand %xmm1, %xmm2
+; SSE41-NEXT:    movdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; SSE41-NEXT:    movdqa %xmm3, %xmm4
+; SSE41-NEXT:    pshufb %xmm2, %xmm4
+; SSE41-NEXT:    psrlw $4, %xmm0
+; SSE41-NEXT:    pand %xmm1, %xmm0
+; SSE41-NEXT:    pshufb %xmm0, %xmm3
+; SSE41-NEXT:    paddb %xmm4, %xmm3
+; SSE41-NEXT:    movdqa %xmm3, %xmm1
+; SSE41-NEXT:    psllw $8, %xmm1
+; SSE41-NEXT:    paddb %xmm3, %xmm1
+; SSE41-NEXT:    psrlw $8, %xmm1
+; SSE41-NEXT:    movdqa {{.*#+}} xmm0 = [2,2,2,2,2,2,2,2]
+; SSE41-NEXT:    pcmpgtw %xmm1, %xmm0
+; SSE41-NEXT:    retq
+;
+; AVX1-LABEL: ult_2_v8i16:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX1-NEXT:    vpaddb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpsllw $8, %xmm0, %xmm1
+; AVX1-NEXT:    vpaddb %xmm0, %xmm1, %xmm0
+; AVX1-NEXT:    vpsrlw $8, %xmm0, %xmm0
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [2,2,2,2,2,2,2,2]
+; AVX1-NEXT:    vpcmpgtw %xmm0, %xmm1, %xmm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: ult_2_v8i16:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX2-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX2-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX2-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX2-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX2-NEXT:    vpaddb %xmm2, %xmm0, %xmm0
+; AVX2-NEXT:    vpsllw $8, %xmm0, %xmm1
+; AVX2-NEXT:    vpaddb %xmm0, %xmm1, %xmm0
+; AVX2-NEXT:    vpsrlw $8, %xmm0, %xmm0
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm1 = [2,2,2,2,2,2,2,2]
+; AVX2-NEXT:    vpcmpgtw %xmm0, %xmm1, %xmm0
+; AVX2-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: ult_2_v8i16:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
+; AVX512VPOPCNTDQ-NEXT:    vpopcntd %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpmovdw %zmm0, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    vmovdqa {{.*#+}} xmm1 = [2,2,2,2,2,2,2,2]
+; AVX512VPOPCNTDQ-NEXT:    vpcmpgtw %xmm0, %xmm1, %xmm0
+; AVX512VPOPCNTDQ-NEXT:    vzeroupper
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; AVX512VPOPCNTDQVL-LABEL: ult_2_v8i16:
+; AVX512VPOPCNTDQVL:       # %bb.0:
+; AVX512VPOPCNTDQVL-NEXT:    vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
+; AVX512VPOPCNTDQVL-NEXT:    vpopcntd %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vpmovdw %ymm0, %xmm0
+; AVX512VPOPCNTDQVL-NEXT:    vmovdqa {{.*#+}} xmm1 = [2,2,2,2,2,2,2,2]
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpgtw %xmm0, %xmm1, %xmm0
+; AVX512VPOPCNTDQVL-NEXT:    vzeroupper
+; AVX512VPOPCNTDQVL-NEXT:    retq
+;
+; BITALG_NOVLX-LABEL: ult_2_v8i16:
+; BITALG_NOVLX:       # %bb.0:
+; BITALG_NOVLX-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
+; BITALG_NOVLX-NEXT:    vpopcntw %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    vmovdqa {{.*#+}} xmm1 = [2,2,2,2,2,2,2,2]
+; BITALG_NOVLX-NEXT:    vpcmpgtw %xmm0, %xmm1, %xmm0
+; BITALG_NOVLX-NEXT:    vzeroupper
+; BITALG_NOVLX-NEXT:    retq
+;
+; BITALG-LABEL: ult_2_v8i16:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntw %xmm0, %xmm0
+; BITALG-NEXT:    vpcmpltuw {{.*}}(%rip), %xmm0, %k0
+; BITALG-NEXT:    vpmovm2w %k0, %xmm0
+; BITALG-NEXT:    retq
+  %2 = tail call <8 x i16> @llvm.ctpop.v8i16(<8 x i16> %0)
+  %3 = icmp ult <8 x i16> %2, <i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2>
+  %4 = sext <8 x i1> %3 to <8 x i16>
+  ret <8 x i16> %4
+}
+
+define <8 x i16> @ugt_1_v8i16(<8 x i16> %0) {
+; SSE2-LABEL: ugt_1_v8i16:
+; SSE2:       # %bb.0:
+; SSE2-NEXT:    movdqa %xmm0, %xmm1
+; SSE2-NEXT:    psrlw $1, %xmm1
+; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE2-NEXT:    psubb %xmm1, %xmm0
+; SSE2-NEXT:    movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
+; SSE2-NEXT:    movdqa %xmm0, %xmm2
+; SSE2-NEXT:    pand %xmm1, %xmm2
+; SSE2-NEXT:    psrlw $2, %xmm0
+; SSE2-NEXT:    pand %xmm1, %xmm0
+; SSE2-NEXT:    paddb %xmm2, %xmm0
+; SSE2-NEXT:    movdqa %xmm0, %xmm1
+; SSE2-NEXT:    psrlw $4, %xmm1
+; SSE2-NEXT:    paddb %xmm0, %xmm1
+; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE2-NEXT:    movdqa %xmm1, %xmm0
+; SSE2-NEXT:    psllw $8, %xmm0
+; SSE2-NEXT:    paddb %xmm1, %xmm0
+; SSE2-NEXT:    psrlw $8, %xmm0
+; SSE2-NEXT:    pcmpgtw {{.*}}(%rip), %xmm0
+; SSE2-NEXT:    retq
+;
+; SSE3-LABEL: ugt_1_v8i16:
+; SSE3:       # %bb.0:
+; SSE3-NEXT:    movdqa %xmm0, %xmm1
+; SSE3-NEXT:    psrlw $1, %xmm1
+; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE3-NEXT:    psubb %xmm1, %xmm0
+; SSE3-NEXT:    movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
+; SSE3-NEXT:    movdqa %xmm0, %xmm2
+; SSE3-NEXT:    pand %xmm1, %xmm2
+; SSE3-NEXT:    psrlw $2, %xmm0
+; SSE3-NEXT:    pand %xmm1, %xmm0
+; SSE3-NEXT:    paddb %xmm2, %xmm0
+; SSE3-NEXT:    movdqa %xmm0, %xmm1
+; SSE3-NEXT:    psrlw $4, %xmm1
+; SSE3-NEXT:    paddb %xmm0, %xmm1
+; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE3-NEXT:    movdqa %xmm1, %xmm0
+; SSE3-NEXT:    psllw $8, %xmm0
+; SSE3-NEXT:    paddb %xmm1, %xmm0
+; SSE3-NEXT:    psrlw $8, %xmm0
+; SSE3-NEXT:    pcmpgtw {{.*}}(%rip), %xmm0
+; SSE3-NEXT:    retq
+;
+; SSSE3-LABEL: ugt_1_v8i16:
+; SSSE3:       # %bb.0:
+; SSSE3-NEXT:    movdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; SSSE3-NEXT:    movdqa %xmm0, %xmm2
+; SSSE3-NEXT:    pand %xmm1, %xmm2
+; SSSE3-NEXT:    movdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; SSSE3-NEXT:    movdqa %xmm3, %xmm4
+; SSSE3-NEXT:    pshufb %xmm2, %xmm4
+; SSSE3-NEXT:    psrlw $4, %xmm0
+; SSSE3-NEXT:    pand %xmm1, %xmm0
+; SSSE3-NEXT:    pshufb %xmm0, %xmm3
+; SSSE3-NEXT:    paddb %xmm4, %xmm3
+; SSSE3-NEXT:    movdqa %xmm3, %xmm0
+; SSSE3-NEXT:    psllw $8, %xmm0
+; SSSE3-NEXT:    paddb %xmm3, %xmm0
+; SSSE3-NEXT:    psrlw $8, %xmm0
+; SSSE3-NEXT:    pcmpgtw {{.*}}(%rip), %xmm0
+; SSSE3-NEXT:    retq
+;
+; SSE41-LABEL: ugt_1_v8i16:
+; SSE41:       # %bb.0:
+; SSE41-NEXT:    movdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; SSE41-NEXT:    movdqa %xmm0, %xmm2
+; SSE41-NEXT:    pand %xmm1, %xmm2
+; SSE41-NEXT:    movdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; SSE41-NEXT:    movdqa %xmm3, %xmm4
+; SSE41-NEXT:    pshufb %xmm2, %xmm4
+; SSE41-NEXT:    psrlw $4, %xmm0
+; SSE41-NEXT:    pand %xmm1, %xmm0
+; SSE41-NEXT:    pshufb %xmm0, %xmm3
+; SSE41-NEXT:    paddb %xmm4, %xmm3
+; SSE41-NEXT:    movdqa %xmm3, %xmm0
+; SSE41-NEXT:    psllw $8, %xmm0
+; SSE41-NEXT:    paddb %xmm3, %xmm0
+; SSE41-NEXT:    psrlw $8, %xmm0
+; SSE41-NEXT:    pcmpgtw {{.*}}(%rip), %xmm0
+; SSE41-NEXT:    retq
+;
+; AVX1-LABEL: ugt_1_v8i16:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX1-NEXT:    vpaddb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpsllw $8, %xmm0, %xmm1
+; AVX1-NEXT:    vpaddb %xmm0, %xmm1, %xmm0
+; AVX1-NEXT:    vpsrlw $8, %xmm0, %xmm0
+; AVX1-NEXT:    vpcmpgtw {{.*}}(%rip), %xmm0, %xmm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: ugt_1_v8i16:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX2-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX2-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX2-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX2-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX2-NEXT:    vpaddb %xmm2, %xmm0, %xmm0
+; AVX2-NEXT:    vpsllw $8, %xmm0, %xmm1
+; AVX2-NEXT:    vpaddb %xmm0, %xmm1, %xmm0
+; AVX2-NEXT:    vpsrlw $8, %xmm0, %xmm0
+; AVX2-NEXT:    vpcmpgtw {{.*}}(%rip), %xmm0, %xmm0
+; AVX2-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: ugt_1_v8i16:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
+; AVX512VPOPCNTDQ-NEXT:    vpopcntd %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpmovdw %zmm0, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    vpcmpgtw {{.*}}(%rip), %xmm0, %xmm0
+; AVX512VPOPCNTDQ-NEXT:    vzeroupper
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; AVX512VPOPCNTDQVL-LABEL: ugt_1_v8i16:
+; AVX512VPOPCNTDQVL:       # %bb.0:
+; AVX512VPOPCNTDQVL-NEXT:    vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
+; AVX512VPOPCNTDQVL-NEXT:    vpopcntd %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vpmovdw %ymm0, %xmm0
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpgtw {{.*}}(%rip), %xmm0, %xmm0
+; AVX512VPOPCNTDQVL-NEXT:    vzeroupper
+; AVX512VPOPCNTDQVL-NEXT:    retq
+;
+; BITALG_NOVLX-LABEL: ugt_1_v8i16:
+; BITALG_NOVLX:       # %bb.0:
+; BITALG_NOVLX-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
+; BITALG_NOVLX-NEXT:    vpopcntw %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    vpcmpgtw {{.*}}(%rip), %xmm0, %xmm0
+; BITALG_NOVLX-NEXT:    vzeroupper
+; BITALG_NOVLX-NEXT:    retq
+;
+; BITALG-LABEL: ugt_1_v8i16:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntw %xmm0, %xmm0
+; BITALG-NEXT:    vpcmpnleuw {{.*}}(%rip), %xmm0, %k0
+; BITALG-NEXT:    vpmovm2w %k0, %xmm0
+; BITALG-NEXT:    retq
+  %2 = tail call <8 x i16> @llvm.ctpop.v8i16(<8 x i16> %0)
+  %3 = icmp ugt <8 x i16> %2, <i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1>
+  %4 = sext <8 x i1> %3 to <8 x i16>
+  ret <8 x i16> %4
+}
+
+define <8 x i16> @eq_1_v8i16(<8 x i16> %0) {
+; SSE2-LABEL: eq_1_v8i16:
+; SSE2:       # %bb.0:
+; SSE2-NEXT:    movdqa %xmm0, %xmm1
+; SSE2-NEXT:    psrlw $1, %xmm1
+; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE2-NEXT:    psubb %xmm1, %xmm0
+; SSE2-NEXT:    movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
+; SSE2-NEXT:    movdqa %xmm0, %xmm2
+; SSE2-NEXT:    pand %xmm1, %xmm2
+; SSE2-NEXT:    psrlw $2, %xmm0
+; SSE2-NEXT:    pand %xmm1, %xmm0
+; SSE2-NEXT:    paddb %xmm2, %xmm0
+; SSE2-NEXT:    movdqa %xmm0, %xmm1
+; SSE2-NEXT:    psrlw $4, %xmm1
+; SSE2-NEXT:    paddb %xmm0, %xmm1
+; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE2-NEXT:    movdqa %xmm1, %xmm0
+; SSE2-NEXT:    psllw $8, %xmm0
+; SSE2-NEXT:    paddb %xmm1, %xmm0
+; SSE2-NEXT:    psrlw $8, %xmm0
+; SSE2-NEXT:    pcmpeqw {{.*}}(%rip), %xmm0
+; SSE2-NEXT:    retq
+;
+; SSE3-LABEL: eq_1_v8i16:
+; SSE3:       # %bb.0:
+; SSE3-NEXT:    movdqa %xmm0, %xmm1
+; SSE3-NEXT:    psrlw $1, %xmm1
+; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE3-NEXT:    psubb %xmm1, %xmm0
+; SSE3-NEXT:    movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
+; SSE3-NEXT:    movdqa %xmm0, %xmm2
+; SSE3-NEXT:    pand %xmm1, %xmm2
+; SSE3-NEXT:    psrlw $2, %xmm0
+; SSE3-NEXT:    pand %xmm1, %xmm0
+; SSE3-NEXT:    paddb %xmm2, %xmm0
+; SSE3-NEXT:    movdqa %xmm0, %xmm1
+; SSE3-NEXT:    psrlw $4, %xmm1
+; SSE3-NEXT:    paddb %xmm0, %xmm1
+; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE3-NEXT:    movdqa %xmm1, %xmm0
+; SSE3-NEXT:    psllw $8, %xmm0
+; SSE3-NEXT:    paddb %xmm1, %xmm0
+; SSE3-NEXT:    psrlw $8, %xmm0
+; SSE3-NEXT:    pcmpeqw {{.*}}(%rip), %xmm0
+; SSE3-NEXT:    retq
+;
+; SSSE3-LABEL: eq_1_v8i16:
+; SSSE3:       # %bb.0:
+; SSSE3-NEXT:    movdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; SSSE3-NEXT:    movdqa %xmm0, %xmm2
+; SSSE3-NEXT:    pand %xmm1, %xmm2
+; SSSE3-NEXT:    movdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; SSSE3-NEXT:    movdqa %xmm3, %xmm4
+; SSSE3-NEXT:    pshufb %xmm2, %xmm4
+; SSSE3-NEXT:    psrlw $4, %xmm0
+; SSSE3-NEXT:    pand %xmm1, %xmm0
+; SSSE3-NEXT:    pshufb %xmm0, %xmm3
+; SSSE3-NEXT:    paddb %xmm4, %xmm3
+; SSSE3-NEXT:    movdqa %xmm3, %xmm0
+; SSSE3-NEXT:    psllw $8, %xmm0
+; SSSE3-NEXT:    paddb %xmm3, %xmm0
+; SSSE3-NEXT:    psrlw $8, %xmm0
+; SSSE3-NEXT:    pcmpeqw {{.*}}(%rip), %xmm0
+; SSSE3-NEXT:    retq
+;
+; SSE41-LABEL: eq_1_v8i16:
+; SSE41:       # %bb.0:
+; SSE41-NEXT:    movdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; SSE41-NEXT:    movdqa %xmm0, %xmm2
+; SSE41-NEXT:    pand %xmm1, %xmm2
+; SSE41-NEXT:    movdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; SSE41-NEXT:    movdqa %xmm3, %xmm4
+; SSE41-NEXT:    pshufb %xmm2, %xmm4
+; SSE41-NEXT:    psrlw $4, %xmm0
+; SSE41-NEXT:    pand %xmm1, %xmm0
+; SSE41-NEXT:    pshufb %xmm0, %xmm3
+; SSE41-NEXT:    paddb %xmm4, %xmm3
+; SSE41-NEXT:    movdqa %xmm3, %xmm0
+; SSE41-NEXT:    psllw $8, %xmm0
+; SSE41-NEXT:    paddb %xmm3, %xmm0
+; SSE41-NEXT:    psrlw $8, %xmm0
+; SSE41-NEXT:    pcmpeqw {{.*}}(%rip), %xmm0
+; SSE41-NEXT:    retq
+;
+; AVX1-LABEL: eq_1_v8i16:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX1-NEXT:    vpaddb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpsllw $8, %xmm0, %xmm1
+; AVX1-NEXT:    vpaddb %xmm0, %xmm1, %xmm0
+; AVX1-NEXT:    vpsrlw $8, %xmm0, %xmm0
+; AVX1-NEXT:    vpcmpeqw {{.*}}(%rip), %xmm0, %xmm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: eq_1_v8i16:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX2-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX2-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX2-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX2-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX2-NEXT:    vpaddb %xmm2, %xmm0, %xmm0
+; AVX2-NEXT:    vpsllw $8, %xmm0, %xmm1
+; AVX2-NEXT:    vpaddb %xmm0, %xmm1, %xmm0
+; AVX2-NEXT:    vpsrlw $8, %xmm0, %xmm0
+; AVX2-NEXT:    vpcmpeqw {{.*}}(%rip), %xmm0, %xmm0
+; AVX2-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: eq_1_v8i16:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
+; AVX512VPOPCNTDQ-NEXT:    vpopcntd %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpmovdw %zmm0, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    vpcmpeqw {{.*}}(%rip), %xmm0, %xmm0
+; AVX512VPOPCNTDQ-NEXT:    vzeroupper
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; AVX512VPOPCNTDQVL-LABEL: eq_1_v8i16:
+; AVX512VPOPCNTDQVL:       # %bb.0:
+; AVX512VPOPCNTDQVL-NEXT:    vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
+; AVX512VPOPCNTDQVL-NEXT:    vpopcntd %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vpmovdw %ymm0, %xmm0
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpeqw {{.*}}(%rip), %xmm0, %xmm0
+; AVX512VPOPCNTDQVL-NEXT:    vzeroupper
+; AVX512VPOPCNTDQVL-NEXT:    retq
+;
+; BITALG_NOVLX-LABEL: eq_1_v8i16:
+; BITALG_NOVLX:       # %bb.0:
+; BITALG_NOVLX-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
+; BITALG_NOVLX-NEXT:    vpopcntw %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    vpcmpeqw {{.*}}(%rip), %xmm0, %xmm0
+; BITALG_NOVLX-NEXT:    vzeroupper
+; BITALG_NOVLX-NEXT:    retq
+;
+; BITALG-LABEL: eq_1_v8i16:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntw %xmm0, %xmm0
+; BITALG-NEXT:    vpcmpeqw {{.*}}(%rip), %xmm0, %xmm0
+; BITALG-NEXT:    retq
+  %2 = tail call <8 x i16> @llvm.ctpop.v8i16(<8 x i16> %0)
+  %3 = icmp eq <8 x i16> %2, <i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1>
+  %4 = sext <8 x i1> %3 to <8 x i16>
+  ret <8 x i16> %4
+}
+
+define <8 x i16> @ne_1_v8i16(<8 x i16> %0) {
+; SSE2-LABEL: ne_1_v8i16:
+; SSE2:       # %bb.0:
+; SSE2-NEXT:    movdqa %xmm0, %xmm1
+; SSE2-NEXT:    psrlw $1, %xmm1
+; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE2-NEXT:    psubb %xmm1, %xmm0
+; SSE2-NEXT:    movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
+; SSE2-NEXT:    movdqa %xmm0, %xmm2
+; SSE2-NEXT:    pand %xmm1, %xmm2
+; SSE2-NEXT:    psrlw $2, %xmm0
+; SSE2-NEXT:    pand %xmm1, %xmm0
+; SSE2-NEXT:    paddb %xmm2, %xmm0
+; SSE2-NEXT:    movdqa %xmm0, %xmm1
+; SSE2-NEXT:    psrlw $4, %xmm1
+; SSE2-NEXT:    paddb %xmm0, %xmm1
+; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE2-NEXT:    movdqa %xmm1, %xmm0
+; SSE2-NEXT:    psllw $8, %xmm0
+; SSE2-NEXT:    paddb %xmm1, %xmm0
+; SSE2-NEXT:    psrlw $8, %xmm0
+; SSE2-NEXT:    pcmpeqw {{.*}}(%rip), %xmm0
+; SSE2-NEXT:    pcmpeqd %xmm1, %xmm1
+; SSE2-NEXT:    pxor %xmm1, %xmm0
+; SSE2-NEXT:    retq
+;
+; SSE3-LABEL: ne_1_v8i16:
+; SSE3:       # %bb.0:
+; SSE3-NEXT:    movdqa %xmm0, %xmm1
+; SSE3-NEXT:    psrlw $1, %xmm1
+; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE3-NEXT:    psubb %xmm1, %xmm0
+; SSE3-NEXT:    movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
+; SSE3-NEXT:    movdqa %xmm0, %xmm2
+; SSE3-NEXT:    pand %xmm1, %xmm2
+; SSE3-NEXT:    psrlw $2, %xmm0
+; SSE3-NEXT:    pand %xmm1, %xmm0
+; SSE3-NEXT:    paddb %xmm2, %xmm0
+; SSE3-NEXT:    movdqa %xmm0, %xmm1
+; SSE3-NEXT:    psrlw $4, %xmm1
+; SSE3-NEXT:    paddb %xmm0, %xmm1
+; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE3-NEXT:    movdqa %xmm1, %xmm0
+; SSE3-NEXT:    psllw $8, %xmm0
+; SSE3-NEXT:    paddb %xmm1, %xmm0
+; SSE3-NEXT:    psrlw $8, %xmm0
+; SSE3-NEXT:    pcmpeqw {{.*}}(%rip), %xmm0
+; SSE3-NEXT:    pcmpeqd %xmm1, %xmm1
+; SSE3-NEXT:    pxor %xmm1, %xmm0
+; SSE3-NEXT:    retq
+;
+; SSSE3-LABEL: ne_1_v8i16:
+; SSSE3:       # %bb.0:
+; SSSE3-NEXT:    movdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; SSSE3-NEXT:    movdqa %xmm0, %xmm2
+; SSSE3-NEXT:    pand %xmm1, %xmm2
+; SSSE3-NEXT:    movdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; SSSE3-NEXT:    movdqa %xmm3, %xmm4
+; SSSE3-NEXT:    pshufb %xmm2, %xmm4
+; SSSE3-NEXT:    psrlw $4, %xmm0
+; SSSE3-NEXT:    pand %xmm1, %xmm0
+; SSSE3-NEXT:    pshufb %xmm0, %xmm3
+; SSSE3-NEXT:    paddb %xmm4, %xmm3
+; SSSE3-NEXT:    movdqa %xmm3, %xmm1
+; SSSE3-NEXT:    psllw $8, %xmm1
+; SSSE3-NEXT:    paddb %xmm3, %xmm1
+; SSSE3-NEXT:    psrlw $8, %xmm1
+; SSSE3-NEXT:    pcmpeqw {{.*}}(%rip), %xmm1
+; SSSE3-NEXT:    pcmpeqd %xmm0, %xmm0
+; SSSE3-NEXT:    pxor %xmm1, %xmm0
+; SSSE3-NEXT:    retq
+;
+; SSE41-LABEL: ne_1_v8i16:
+; SSE41:       # %bb.0:
+; SSE41-NEXT:    movdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; SSE41-NEXT:    movdqa %xmm0, %xmm2
+; SSE41-NEXT:    pand %xmm1, %xmm2
+; SSE41-NEXT:    movdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; SSE41-NEXT:    movdqa %xmm3, %xmm4
+; SSE41-NEXT:    pshufb %xmm2, %xmm4
+; SSE41-NEXT:    psrlw $4, %xmm0
+; SSE41-NEXT:    pand %xmm1, %xmm0
+; SSE41-NEXT:    pshufb %xmm0, %xmm3
+; SSE41-NEXT:    paddb %xmm4, %xmm3
+; SSE41-NEXT:    movdqa %xmm3, %xmm1
+; SSE41-NEXT:    psllw $8, %xmm1
+; SSE41-NEXT:    paddb %xmm3, %xmm1
+; SSE41-NEXT:    psrlw $8, %xmm1
+; SSE41-NEXT:    pcmpeqw {{.*}}(%rip), %xmm1
+; SSE41-NEXT:    pcmpeqd %xmm0, %xmm0
+; SSE41-NEXT:    pxor %xmm1, %xmm0
+; SSE41-NEXT:    retq
+;
+; AVX1-LABEL: ne_1_v8i16:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX1-NEXT:    vpaddb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpsllw $8, %xmm0, %xmm1
+; AVX1-NEXT:    vpaddb %xmm0, %xmm1, %xmm0
+; AVX1-NEXT:    vpsrlw $8, %xmm0, %xmm0
+; AVX1-NEXT:    vpcmpeqw {{.*}}(%rip), %xmm0, %xmm0
+; AVX1-NEXT:    vpcmpeqd %xmm1, %xmm1, %xmm1
+; AVX1-NEXT:    vpxor %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: ne_1_v8i16:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX2-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX2-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX2-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX2-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX2-NEXT:    vpaddb %xmm2, %xmm0, %xmm0
+; AVX2-NEXT:    vpsllw $8, %xmm0, %xmm1
+; AVX2-NEXT:    vpaddb %xmm0, %xmm1, %xmm0
+; AVX2-NEXT:    vpsrlw $8, %xmm0, %xmm0
+; AVX2-NEXT:    vpcmpeqw {{.*}}(%rip), %xmm0, %xmm0
+; AVX2-NEXT:    vpcmpeqd %xmm1, %xmm1, %xmm1
+; AVX2-NEXT:    vpxor %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: ne_1_v8i16:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
+; AVX512VPOPCNTDQ-NEXT:    vpopcntd %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpmovdw %zmm0, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    vpcmpeqw {{.*}}(%rip), %xmm0, %xmm0
+; AVX512VPOPCNTDQ-NEXT:    vpternlogq $15, %zmm0, %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    # kill: def $xmm0 killed $xmm0 killed $zmm0
+; AVX512VPOPCNTDQ-NEXT:    vzeroupper
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; AVX512VPOPCNTDQVL-LABEL: ne_1_v8i16:
+; AVX512VPOPCNTDQVL:       # %bb.0:
+; AVX512VPOPCNTDQVL-NEXT:    vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
+; AVX512VPOPCNTDQVL-NEXT:    vpopcntd %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vpmovdw %ymm0, %xmm0
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpeqw {{.*}}(%rip), %xmm0, %xmm0
+; AVX512VPOPCNTDQVL-NEXT:    vpternlogq $15, %xmm0, %xmm0, %xmm0
+; AVX512VPOPCNTDQVL-NEXT:    vzeroupper
+; AVX512VPOPCNTDQVL-NEXT:    retq
+;
+; BITALG_NOVLX-LABEL: ne_1_v8i16:
+; BITALG_NOVLX:       # %bb.0:
+; BITALG_NOVLX-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
+; BITALG_NOVLX-NEXT:    vpopcntw %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    vpcmpeqw {{.*}}(%rip), %xmm0, %xmm0
+; BITALG_NOVLX-NEXT:    vpternlogq $15, %zmm0, %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    # kill: def $xmm0 killed $xmm0 killed $zmm0
+; BITALG_NOVLX-NEXT:    vzeroupper
+; BITALG_NOVLX-NEXT:    retq
+;
+; BITALG-LABEL: ne_1_v8i16:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntw %xmm0, %xmm0
+; BITALG-NEXT:    vpcmpeqw {{.*}}(%rip), %xmm0, %xmm0
+; BITALG-NEXT:    vpternlogq $15, %xmm0, %xmm0, %xmm0
+; BITALG-NEXT:    retq
+  %2 = tail call <8 x i16> @llvm.ctpop.v8i16(<8 x i16> %0)
+  %3 = icmp ne <8 x i16> %2, <i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1>
+  %4 = sext <8 x i1> %3 to <8 x i16>
+  ret <8 x i16> %4
+}
+
+define <16 x i8> @ult_2_v16i8(<16 x i8> %0) {
+; SSE2-LABEL: ult_2_v16i8:
+; SSE2:       # %bb.0:
+; SSE2-NEXT:    movdqa %xmm0, %xmm1
+; SSE2-NEXT:    psrlw $1, %xmm1
+; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE2-NEXT:    psubb %xmm1, %xmm0
+; SSE2-NEXT:    movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
+; SSE2-NEXT:    movdqa %xmm0, %xmm2
+; SSE2-NEXT:    pand %xmm1, %xmm2
+; SSE2-NEXT:    psrlw $2, %xmm0
+; SSE2-NEXT:    pand %xmm1, %xmm0
+; SSE2-NEXT:    paddb %xmm2, %xmm0
+; SSE2-NEXT:    movdqa %xmm0, %xmm1
+; SSE2-NEXT:    psrlw $4, %xmm1
+; SSE2-NEXT:    paddb %xmm0, %xmm1
+; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE2-NEXT:    movdqa {{.*#+}} xmm0 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2]
+; SSE2-NEXT:    pcmpgtb %xmm1, %xmm0
+; SSE2-NEXT:    retq
+;
+; SSE3-LABEL: ult_2_v16i8:
+; SSE3:       # %bb.0:
+; SSE3-NEXT:    movdqa %xmm0, %xmm1
+; SSE3-NEXT:    psrlw $1, %xmm1
+; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE3-NEXT:    psubb %xmm1, %xmm0
+; SSE3-NEXT:    movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
+; SSE3-NEXT:    movdqa %xmm0, %xmm2
+; SSE3-NEXT:    pand %xmm1, %xmm2
+; SSE3-NEXT:    psrlw $2, %xmm0
+; SSE3-NEXT:    pand %xmm1, %xmm0
+; SSE3-NEXT:    paddb %xmm2, %xmm0
+; SSE3-NEXT:    movdqa %xmm0, %xmm1
+; SSE3-NEXT:    psrlw $4, %xmm1
+; SSE3-NEXT:    paddb %xmm0, %xmm1
+; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE3-NEXT:    movdqa {{.*#+}} xmm0 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2]
+; SSE3-NEXT:    pcmpgtb %xmm1, %xmm0
+; SSE3-NEXT:    retq
+;
+; SSSE3-LABEL: ult_2_v16i8:
+; SSSE3:       # %bb.0:
+; SSSE3-NEXT:    movdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; SSSE3-NEXT:    movdqa %xmm0, %xmm2
+; SSSE3-NEXT:    pand %xmm1, %xmm2
+; SSSE3-NEXT:    movdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; SSSE3-NEXT:    movdqa %xmm3, %xmm4
+; SSSE3-NEXT:    pshufb %xmm2, %xmm4
+; SSSE3-NEXT:    psrlw $4, %xmm0
+; SSSE3-NEXT:    pand %xmm1, %xmm0
+; SSSE3-NEXT:    pshufb %xmm0, %xmm3
+; SSSE3-NEXT:    paddb %xmm4, %xmm3
+; SSSE3-NEXT:    movdqa {{.*#+}} xmm0 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1]
+; SSSE3-NEXT:    pminub %xmm3, %xmm0
+; SSSE3-NEXT:    pcmpeqb %xmm3, %xmm0
+; SSSE3-NEXT:    retq
+;
+; SSE41-LABEL: ult_2_v16i8:
+; SSE41:       # %bb.0:
+; SSE41-NEXT:    movdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; SSE41-NEXT:    movdqa %xmm0, %xmm2
+; SSE41-NEXT:    pand %xmm1, %xmm2
+; SSE41-NEXT:    movdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; SSE41-NEXT:    movdqa %xmm3, %xmm4
+; SSE41-NEXT:    pshufb %xmm2, %xmm4
+; SSE41-NEXT:    psrlw $4, %xmm0
+; SSE41-NEXT:    pand %xmm1, %xmm0
+; SSE41-NEXT:    pshufb %xmm0, %xmm3
+; SSE41-NEXT:    paddb %xmm4, %xmm3
+; SSE41-NEXT:    movdqa {{.*#+}} xmm0 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1]
+; SSE41-NEXT:    pminub %xmm3, %xmm0
+; SSE41-NEXT:    pcmpeqb %xmm3, %xmm0
+; SSE41-NEXT:    retq
+;
+; AVX1-LABEL: ult_2_v16i8:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX1-NEXT:    vpaddb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpminub {{.*}}(%rip), %xmm0, %xmm1
+; AVX1-NEXT:    vpcmpeqb %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: ult_2_v16i8:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX2-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX2-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX2-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX2-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX2-NEXT:    vpaddb %xmm2, %xmm0, %xmm0
+; AVX2-NEXT:    vpminub {{.*}}(%rip), %xmm0, %xmm1
+; AVX2-NEXT:    vpcmpeqb %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: ult_2_v16i8:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    vpmovzxbd {{.*#+}} zmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero,xmm0[8],zero,zero,zero,xmm0[9],zero,zero,zero,xmm0[10],zero,zero,zero,xmm0[11],zero,zero,zero,xmm0[12],zero,zero,zero,xmm0[13],zero,zero,zero,xmm0[14],zero,zero,zero,xmm0[15],zero,zero,zero
+; AVX512VPOPCNTDQ-NEXT:    vpopcntd %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512VPOPCNTDQ-NEXT:    vmovdqa {{.*#+}} xmm1 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2]
+; AVX512VPOPCNTDQ-NEXT:    vpcmpgtb %xmm0, %xmm1, %xmm0
+; AVX512VPOPCNTDQ-NEXT:    vzeroupper
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; AVX512VPOPCNTDQVL-LABEL: ult_2_v16i8:
+; AVX512VPOPCNTDQVL:       # %bb.0:
+; AVX512VPOPCNTDQVL-NEXT:    vpmovzxbd {{.*#+}} zmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero,xmm0[8],zero,zero,zero,xmm0[9],zero,zero,zero,xmm0[10],zero,zero,zero,xmm0[11],zero,zero,zero,xmm0[12],zero,zero,zero,xmm0[13],zero,zero,zero,xmm0[14],zero,zero,zero,xmm0[15],zero,zero,zero
+; AVX512VPOPCNTDQVL-NEXT:    vpopcntd %zmm0, %zmm0
+; AVX512VPOPCNTDQVL-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512VPOPCNTDQVL-NEXT:    vmovdqa {{.*#+}} xmm1 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2]
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpgtb %xmm0, %xmm1, %xmm0
+; AVX512VPOPCNTDQVL-NEXT:    vzeroupper
+; AVX512VPOPCNTDQVL-NEXT:    retq
+;
+; BITALG_NOVLX-LABEL: ult_2_v16i8:
+; BITALG_NOVLX:       # %bb.0:
+; BITALG_NOVLX-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
+; BITALG_NOVLX-NEXT:    vpopcntb %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    vmovdqa {{.*#+}} xmm1 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2]
+; BITALG_NOVLX-NEXT:    vpcmpgtb %xmm0, %xmm1, %xmm0
+; BITALG_NOVLX-NEXT:    vzeroupper
+; BITALG_NOVLX-NEXT:    retq
+;
+; BITALG-LABEL: ult_2_v16i8:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntb %xmm0, %xmm0
+; BITALG-NEXT:    vpcmpltub {{.*}}(%rip), %xmm0, %k0
+; BITALG-NEXT:    vpmovm2b %k0, %xmm0
+; BITALG-NEXT:    retq
+  %2 = tail call <16 x i8> @llvm.ctpop.v16i8(<16 x i8> %0)
+  %3 = icmp ult <16 x i8> %2, <i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2>
+  %4 = sext <16 x i1> %3 to <16 x i8>
+  ret <16 x i8> %4
+}
+
+define <16 x i8> @ugt_1_v16i8(<16 x i8> %0) {
+; SSE2-LABEL: ugt_1_v16i8:
+; SSE2:       # %bb.0:
+; SSE2-NEXT:    movdqa %xmm0, %xmm1
+; SSE2-NEXT:    psrlw $1, %xmm1
+; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE2-NEXT:    psubb %xmm1, %xmm0
+; SSE2-NEXT:    movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
+; SSE2-NEXT:    movdqa %xmm0, %xmm2
+; SSE2-NEXT:    pand %xmm1, %xmm2
+; SSE2-NEXT:    psrlw $2, %xmm0
+; SSE2-NEXT:    pand %xmm1, %xmm0
+; SSE2-NEXT:    paddb %xmm2, %xmm0
+; SSE2-NEXT:    movdqa %xmm0, %xmm1
+; SSE2-NEXT:    psrlw $4, %xmm1
+; SSE2-NEXT:    paddb %xmm0, %xmm1
+; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE2-NEXT:    pcmpgtb {{.*}}(%rip), %xmm1
+; SSE2-NEXT:    movdqa %xmm1, %xmm0
+; SSE2-NEXT:    retq
+;
+; SSE3-LABEL: ugt_1_v16i8:
+; SSE3:       # %bb.0:
+; SSE3-NEXT:    movdqa %xmm0, %xmm1
+; SSE3-NEXT:    psrlw $1, %xmm1
+; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE3-NEXT:    psubb %xmm1, %xmm0
+; SSE3-NEXT:    movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
+; SSE3-NEXT:    movdqa %xmm0, %xmm2
+; SSE3-NEXT:    pand %xmm1, %xmm2
+; SSE3-NEXT:    psrlw $2, %xmm0
+; SSE3-NEXT:    pand %xmm1, %xmm0
+; SSE3-NEXT:    paddb %xmm2, %xmm0
+; SSE3-NEXT:    movdqa %xmm0, %xmm1
+; SSE3-NEXT:    psrlw $4, %xmm1
+; SSE3-NEXT:    paddb %xmm0, %xmm1
+; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE3-NEXT:    pcmpgtb {{.*}}(%rip), %xmm1
+; SSE3-NEXT:    movdqa %xmm1, %xmm0
+; SSE3-NEXT:    retq
+;
+; SSSE3-LABEL: ugt_1_v16i8:
+; SSSE3:       # %bb.0:
+; SSSE3-NEXT:    movdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; SSSE3-NEXT:    movdqa %xmm0, %xmm2
+; SSSE3-NEXT:    pand %xmm1, %xmm2
+; SSSE3-NEXT:    movdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; SSSE3-NEXT:    movdqa %xmm3, %xmm4
+; SSSE3-NEXT:    pshufb %xmm2, %xmm4
+; SSSE3-NEXT:    psrlw $4, %xmm0
+; SSSE3-NEXT:    pand %xmm1, %xmm0
+; SSSE3-NEXT:    pshufb %xmm0, %xmm3
+; SSSE3-NEXT:    paddb %xmm4, %xmm3
+; SSSE3-NEXT:    movdqa {{.*#+}} xmm0 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2]
+; SSSE3-NEXT:    pmaxub %xmm3, %xmm0
+; SSSE3-NEXT:    pcmpeqb %xmm3, %xmm0
+; SSSE3-NEXT:    retq
+;
+; SSE41-LABEL: ugt_1_v16i8:
+; SSE41:       # %bb.0:
+; SSE41-NEXT:    movdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; SSE41-NEXT:    movdqa %xmm0, %xmm2
+; SSE41-NEXT:    pand %xmm1, %xmm2
+; SSE41-NEXT:    movdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; SSE41-NEXT:    movdqa %xmm3, %xmm4
+; SSE41-NEXT:    pshufb %xmm2, %xmm4
+; SSE41-NEXT:    psrlw $4, %xmm0
+; SSE41-NEXT:    pand %xmm1, %xmm0
+; SSE41-NEXT:    pshufb %xmm0, %xmm3
+; SSE41-NEXT:    paddb %xmm4, %xmm3
+; SSE41-NEXT:    movdqa {{.*#+}} xmm0 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2]
+; SSE41-NEXT:    pmaxub %xmm3, %xmm0
+; SSE41-NEXT:    pcmpeqb %xmm3, %xmm0
+; SSE41-NEXT:    retq
+;
+; AVX1-LABEL: ugt_1_v16i8:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX1-NEXT:    vpaddb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpmaxub {{.*}}(%rip), %xmm0, %xmm1
+; AVX1-NEXT:    vpcmpeqb %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: ugt_1_v16i8:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX2-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX2-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX2-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX2-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX2-NEXT:    vpaddb %xmm2, %xmm0, %xmm0
+; AVX2-NEXT:    vpmaxub {{.*}}(%rip), %xmm0, %xmm1
+; AVX2-NEXT:    vpcmpeqb %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: ugt_1_v16i8:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    vpmovzxbd {{.*#+}} zmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero,xmm0[8],zero,zero,zero,xmm0[9],zero,zero,zero,xmm0[10],zero,zero,zero,xmm0[11],zero,zero,zero,xmm0[12],zero,zero,zero,xmm0[13],zero,zero,zero,xmm0[14],zero,zero,zero,xmm0[15],zero,zero,zero
+; AVX512VPOPCNTDQ-NEXT:    vpopcntd %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512VPOPCNTDQ-NEXT:    vpcmpgtb {{.*}}(%rip), %xmm0, %xmm0
+; AVX512VPOPCNTDQ-NEXT:    vzeroupper
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; AVX512VPOPCNTDQVL-LABEL: ugt_1_v16i8:
+; AVX512VPOPCNTDQVL:       # %bb.0:
+; AVX512VPOPCNTDQVL-NEXT:    vpmovzxbd {{.*#+}} zmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero,xmm0[8],zero,zero,zero,xmm0[9],zero,zero,zero,xmm0[10],zero,zero,zero,xmm0[11],zero,zero,zero,xmm0[12],zero,zero,zero,xmm0[13],zero,zero,zero,xmm0[14],zero,zero,zero,xmm0[15],zero,zero,zero
+; AVX512VPOPCNTDQVL-NEXT:    vpopcntd %zmm0, %zmm0
+; AVX512VPOPCNTDQVL-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpgtb {{.*}}(%rip), %xmm0, %xmm0
+; AVX512VPOPCNTDQVL-NEXT:    vzeroupper
+; AVX512VPOPCNTDQVL-NEXT:    retq
+;
+; BITALG_NOVLX-LABEL: ugt_1_v16i8:
+; BITALG_NOVLX:       # %bb.0:
+; BITALG_NOVLX-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
+; BITALG_NOVLX-NEXT:    vpopcntb %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    vpcmpgtb {{.*}}(%rip), %xmm0, %xmm0
+; BITALG_NOVLX-NEXT:    vzeroupper
+; BITALG_NOVLX-NEXT:    retq
+;
+; BITALG-LABEL: ugt_1_v16i8:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntb %xmm0, %xmm0
+; BITALG-NEXT:    vpcmpnleub {{.*}}(%rip), %xmm0, %k0
+; BITALG-NEXT:    vpmovm2b %k0, %xmm0
+; BITALG-NEXT:    retq
+  %2 = tail call <16 x i8> @llvm.ctpop.v16i8(<16 x i8> %0)
+  %3 = icmp ugt <16 x i8> %2, <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
+  %4 = sext <16 x i1> %3 to <16 x i8>
+  ret <16 x i8> %4
+}
+
+define <16 x i8> @eq_1_v16i8(<16 x i8> %0) {
+; SSE2-LABEL: eq_1_v16i8:
+; SSE2:       # %bb.0:
+; SSE2-NEXT:    movdqa %xmm0, %xmm1
+; SSE2-NEXT:    psrlw $1, %xmm1
+; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE2-NEXT:    psubb %xmm1, %xmm0
+; SSE2-NEXT:    movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
+; SSE2-NEXT:    movdqa %xmm0, %xmm2
+; SSE2-NEXT:    pand %xmm1, %xmm2
+; SSE2-NEXT:    psrlw $2, %xmm0
+; SSE2-NEXT:    pand %xmm1, %xmm0
+; SSE2-NEXT:    paddb %xmm2, %xmm0
+; SSE2-NEXT:    movdqa %xmm0, %xmm1
+; SSE2-NEXT:    psrlw $4, %xmm1
+; SSE2-NEXT:    paddb %xmm0, %xmm1
+; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE2-NEXT:    pcmpeqb {{.*}}(%rip), %xmm1
+; SSE2-NEXT:    movdqa %xmm1, %xmm0
+; SSE2-NEXT:    retq
+;
+; SSE3-LABEL: eq_1_v16i8:
+; SSE3:       # %bb.0:
+; SSE3-NEXT:    movdqa %xmm0, %xmm1
+; SSE3-NEXT:    psrlw $1, %xmm1
+; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE3-NEXT:    psubb %xmm1, %xmm0
+; SSE3-NEXT:    movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
+; SSE3-NEXT:    movdqa %xmm0, %xmm2
+; SSE3-NEXT:    pand %xmm1, %xmm2
+; SSE3-NEXT:    psrlw $2, %xmm0
+; SSE3-NEXT:    pand %xmm1, %xmm0
+; SSE3-NEXT:    paddb %xmm2, %xmm0
+; SSE3-NEXT:    movdqa %xmm0, %xmm1
+; SSE3-NEXT:    psrlw $4, %xmm1
+; SSE3-NEXT:    paddb %xmm0, %xmm1
+; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE3-NEXT:    pcmpeqb {{.*}}(%rip), %xmm1
+; SSE3-NEXT:    movdqa %xmm1, %xmm0
+; SSE3-NEXT:    retq
+;
+; SSSE3-LABEL: eq_1_v16i8:
+; SSSE3:       # %bb.0:
+; SSSE3-NEXT:    movdqa {{.*#+}} xmm2 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; SSSE3-NEXT:    movdqa %xmm0, %xmm3
+; SSSE3-NEXT:    pand %xmm2, %xmm3
+; SSSE3-NEXT:    movdqa {{.*#+}} xmm1 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; SSSE3-NEXT:    movdqa %xmm1, %xmm4
+; SSSE3-NEXT:    pshufb %xmm3, %xmm4
+; SSSE3-NEXT:    psrlw $4, %xmm0
+; SSSE3-NEXT:    pand %xmm2, %xmm0
+; SSSE3-NEXT:    pshufb %xmm0, %xmm1
+; SSSE3-NEXT:    paddb %xmm4, %xmm1
+; SSSE3-NEXT:    pcmpeqb {{.*}}(%rip), %xmm1
+; SSSE3-NEXT:    movdqa %xmm1, %xmm0
+; SSSE3-NEXT:    retq
+;
+; SSE41-LABEL: eq_1_v16i8:
+; SSE41:       # %bb.0:
+; SSE41-NEXT:    movdqa {{.*#+}} xmm2 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; SSE41-NEXT:    movdqa %xmm0, %xmm3
+; SSE41-NEXT:    pand %xmm2, %xmm3
+; SSE41-NEXT:    movdqa {{.*#+}} xmm1 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; SSE41-NEXT:    movdqa %xmm1, %xmm4
+; SSE41-NEXT:    pshufb %xmm3, %xmm4
+; SSE41-NEXT:    psrlw $4, %xmm0
+; SSE41-NEXT:    pand %xmm2, %xmm0
+; SSE41-NEXT:    pshufb %xmm0, %xmm1
+; SSE41-NEXT:    paddb %xmm4, %xmm1
+; SSE41-NEXT:    pcmpeqb {{.*}}(%rip), %xmm1
+; SSE41-NEXT:    movdqa %xmm1, %xmm0
+; SSE41-NEXT:    retq
+;
+; AVX1-LABEL: eq_1_v16i8:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX1-NEXT:    vpaddb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpcmpeqb {{.*}}(%rip), %xmm0, %xmm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: eq_1_v16i8:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX2-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX2-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX2-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX2-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX2-NEXT:    vpaddb %xmm2, %xmm0, %xmm0
+; AVX2-NEXT:    vpcmpeqb {{.*}}(%rip), %xmm0, %xmm0
+; AVX2-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: eq_1_v16i8:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    vpmovzxbd {{.*#+}} zmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero,xmm0[8],zero,zero,zero,xmm0[9],zero,zero,zero,xmm0[10],zero,zero,zero,xmm0[11],zero,zero,zero,xmm0[12],zero,zero,zero,xmm0[13],zero,zero,zero,xmm0[14],zero,zero,zero,xmm0[15],zero,zero,zero
+; AVX512VPOPCNTDQ-NEXT:    vpopcntd %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512VPOPCNTDQ-NEXT:    vpcmpeqb {{.*}}(%rip), %xmm0, %xmm0
+; AVX512VPOPCNTDQ-NEXT:    vzeroupper
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; AVX512VPOPCNTDQVL-LABEL: eq_1_v16i8:
+; AVX512VPOPCNTDQVL:       # %bb.0:
+; AVX512VPOPCNTDQVL-NEXT:    vpmovzxbd {{.*#+}} zmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero,xmm0[8],zero,zero,zero,xmm0[9],zero,zero,zero,xmm0[10],zero,zero,zero,xmm0[11],zero,zero,zero,xmm0[12],zero,zero,zero,xmm0[13],zero,zero,zero,xmm0[14],zero,zero,zero,xmm0[15],zero,zero,zero
+; AVX512VPOPCNTDQVL-NEXT:    vpopcntd %zmm0, %zmm0
+; AVX512VPOPCNTDQVL-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpeqb {{.*}}(%rip), %xmm0, %xmm0
+; AVX512VPOPCNTDQVL-NEXT:    vzeroupper
+; AVX512VPOPCNTDQVL-NEXT:    retq
+;
+; BITALG_NOVLX-LABEL: eq_1_v16i8:
+; BITALG_NOVLX:       # %bb.0:
+; BITALG_NOVLX-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
+; BITALG_NOVLX-NEXT:    vpopcntb %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    vpcmpeqb {{.*}}(%rip), %xmm0, %xmm0
+; BITALG_NOVLX-NEXT:    vzeroupper
+; BITALG_NOVLX-NEXT:    retq
+;
+; BITALG-LABEL: eq_1_v16i8:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntb %xmm0, %xmm0
+; BITALG-NEXT:    vpcmpeqb {{.*}}(%rip), %xmm0, %xmm0
+; BITALG-NEXT:    retq
+  %2 = tail call <16 x i8> @llvm.ctpop.v16i8(<16 x i8> %0)
+  %3 = icmp eq <16 x i8> %2, <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
+  %4 = sext <16 x i1> %3 to <16 x i8>
+  ret <16 x i8> %4
+}
+
+define <16 x i8> @ne_1_v16i8(<16 x i8> %0) {
+; SSE2-LABEL: ne_1_v16i8:
+; SSE2:       # %bb.0:
+; SSE2-NEXT:    movdqa %xmm0, %xmm1
+; SSE2-NEXT:    psrlw $1, %xmm1
+; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE2-NEXT:    psubb %xmm1, %xmm0
+; SSE2-NEXT:    movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
+; SSE2-NEXT:    movdqa %xmm0, %xmm2
+; SSE2-NEXT:    pand %xmm1, %xmm2
+; SSE2-NEXT:    psrlw $2, %xmm0
+; SSE2-NEXT:    pand %xmm1, %xmm0
+; SSE2-NEXT:    paddb %xmm2, %xmm0
+; SSE2-NEXT:    movdqa %xmm0, %xmm1
+; SSE2-NEXT:    psrlw $4, %xmm1
+; SSE2-NEXT:    paddb %xmm0, %xmm1
+; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE2-NEXT:    pcmpeqb {{.*}}(%rip), %xmm1
+; SSE2-NEXT:    pcmpeqd %xmm0, %xmm0
+; SSE2-NEXT:    pxor %xmm0, %xmm1
+; SSE2-NEXT:    movdqa %xmm1, %xmm0
+; SSE2-NEXT:    retq
+;
+; SSE3-LABEL: ne_1_v16i8:
+; SSE3:       # %bb.0:
+; SSE3-NEXT:    movdqa %xmm0, %xmm1
+; SSE3-NEXT:    psrlw $1, %xmm1
+; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE3-NEXT:    psubb %xmm1, %xmm0
+; SSE3-NEXT:    movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
+; SSE3-NEXT:    movdqa %xmm0, %xmm2
+; SSE3-NEXT:    pand %xmm1, %xmm2
+; SSE3-NEXT:    psrlw $2, %xmm0
+; SSE3-NEXT:    pand %xmm1, %xmm0
+; SSE3-NEXT:    paddb %xmm2, %xmm0
+; SSE3-NEXT:    movdqa %xmm0, %xmm1
+; SSE3-NEXT:    psrlw $4, %xmm1
+; SSE3-NEXT:    paddb %xmm0, %xmm1
+; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
+; SSE3-NEXT:    pcmpeqb {{.*}}(%rip), %xmm1
+; SSE3-NEXT:    pcmpeqd %xmm0, %xmm0
+; SSE3-NEXT:    pxor %xmm0, %xmm1
+; SSE3-NEXT:    movdqa %xmm1, %xmm0
+; SSE3-NEXT:    retq
+;
+; SSSE3-LABEL: ne_1_v16i8:
+; SSSE3:       # %bb.0:
+; SSSE3-NEXT:    movdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; SSSE3-NEXT:    movdqa %xmm0, %xmm2
+; SSSE3-NEXT:    pand %xmm1, %xmm2
+; SSSE3-NEXT:    movdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; SSSE3-NEXT:    movdqa %xmm3, %xmm4
+; SSSE3-NEXT:    pshufb %xmm2, %xmm4
+; SSSE3-NEXT:    psrlw $4, %xmm0
+; SSSE3-NEXT:    pand %xmm1, %xmm0
+; SSSE3-NEXT:    pshufb %xmm0, %xmm3
+; SSSE3-NEXT:    paddb %xmm4, %xmm3
+; SSSE3-NEXT:    pcmpeqb {{.*}}(%rip), %xmm3
+; SSSE3-NEXT:    pcmpeqd %xmm0, %xmm0
+; SSSE3-NEXT:    pxor %xmm3, %xmm0
+; SSSE3-NEXT:    retq
+;
+; SSE41-LABEL: ne_1_v16i8:
+; SSE41:       # %bb.0:
+; SSE41-NEXT:    movdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; SSE41-NEXT:    movdqa %xmm0, %xmm2
+; SSE41-NEXT:    pand %xmm1, %xmm2
+; SSE41-NEXT:    movdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; SSE41-NEXT:    movdqa %xmm3, %xmm4
+; SSE41-NEXT:    pshufb %xmm2, %xmm4
+; SSE41-NEXT:    psrlw $4, %xmm0
+; SSE41-NEXT:    pand %xmm1, %xmm0
+; SSE41-NEXT:    pshufb %xmm0, %xmm3
+; SSE41-NEXT:    paddb %xmm4, %xmm3
+; SSE41-NEXT:    pcmpeqb {{.*}}(%rip), %xmm3
+; SSE41-NEXT:    pcmpeqd %xmm0, %xmm0
+; SSE41-NEXT:    pxor %xmm3, %xmm0
+; SSE41-NEXT:    retq
+;
+; AVX1-LABEL: ne_1_v16i8:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX1-NEXT:    vpaddb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpcmpeqb {{.*}}(%rip), %xmm0, %xmm0
+; AVX1-NEXT:    vpcmpeqd %xmm1, %xmm1, %xmm1
+; AVX1-NEXT:    vpxor %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: ne_1_v16i8:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX2-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX2-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX2-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX2-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX2-NEXT:    vpaddb %xmm2, %xmm0, %xmm0
+; AVX2-NEXT:    vpcmpeqb {{.*}}(%rip), %xmm0, %xmm0
+; AVX2-NEXT:    vpcmpeqd %xmm1, %xmm1, %xmm1
+; AVX2-NEXT:    vpxor %xmm1, %xmm0, %xmm0
+; AVX2-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: ne_1_v16i8:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    vpmovzxbd {{.*#+}} zmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero,xmm0[8],zero,zero,zero,xmm0[9],zero,zero,zero,xmm0[10],zero,zero,zero,xmm0[11],zero,zero,zero,xmm0[12],zero,zero,zero,xmm0[13],zero,zero,zero,xmm0[14],zero,zero,zero,xmm0[15],zero,zero,zero
+; AVX512VPOPCNTDQ-NEXT:    vpopcntd %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512VPOPCNTDQ-NEXT:    vpcmpeqb {{.*}}(%rip), %xmm0, %xmm0
+; AVX512VPOPCNTDQ-NEXT:    vpternlogq $15, %zmm0, %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    # kill: def $xmm0 killed $xmm0 killed $zmm0
+; AVX512VPOPCNTDQ-NEXT:    vzeroupper
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; AVX512VPOPCNTDQVL-LABEL: ne_1_v16i8:
+; AVX512VPOPCNTDQVL:       # %bb.0:
+; AVX512VPOPCNTDQVL-NEXT:    vpmovzxbd {{.*#+}} zmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero,xmm0[8],zero,zero,zero,xmm0[9],zero,zero,zero,xmm0[10],zero,zero,zero,xmm0[11],zero,zero,zero,xmm0[12],zero,zero,zero,xmm0[13],zero,zero,zero,xmm0[14],zero,zero,zero,xmm0[15],zero,zero,zero
+; AVX512VPOPCNTDQVL-NEXT:    vpopcntd %zmm0, %zmm0
+; AVX512VPOPCNTDQVL-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpeqb {{.*}}(%rip), %xmm0, %xmm0
+; AVX512VPOPCNTDQVL-NEXT:    vpternlogq $15, %xmm0, %xmm0, %xmm0
+; AVX512VPOPCNTDQVL-NEXT:    vzeroupper
+; AVX512VPOPCNTDQVL-NEXT:    retq
+;
+; BITALG_NOVLX-LABEL: ne_1_v16i8:
+; BITALG_NOVLX:       # %bb.0:
+; BITALG_NOVLX-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
+; BITALG_NOVLX-NEXT:    vpopcntb %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    vpcmpeqb {{.*}}(%rip), %xmm0, %xmm0
+; BITALG_NOVLX-NEXT:    vpternlogq $15, %zmm0, %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    # kill: def $xmm0 killed $xmm0 killed $zmm0
+; BITALG_NOVLX-NEXT:    vzeroupper
+; BITALG_NOVLX-NEXT:    retq
+;
+; BITALG-LABEL: ne_1_v16i8:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntb %xmm0, %xmm0
+; BITALG-NEXT:    vpcmpeqb {{.*}}(%rip), %xmm0, %xmm0
+; BITALG-NEXT:    vpternlogq $15, %xmm0, %xmm0, %xmm0
+; BITALG-NEXT:    retq
+  %2 = tail call <16 x i8> @llvm.ctpop.v16i8(<16 x i8> %0)
+  %3 = icmp ne <16 x i8> %2, <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
+  %4 = sext <16 x i1> %3 to <16 x i8>
+  ret <16 x i8> %4
+}
+
 declare <2 x i64> @llvm.ctpop.v2i64(<2 x i64>)
 declare <4 x i32> @llvm.ctpop.v4i32(<4 x i32>)
 declare <8 x i16> @llvm.ctpop.v8i16(<8 x i16>)
diff --git a/llvm/test/CodeGen/X86/vector-popcnt-256.ll b/llvm/test/CodeGen/X86/vector-popcnt-256.ll
index 570f59673d1c..9b6b8d02820a 100644
--- a/llvm/test/CodeGen/X86/vector-popcnt-256.ll
+++ b/llvm/test/CodeGen/X86/vector-popcnt-256.ll
@@ -341,6 +341,1457 @@ define <32 x i8> @foldv32i8() nounwind {
   ret <32 x i8> %out
 }
 
+define <4 x i64> @ult_2_v4i64(<4 x i64> %0) {
+; AVX1-LABEL: ult_2_v4i64:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm4
+; AVX1-NEXT:    vpand %xmm1, %xmm4, %xmm4
+; AVX1-NEXT:    vpshufb %xmm4, %xmm3, %xmm4
+; AVX1-NEXT:    vpaddb %xmm2, %xmm4, %xmm2
+; AVX1-NEXT:    vpxor %xmm4, %xmm4, %xmm4
+; AVX1-NEXT:    vpsadbw %xmm4, %xmm2, %xmm2
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm5
+; AVX1-NEXT:    vpshufb %xmm5, %xmm3, %xmm5
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX1-NEXT:    vpaddb %xmm5, %xmm0, %xmm0
+; AVX1-NEXT:    vpsadbw %xmm4, %xmm0, %xmm0
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [2,2]
+; AVX1-NEXT:    vpcmpgtq %xmm0, %xmm1, %xmm0
+; AVX1-NEXT:    vpcmpgtq %xmm2, %xmm1, %xmm1
+; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: ult_2_v4i64:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX2-NEXT:    vpand %ymm1, %ymm0, %ymm2
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX2-NEXT:    vpshufb %ymm2, %ymm3, %ymm2
+; AVX2-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX2-NEXT:    vpand %ymm1, %ymm0, %ymm0
+; AVX2-NEXT:    vpshufb %ymm0, %ymm3, %ymm0
+; AVX2-NEXT:    vpaddb %ymm2, %ymm0, %ymm0
+; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX2-NEXT:    vpsadbw %ymm1, %ymm0, %ymm0
+; AVX2-NEXT:    vpbroadcastq {{.*#+}} ymm1 = [2,2,2,2]
+; AVX2-NEXT:    vpcmpgtq %ymm0, %ymm1, %ymm0
+; AVX2-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: ult_2_v4i64:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpopcntq %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpbroadcastq {{.*#+}} ymm1 = [2,2,2,2]
+; AVX512VPOPCNTDQ-NEXT:    vpcmpgtq %ymm0, %ymm1, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; AVX512VPOPCNTDQVL-LABEL: ult_2_v4i64:
+; AVX512VPOPCNTDQVL:       # %bb.0:
+; AVX512VPOPCNTDQVL-NEXT:    vpopcntq %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpltuq {{.*}}(%rip){1to4}, %ymm0, %k1
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpeqd %ymm0, %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vmovdqa64 %ymm0, %ymm0 {%k1} {z}
+; AVX512VPOPCNTDQVL-NEXT:    retq
+;
+; BITALG_NOVLX-LABEL: ult_2_v4i64:
+; BITALG_NOVLX:       # %bb.0:
+; BITALG_NOVLX-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; BITALG_NOVLX-NEXT:    vpopcntb %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG_NOVLX-NEXT:    vpsadbw %ymm1, %ymm0, %ymm0
+; BITALG_NOVLX-NEXT:    vpbroadcastq {{.*#+}} ymm1 = [2,2,2,2]
+; BITALG_NOVLX-NEXT:    vpcmpgtq %ymm0, %ymm1, %ymm0
+; BITALG_NOVLX-NEXT:    retq
+;
+; BITALG-LABEL: ult_2_v4i64:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntb %ymm0, %ymm0
+; BITALG-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG-NEXT:    vpsadbw %ymm1, %ymm0, %ymm0
+; BITALG-NEXT:    vpcmpltuq {{.*}}(%rip){1to4}, %ymm0, %k1
+; BITALG-NEXT:    vpcmpeqd %ymm0, %ymm0, %ymm0
+; BITALG-NEXT:    vmovdqa64 %ymm0, %ymm0 {%k1} {z}
+; BITALG-NEXT:    retq
+  %2 = tail call <4 x i64> @llvm.ctpop.v4i64(<4 x i64> %0)
+  %3 = icmp ult <4 x i64> %2, <i64 2, i64 2, i64 2, i64 2>
+  %4 = sext <4 x i1> %3 to <4 x i64>
+  ret <4 x i64> %4
+}
+
+define <4 x i64> @ugt_1_v4i64(<4 x i64> %0) {
+; AVX1-LABEL: ugt_1_v4i64:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm4
+; AVX1-NEXT:    vpand %xmm1, %xmm4, %xmm4
+; AVX1-NEXT:    vpshufb %xmm4, %xmm3, %xmm4
+; AVX1-NEXT:    vpaddb %xmm2, %xmm4, %xmm2
+; AVX1-NEXT:    vpxor %xmm4, %xmm4, %xmm4
+; AVX1-NEXT:    vpsadbw %xmm4, %xmm2, %xmm2
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm5
+; AVX1-NEXT:    vpshufb %xmm5, %xmm3, %xmm5
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX1-NEXT:    vpaddb %xmm5, %xmm0, %xmm0
+; AVX1-NEXT:    vpsadbw %xmm4, %xmm0, %xmm0
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [1,1]
+; AVX1-NEXT:    vpcmpgtq %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpcmpgtq %xmm1, %xmm2, %xmm1
+; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: ugt_1_v4i64:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX2-NEXT:    vpand %ymm1, %ymm0, %ymm2
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX2-NEXT:    vpshufb %ymm2, %ymm3, %ymm2
+; AVX2-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX2-NEXT:    vpand %ymm1, %ymm0, %ymm0
+; AVX2-NEXT:    vpshufb %ymm0, %ymm3, %ymm0
+; AVX2-NEXT:    vpaddb %ymm2, %ymm0, %ymm0
+; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX2-NEXT:    vpsadbw %ymm1, %ymm0, %ymm0
+; AVX2-NEXT:    vpbroadcastq {{.*#+}} ymm1 = [1,1,1,1]
+; AVX2-NEXT:    vpcmpgtq %ymm1, %ymm0, %ymm0
+; AVX2-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: ugt_1_v4i64:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpopcntq %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpbroadcastq {{.*#+}} ymm1 = [1,1,1,1]
+; AVX512VPOPCNTDQ-NEXT:    vpcmpgtq %ymm1, %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; AVX512VPOPCNTDQVL-LABEL: ugt_1_v4i64:
+; AVX512VPOPCNTDQVL:       # %bb.0:
+; AVX512VPOPCNTDQVL-NEXT:    vpopcntq %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpnleuq {{.*}}(%rip){1to4}, %ymm0, %k1
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpeqd %ymm0, %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vmovdqa64 %ymm0, %ymm0 {%k1} {z}
+; AVX512VPOPCNTDQVL-NEXT:    retq
+;
+; BITALG_NOVLX-LABEL: ugt_1_v4i64:
+; BITALG_NOVLX:       # %bb.0:
+; BITALG_NOVLX-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; BITALG_NOVLX-NEXT:    vpopcntb %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG_NOVLX-NEXT:    vpsadbw %ymm1, %ymm0, %ymm0
+; BITALG_NOVLX-NEXT:    vpbroadcastq {{.*#+}} ymm1 = [1,1,1,1]
+; BITALG_NOVLX-NEXT:    vpcmpgtq %ymm1, %ymm0, %ymm0
+; BITALG_NOVLX-NEXT:    retq
+;
+; BITALG-LABEL: ugt_1_v4i64:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntb %ymm0, %ymm0
+; BITALG-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG-NEXT:    vpsadbw %ymm1, %ymm0, %ymm0
+; BITALG-NEXT:    vpcmpnleuq {{.*}}(%rip){1to4}, %ymm0, %k1
+; BITALG-NEXT:    vpcmpeqd %ymm0, %ymm0, %ymm0
+; BITALG-NEXT:    vmovdqa64 %ymm0, %ymm0 {%k1} {z}
+; BITALG-NEXT:    retq
+  %2 = tail call <4 x i64> @llvm.ctpop.v4i64(<4 x i64> %0)
+  %3 = icmp ugt <4 x i64> %2, <i64 1, i64 1, i64 1, i64 1>
+  %4 = sext <4 x i1> %3 to <4 x i64>
+  ret <4 x i64> %4
+}
+
+define <4 x i64> @eq_1_v4i64(<4 x i64> %0) {
+; AVX1-LABEL: eq_1_v4i64:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm4
+; AVX1-NEXT:    vpand %xmm1, %xmm4, %xmm4
+; AVX1-NEXT:    vpshufb %xmm4, %xmm3, %xmm4
+; AVX1-NEXT:    vpaddb %xmm2, %xmm4, %xmm2
+; AVX1-NEXT:    vpxor %xmm4, %xmm4, %xmm4
+; AVX1-NEXT:    vpsadbw %xmm4, %xmm2, %xmm2
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm5
+; AVX1-NEXT:    vpshufb %xmm5, %xmm3, %xmm5
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX1-NEXT:    vpaddb %xmm5, %xmm0, %xmm0
+; AVX1-NEXT:    vpsadbw %xmm4, %xmm0, %xmm0
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [1,1]
+; AVX1-NEXT:    vpcmpeqq %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpcmpeqq %xmm1, %xmm2, %xmm1
+; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: eq_1_v4i64:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX2-NEXT:    vpand %ymm1, %ymm0, %ymm2
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX2-NEXT:    vpshufb %ymm2, %ymm3, %ymm2
+; AVX2-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX2-NEXT:    vpand %ymm1, %ymm0, %ymm0
+; AVX2-NEXT:    vpshufb %ymm0, %ymm3, %ymm0
+; AVX2-NEXT:    vpaddb %ymm2, %ymm0, %ymm0
+; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX2-NEXT:    vpsadbw %ymm1, %ymm0, %ymm0
+; AVX2-NEXT:    vpbroadcastq {{.*#+}} ymm1 = [1,1,1,1]
+; AVX2-NEXT:    vpcmpeqq %ymm1, %ymm0, %ymm0
+; AVX2-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: eq_1_v4i64:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpopcntq %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpbroadcastq {{.*#+}} ymm1 = [1,1,1,1]
+; AVX512VPOPCNTDQ-NEXT:    vpcmpeqq %ymm1, %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; AVX512VPOPCNTDQVL-LABEL: eq_1_v4i64:
+; AVX512VPOPCNTDQVL:       # %bb.0:
+; AVX512VPOPCNTDQVL-NEXT:    vpopcntq %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vpbroadcastq {{.*#+}} ymm1 = [1,1,1,1]
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpeqq %ymm1, %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    retq
+;
+; BITALG_NOVLX-LABEL: eq_1_v4i64:
+; BITALG_NOVLX:       # %bb.0:
+; BITALG_NOVLX-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; BITALG_NOVLX-NEXT:    vpopcntb %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG_NOVLX-NEXT:    vpsadbw %ymm1, %ymm0, %ymm0
+; BITALG_NOVLX-NEXT:    vpbroadcastq {{.*#+}} ymm1 = [1,1,1,1]
+; BITALG_NOVLX-NEXT:    vpcmpeqq %ymm1, %ymm0, %ymm0
+; BITALG_NOVLX-NEXT:    retq
+;
+; BITALG-LABEL: eq_1_v4i64:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntb %ymm0, %ymm0
+; BITALG-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG-NEXT:    vpsadbw %ymm1, %ymm0, %ymm0
+; BITALG-NEXT:    vpbroadcastq {{.*#+}} ymm1 = [1,1,1,1]
+; BITALG-NEXT:    vpcmpeqq %ymm1, %ymm0, %ymm0
+; BITALG-NEXT:    retq
+  %2 = tail call <4 x i64> @llvm.ctpop.v4i64(<4 x i64> %0)
+  %3 = icmp eq <4 x i64> %2, <i64 1, i64 1, i64 1, i64 1>
+  %4 = sext <4 x i1> %3 to <4 x i64>
+  ret <4 x i64> %4
+}
+
+define <4 x i64> @ne_1_v4i64(<4 x i64> %0) {
+; AVX1-LABEL: ne_1_v4i64:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm4
+; AVX1-NEXT:    vpand %xmm1, %xmm4, %xmm4
+; AVX1-NEXT:    vpshufb %xmm4, %xmm3, %xmm4
+; AVX1-NEXT:    vpaddb %xmm2, %xmm4, %xmm2
+; AVX1-NEXT:    vpxor %xmm4, %xmm4, %xmm4
+; AVX1-NEXT:    vpsadbw %xmm4, %xmm2, %xmm2
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm5
+; AVX1-NEXT:    vpshufb %xmm5, %xmm3, %xmm5
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX1-NEXT:    vpaddb %xmm5, %xmm0, %xmm0
+; AVX1-NEXT:    vpsadbw %xmm4, %xmm0, %xmm0
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [1,1]
+; AVX1-NEXT:    vpcmpeqq %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpcmpeqd %xmm3, %xmm3, %xmm3
+; AVX1-NEXT:    vpxor %xmm3, %xmm0, %xmm0
+; AVX1-NEXT:    vpcmpeqq %xmm1, %xmm2, %xmm1
+; AVX1-NEXT:    vpxor %xmm3, %xmm1, %xmm1
+; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: ne_1_v4i64:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX2-NEXT:    vpand %ymm1, %ymm0, %ymm2
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX2-NEXT:    vpshufb %ymm2, %ymm3, %ymm2
+; AVX2-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX2-NEXT:    vpand %ymm1, %ymm0, %ymm0
+; AVX2-NEXT:    vpshufb %ymm0, %ymm3, %ymm0
+; AVX2-NEXT:    vpaddb %ymm2, %ymm0, %ymm0
+; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX2-NEXT:    vpsadbw %ymm1, %ymm0, %ymm0
+; AVX2-NEXT:    vpbroadcastq {{.*#+}} ymm1 = [1,1,1,1]
+; AVX2-NEXT:    vpcmpeqq %ymm1, %ymm0, %ymm0
+; AVX2-NEXT:    vpcmpeqd %ymm1, %ymm1, %ymm1
+; AVX2-NEXT:    vpxor %ymm1, %ymm0, %ymm0
+; AVX2-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: ne_1_v4i64:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpopcntq %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpbroadcastq {{.*#+}} ymm1 = [1,1,1,1]
+; AVX512VPOPCNTDQ-NEXT:    vpcmpeqq %ymm1, %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    vpternlogq $15, %zmm0, %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    # kill: def $ymm0 killed $ymm0 killed $zmm0
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; AVX512VPOPCNTDQVL-LABEL: ne_1_v4i64:
+; AVX512VPOPCNTDQVL:       # %bb.0:
+; AVX512VPOPCNTDQVL-NEXT:    vpopcntq %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vpbroadcastq {{.*#+}} ymm1 = [1,1,1,1]
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpeqq %ymm1, %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vpternlogq $15, %ymm0, %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    retq
+;
+; BITALG_NOVLX-LABEL: ne_1_v4i64:
+; BITALG_NOVLX:       # %bb.0:
+; BITALG_NOVLX-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; BITALG_NOVLX-NEXT:    vpopcntb %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG_NOVLX-NEXT:    vpsadbw %ymm1, %ymm0, %ymm0
+; BITALG_NOVLX-NEXT:    vpbroadcastq {{.*#+}} ymm1 = [1,1,1,1]
+; BITALG_NOVLX-NEXT:    vpcmpeqq %ymm1, %ymm0, %ymm0
+; BITALG_NOVLX-NEXT:    vpternlogq $15, %zmm0, %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    # kill: def $ymm0 killed $ymm0 killed $zmm0
+; BITALG_NOVLX-NEXT:    retq
+;
+; BITALG-LABEL: ne_1_v4i64:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntb %ymm0, %ymm0
+; BITALG-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG-NEXT:    vpsadbw %ymm1, %ymm0, %ymm0
+; BITALG-NEXT:    vpbroadcastq {{.*#+}} ymm1 = [1,1,1,1]
+; BITALG-NEXT:    vpcmpeqq %ymm1, %ymm0, %ymm0
+; BITALG-NEXT:    vpternlogq $15, %ymm0, %ymm0, %ymm0
+; BITALG-NEXT:    retq
+  %2 = tail call <4 x i64> @llvm.ctpop.v4i64(<4 x i64> %0)
+  %3 = icmp ne <4 x i64> %2, <i64 1, i64 1, i64 1, i64 1>
+  %4 = sext <4 x i1> %3 to <4 x i64>
+  ret <4 x i64> %4
+}
+
+define <8 x i32> @ult_2_v8i32(<8 x i32> %0) {
+; AVX1-LABEL: ult_2_v8i32:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm4
+; AVX1-NEXT:    vpand %xmm1, %xmm4, %xmm4
+; AVX1-NEXT:    vpshufb %xmm4, %xmm3, %xmm4
+; AVX1-NEXT:    vpaddb %xmm2, %xmm4, %xmm2
+; AVX1-NEXT:    vpxor %xmm4, %xmm4, %xmm4
+; AVX1-NEXT:    vpunpckhdq {{.*#+}} xmm5 = xmm2[2],xmm4[2],xmm2[3],xmm4[3]
+; AVX1-NEXT:    vpsadbw %xmm4, %xmm5, %xmm5
+; AVX1-NEXT:    vpmovzxdq {{.*#+}} xmm2 = xmm2[0],zero,xmm2[1],zero
+; AVX1-NEXT:    vpsadbw %xmm4, %xmm2, %xmm2
+; AVX1-NEXT:    vpackuswb %xmm5, %xmm2, %xmm2
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm5
+; AVX1-NEXT:    vpshufb %xmm5, %xmm3, %xmm5
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX1-NEXT:    vpaddb %xmm5, %xmm0, %xmm0
+; AVX1-NEXT:    vpunpckhdq {{.*#+}} xmm1 = xmm0[2],xmm4[2],xmm0[3],xmm4[3]
+; AVX1-NEXT:    vpsadbw %xmm4, %xmm1, %xmm1
+; AVX1-NEXT:    vpmovzxdq {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero
+; AVX1-NEXT:    vpsadbw %xmm4, %xmm0, %xmm0
+; AVX1-NEXT:    vpackuswb %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [2,2,2,2]
+; AVX1-NEXT:    vpcmpgtd %xmm0, %xmm1, %xmm0
+; AVX1-NEXT:    vpcmpgtd %xmm2, %xmm1, %xmm1
+; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: ult_2_v8i32:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX2-NEXT:    vpand %ymm1, %ymm0, %ymm2
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX2-NEXT:    vpshufb %ymm2, %ymm3, %ymm2
+; AVX2-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX2-NEXT:    vpand %ymm1, %ymm0, %ymm0
+; AVX2-NEXT:    vpshufb %ymm0, %ymm3, %ymm0
+; AVX2-NEXT:    vpaddb %ymm2, %ymm0, %ymm0
+; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX2-NEXT:    vpunpckhdq {{.*#+}} ymm2 = ymm0[2],ymm1[2],ymm0[3],ymm1[3],ymm0[6],ymm1[6],ymm0[7],ymm1[7]
+; AVX2-NEXT:    vpsadbw %ymm1, %ymm2, %ymm2
+; AVX2-NEXT:    vpunpckldq {{.*#+}} ymm0 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[4],ymm1[4],ymm0[5],ymm1[5]
+; AVX2-NEXT:    vpsadbw %ymm1, %ymm0, %ymm0
+; AVX2-NEXT:    vpackuswb %ymm2, %ymm0, %ymm0
+; AVX2-NEXT:    vpbroadcastd {{.*#+}} ymm1 = [2,2,2,2,2,2,2,2]
+; AVX2-NEXT:    vpcmpgtd %ymm0, %ymm1, %ymm0
+; AVX2-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: ult_2_v8i32:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpopcntd %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpbroadcastd {{.*#+}} ymm1 = [2,2,2,2,2,2,2,2]
+; AVX512VPOPCNTDQ-NEXT:    vpcmpgtd %ymm0, %ymm1, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; AVX512VPOPCNTDQVL-LABEL: ult_2_v8i32:
+; AVX512VPOPCNTDQVL:       # %bb.0:
+; AVX512VPOPCNTDQVL-NEXT:    vpopcntd %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpltud {{.*}}(%rip){1to8}, %ymm0, %k1
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpeqd %ymm0, %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vmovdqa32 %ymm0, %ymm0 {%k1} {z}
+; AVX512VPOPCNTDQVL-NEXT:    retq
+;
+; BITALG_NOVLX-LABEL: ult_2_v8i32:
+; BITALG_NOVLX:       # %bb.0:
+; BITALG_NOVLX-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; BITALG_NOVLX-NEXT:    vpopcntb %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG_NOVLX-NEXT:    vpunpckhdq {{.*#+}} ymm2 = ymm0[2],ymm1[2],ymm0[3],ymm1[3],ymm0[6],ymm1[6],ymm0[7],ymm1[7]
+; BITALG_NOVLX-NEXT:    vpsadbw %ymm1, %ymm2, %ymm2
+; BITALG_NOVLX-NEXT:    vpunpckldq {{.*#+}} ymm0 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[4],ymm1[4],ymm0[5],ymm1[5]
+; BITALG_NOVLX-NEXT:    vpsadbw %ymm1, %ymm0, %ymm0
+; BITALG_NOVLX-NEXT:    vpackuswb %ymm2, %ymm0, %ymm0
+; BITALG_NOVLX-NEXT:    vpbroadcastd {{.*#+}} ymm1 = [2,2,2,2,2,2,2,2]
+; BITALG_NOVLX-NEXT:    vpcmpgtd %ymm0, %ymm1, %ymm0
+; BITALG_NOVLX-NEXT:    retq
+;
+; BITALG-LABEL: ult_2_v8i32:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntb %ymm0, %ymm0
+; BITALG-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG-NEXT:    vpunpckhdq {{.*#+}} ymm2 = ymm0[2],ymm1[2],ymm0[3],ymm1[3],ymm0[6],ymm1[6],ymm0[7],ymm1[7]
+; BITALG-NEXT:    vpsadbw %ymm1, %ymm2, %ymm2
+; BITALG-NEXT:    vpunpckldq {{.*#+}} ymm0 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[4],ymm1[4],ymm0[5],ymm1[5]
+; BITALG-NEXT:    vpsadbw %ymm1, %ymm0, %ymm0
+; BITALG-NEXT:    vpackuswb %ymm2, %ymm0, %ymm0
+; BITALG-NEXT:    vpcmpltud {{.*}}(%rip){1to8}, %ymm0, %k1
+; BITALG-NEXT:    vpcmpeqd %ymm0, %ymm0, %ymm0
+; BITALG-NEXT:    vmovdqa32 %ymm0, %ymm0 {%k1} {z}
+; BITALG-NEXT:    retq
+  %2 = tail call <8 x i32> @llvm.ctpop.v8i32(<8 x i32> %0)
+  %3 = icmp ult <8 x i32> %2, <i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2>
+  %4 = sext <8 x i1> %3 to <8 x i32>
+  ret <8 x i32> %4
+}
+
+define <8 x i32> @ugt_1_v8i32(<8 x i32> %0) {
+; AVX1-LABEL: ugt_1_v8i32:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm4
+; AVX1-NEXT:    vpand %xmm1, %xmm4, %xmm4
+; AVX1-NEXT:    vpshufb %xmm4, %xmm3, %xmm4
+; AVX1-NEXT:    vpaddb %xmm2, %xmm4, %xmm2
+; AVX1-NEXT:    vpxor %xmm4, %xmm4, %xmm4
+; AVX1-NEXT:    vpunpckhdq {{.*#+}} xmm5 = xmm2[2],xmm4[2],xmm2[3],xmm4[3]
+; AVX1-NEXT:    vpsadbw %xmm4, %xmm5, %xmm5
+; AVX1-NEXT:    vpmovzxdq {{.*#+}} xmm2 = xmm2[0],zero,xmm2[1],zero
+; AVX1-NEXT:    vpsadbw %xmm4, %xmm2, %xmm2
+; AVX1-NEXT:    vpackuswb %xmm5, %xmm2, %xmm2
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm5
+; AVX1-NEXT:    vpshufb %xmm5, %xmm3, %xmm5
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX1-NEXT:    vpaddb %xmm5, %xmm0, %xmm0
+; AVX1-NEXT:    vpunpckhdq {{.*#+}} xmm1 = xmm0[2],xmm4[2],xmm0[3],xmm4[3]
+; AVX1-NEXT:    vpsadbw %xmm4, %xmm1, %xmm1
+; AVX1-NEXT:    vpmovzxdq {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero
+; AVX1-NEXT:    vpsadbw %xmm4, %xmm0, %xmm0
+; AVX1-NEXT:    vpackuswb %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [1,1,1,1]
+; AVX1-NEXT:    vpcmpgtd %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpcmpgtd %xmm1, %xmm2, %xmm1
+; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: ugt_1_v8i32:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX2-NEXT:    vpand %ymm1, %ymm0, %ymm2
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX2-NEXT:    vpshufb %ymm2, %ymm3, %ymm2
+; AVX2-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX2-NEXT:    vpand %ymm1, %ymm0, %ymm0
+; AVX2-NEXT:    vpshufb %ymm0, %ymm3, %ymm0
+; AVX2-NEXT:    vpaddb %ymm2, %ymm0, %ymm0
+; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX2-NEXT:    vpunpckhdq {{.*#+}} ymm2 = ymm0[2],ymm1[2],ymm0[3],ymm1[3],ymm0[6],ymm1[6],ymm0[7],ymm1[7]
+; AVX2-NEXT:    vpsadbw %ymm1, %ymm2, %ymm2
+; AVX2-NEXT:    vpunpckldq {{.*#+}} ymm0 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[4],ymm1[4],ymm0[5],ymm1[5]
+; AVX2-NEXT:    vpsadbw %ymm1, %ymm0, %ymm0
+; AVX2-NEXT:    vpackuswb %ymm2, %ymm0, %ymm0
+; AVX2-NEXT:    vpbroadcastd {{.*#+}} ymm1 = [1,1,1,1,1,1,1,1]
+; AVX2-NEXT:    vpcmpgtd %ymm1, %ymm0, %ymm0
+; AVX2-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: ugt_1_v8i32:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpopcntd %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpbroadcastd {{.*#+}} ymm1 = [1,1,1,1,1,1,1,1]
+; AVX512VPOPCNTDQ-NEXT:    vpcmpgtd %ymm1, %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; AVX512VPOPCNTDQVL-LABEL: ugt_1_v8i32:
+; AVX512VPOPCNTDQVL:       # %bb.0:
+; AVX512VPOPCNTDQVL-NEXT:    vpopcntd %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpnleud {{.*}}(%rip){1to8}, %ymm0, %k1
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpeqd %ymm0, %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vmovdqa32 %ymm0, %ymm0 {%k1} {z}
+; AVX512VPOPCNTDQVL-NEXT:    retq
+;
+; BITALG_NOVLX-LABEL: ugt_1_v8i32:
+; BITALG_NOVLX:       # %bb.0:
+; BITALG_NOVLX-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; BITALG_NOVLX-NEXT:    vpopcntb %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG_NOVLX-NEXT:    vpunpckhdq {{.*#+}} ymm2 = ymm0[2],ymm1[2],ymm0[3],ymm1[3],ymm0[6],ymm1[6],ymm0[7],ymm1[7]
+; BITALG_NOVLX-NEXT:    vpsadbw %ymm1, %ymm2, %ymm2
+; BITALG_NOVLX-NEXT:    vpunpckldq {{.*#+}} ymm0 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[4],ymm1[4],ymm0[5],ymm1[5]
+; BITALG_NOVLX-NEXT:    vpsadbw %ymm1, %ymm0, %ymm0
+; BITALG_NOVLX-NEXT:    vpackuswb %ymm2, %ymm0, %ymm0
+; BITALG_NOVLX-NEXT:    vpbroadcastd {{.*#+}} ymm1 = [1,1,1,1,1,1,1,1]
+; BITALG_NOVLX-NEXT:    vpcmpgtd %ymm1, %ymm0, %ymm0
+; BITALG_NOVLX-NEXT:    retq
+;
+; BITALG-LABEL: ugt_1_v8i32:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntb %ymm0, %ymm0
+; BITALG-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG-NEXT:    vpunpckhdq {{.*#+}} ymm2 = ymm0[2],ymm1[2],ymm0[3],ymm1[3],ymm0[6],ymm1[6],ymm0[7],ymm1[7]
+; BITALG-NEXT:    vpsadbw %ymm1, %ymm2, %ymm2
+; BITALG-NEXT:    vpunpckldq {{.*#+}} ymm0 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[4],ymm1[4],ymm0[5],ymm1[5]
+; BITALG-NEXT:    vpsadbw %ymm1, %ymm0, %ymm0
+; BITALG-NEXT:    vpackuswb %ymm2, %ymm0, %ymm0
+; BITALG-NEXT:    vpcmpnleud {{.*}}(%rip){1to8}, %ymm0, %k1
+; BITALG-NEXT:    vpcmpeqd %ymm0, %ymm0, %ymm0
+; BITALG-NEXT:    vmovdqa32 %ymm0, %ymm0 {%k1} {z}
+; BITALG-NEXT:    retq
+  %2 = tail call <8 x i32> @llvm.ctpop.v8i32(<8 x i32> %0)
+  %3 = icmp ugt <8 x i32> %2, <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
+  %4 = sext <8 x i1> %3 to <8 x i32>
+  ret <8 x i32> %4
+}
+
+define <8 x i32> @eq_1_v8i32(<8 x i32> %0) {
+; AVX1-LABEL: eq_1_v8i32:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm4
+; AVX1-NEXT:    vpand %xmm1, %xmm4, %xmm4
+; AVX1-NEXT:    vpshufb %xmm4, %xmm3, %xmm4
+; AVX1-NEXT:    vpaddb %xmm2, %xmm4, %xmm2
+; AVX1-NEXT:    vpxor %xmm4, %xmm4, %xmm4
+; AVX1-NEXT:    vpunpckhdq {{.*#+}} xmm5 = xmm2[2],xmm4[2],xmm2[3],xmm4[3]
+; AVX1-NEXT:    vpsadbw %xmm4, %xmm5, %xmm5
+; AVX1-NEXT:    vpmovzxdq {{.*#+}} xmm2 = xmm2[0],zero,xmm2[1],zero
+; AVX1-NEXT:    vpsadbw %xmm4, %xmm2, %xmm2
+; AVX1-NEXT:    vpackuswb %xmm5, %xmm2, %xmm2
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm5
+; AVX1-NEXT:    vpshufb %xmm5, %xmm3, %xmm5
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX1-NEXT:    vpaddb %xmm5, %xmm0, %xmm0
+; AVX1-NEXT:    vpunpckhdq {{.*#+}} xmm1 = xmm0[2],xmm4[2],xmm0[3],xmm4[3]
+; AVX1-NEXT:    vpsadbw %xmm4, %xmm1, %xmm1
+; AVX1-NEXT:    vpmovzxdq {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero
+; AVX1-NEXT:    vpsadbw %xmm4, %xmm0, %xmm0
+; AVX1-NEXT:    vpackuswb %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [1,1,1,1]
+; AVX1-NEXT:    vpcmpeqd %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpcmpeqd %xmm1, %xmm2, %xmm1
+; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: eq_1_v8i32:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX2-NEXT:    vpand %ymm1, %ymm0, %ymm2
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX2-NEXT:    vpshufb %ymm2, %ymm3, %ymm2
+; AVX2-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX2-NEXT:    vpand %ymm1, %ymm0, %ymm0
+; AVX2-NEXT:    vpshufb %ymm0, %ymm3, %ymm0
+; AVX2-NEXT:    vpaddb %ymm2, %ymm0, %ymm0
+; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX2-NEXT:    vpunpckhdq {{.*#+}} ymm2 = ymm0[2],ymm1[2],ymm0[3],ymm1[3],ymm0[6],ymm1[6],ymm0[7],ymm1[7]
+; AVX2-NEXT:    vpsadbw %ymm1, %ymm2, %ymm2
+; AVX2-NEXT:    vpunpckldq {{.*#+}} ymm0 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[4],ymm1[4],ymm0[5],ymm1[5]
+; AVX2-NEXT:    vpsadbw %ymm1, %ymm0, %ymm0
+; AVX2-NEXT:    vpackuswb %ymm2, %ymm0, %ymm0
+; AVX2-NEXT:    vpbroadcastd {{.*#+}} ymm1 = [1,1,1,1,1,1,1,1]
+; AVX2-NEXT:    vpcmpeqd %ymm1, %ymm0, %ymm0
+; AVX2-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: eq_1_v8i32:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpopcntd %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpbroadcastd {{.*#+}} ymm1 = [1,1,1,1,1,1,1,1]
+; AVX512VPOPCNTDQ-NEXT:    vpcmpeqd %ymm1, %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; AVX512VPOPCNTDQVL-LABEL: eq_1_v8i32:
+; AVX512VPOPCNTDQVL:       # %bb.0:
+; AVX512VPOPCNTDQVL-NEXT:    vpopcntd %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vpbroadcastd {{.*#+}} ymm1 = [1,1,1,1,1,1,1,1]
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpeqd %ymm1, %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    retq
+;
+; BITALG_NOVLX-LABEL: eq_1_v8i32:
+; BITALG_NOVLX:       # %bb.0:
+; BITALG_NOVLX-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; BITALG_NOVLX-NEXT:    vpopcntb %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG_NOVLX-NEXT:    vpunpckhdq {{.*#+}} ymm2 = ymm0[2],ymm1[2],ymm0[3],ymm1[3],ymm0[6],ymm1[6],ymm0[7],ymm1[7]
+; BITALG_NOVLX-NEXT:    vpsadbw %ymm1, %ymm2, %ymm2
+; BITALG_NOVLX-NEXT:    vpunpckldq {{.*#+}} ymm0 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[4],ymm1[4],ymm0[5],ymm1[5]
+; BITALG_NOVLX-NEXT:    vpsadbw %ymm1, %ymm0, %ymm0
+; BITALG_NOVLX-NEXT:    vpackuswb %ymm2, %ymm0, %ymm0
+; BITALG_NOVLX-NEXT:    vpbroadcastd {{.*#+}} ymm1 = [1,1,1,1,1,1,1,1]
+; BITALG_NOVLX-NEXT:    vpcmpeqd %ymm1, %ymm0, %ymm0
+; BITALG_NOVLX-NEXT:    retq
+;
+; BITALG-LABEL: eq_1_v8i32:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntb %ymm0, %ymm0
+; BITALG-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG-NEXT:    vpunpckhdq {{.*#+}} ymm2 = ymm0[2],ymm1[2],ymm0[3],ymm1[3],ymm0[6],ymm1[6],ymm0[7],ymm1[7]
+; BITALG-NEXT:    vpsadbw %ymm1, %ymm2, %ymm2
+; BITALG-NEXT:    vpunpckldq {{.*#+}} ymm0 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[4],ymm1[4],ymm0[5],ymm1[5]
+; BITALG-NEXT:    vpsadbw %ymm1, %ymm0, %ymm0
+; BITALG-NEXT:    vpackuswb %ymm2, %ymm0, %ymm0
+; BITALG-NEXT:    vpbroadcastd {{.*#+}} ymm1 = [1,1,1,1,1,1,1,1]
+; BITALG-NEXT:    vpcmpeqd %ymm1, %ymm0, %ymm0
+; BITALG-NEXT:    retq
+  %2 = tail call <8 x i32> @llvm.ctpop.v8i32(<8 x i32> %0)
+  %3 = icmp eq <8 x i32> %2, <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
+  %4 = sext <8 x i1> %3 to <8 x i32>
+  ret <8 x i32> %4
+}
+
+define <8 x i32> @ne_1_v8i32(<8 x i32> %0) {
+; AVX1-LABEL: ne_1_v8i32:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm4
+; AVX1-NEXT:    vpand %xmm1, %xmm4, %xmm4
+; AVX1-NEXT:    vpshufb %xmm4, %xmm3, %xmm4
+; AVX1-NEXT:    vpaddb %xmm2, %xmm4, %xmm2
+; AVX1-NEXT:    vpxor %xmm4, %xmm4, %xmm4
+; AVX1-NEXT:    vpunpckhdq {{.*#+}} xmm5 = xmm2[2],xmm4[2],xmm2[3],xmm4[3]
+; AVX1-NEXT:    vpsadbw %xmm4, %xmm5, %xmm5
+; AVX1-NEXT:    vpmovzxdq {{.*#+}} xmm2 = xmm2[0],zero,xmm2[1],zero
+; AVX1-NEXT:    vpsadbw %xmm4, %xmm2, %xmm2
+; AVX1-NEXT:    vpackuswb %xmm5, %xmm2, %xmm2
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm5
+; AVX1-NEXT:    vpshufb %xmm5, %xmm3, %xmm5
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX1-NEXT:    vpaddb %xmm5, %xmm0, %xmm0
+; AVX1-NEXT:    vpunpckhdq {{.*#+}} xmm1 = xmm0[2],xmm4[2],xmm0[3],xmm4[3]
+; AVX1-NEXT:    vpsadbw %xmm4, %xmm1, %xmm1
+; AVX1-NEXT:    vpmovzxdq {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero
+; AVX1-NEXT:    vpsadbw %xmm4, %xmm0, %xmm0
+; AVX1-NEXT:    vpackuswb %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [1,1,1,1]
+; AVX1-NEXT:    vpcmpeqd %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpcmpeqd %xmm3, %xmm3, %xmm3
+; AVX1-NEXT:    vpxor %xmm3, %xmm0, %xmm0
+; AVX1-NEXT:    vpcmpeqd %xmm1, %xmm2, %xmm1
+; AVX1-NEXT:    vpxor %xmm3, %xmm1, %xmm1
+; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: ne_1_v8i32:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX2-NEXT:    vpand %ymm1, %ymm0, %ymm2
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX2-NEXT:    vpshufb %ymm2, %ymm3, %ymm2
+; AVX2-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX2-NEXT:    vpand %ymm1, %ymm0, %ymm0
+; AVX2-NEXT:    vpshufb %ymm0, %ymm3, %ymm0
+; AVX2-NEXT:    vpaddb %ymm2, %ymm0, %ymm0
+; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX2-NEXT:    vpunpckhdq {{.*#+}} ymm2 = ymm0[2],ymm1[2],ymm0[3],ymm1[3],ymm0[6],ymm1[6],ymm0[7],ymm1[7]
+; AVX2-NEXT:    vpsadbw %ymm1, %ymm2, %ymm2
+; AVX2-NEXT:    vpunpckldq {{.*#+}} ymm0 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[4],ymm1[4],ymm0[5],ymm1[5]
+; AVX2-NEXT:    vpsadbw %ymm1, %ymm0, %ymm0
+; AVX2-NEXT:    vpackuswb %ymm2, %ymm0, %ymm0
+; AVX2-NEXT:    vpbroadcastd {{.*#+}} ymm1 = [1,1,1,1,1,1,1,1]
+; AVX2-NEXT:    vpcmpeqd %ymm1, %ymm0, %ymm0
+; AVX2-NEXT:    vpcmpeqd %ymm1, %ymm1, %ymm1
+; AVX2-NEXT:    vpxor %ymm1, %ymm0, %ymm0
+; AVX2-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: ne_1_v8i32:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpopcntd %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpbroadcastd {{.*#+}} ymm1 = [1,1,1,1,1,1,1,1]
+; AVX512VPOPCNTDQ-NEXT:    vpcmpeqd %ymm1, %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    vpternlogq $15, %zmm0, %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    # kill: def $ymm0 killed $ymm0 killed $zmm0
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; AVX512VPOPCNTDQVL-LABEL: ne_1_v8i32:
+; AVX512VPOPCNTDQVL:       # %bb.0:
+; AVX512VPOPCNTDQVL-NEXT:    vpopcntd %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vpbroadcastd {{.*#+}} ymm1 = [1,1,1,1,1,1,1,1]
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpeqd %ymm1, %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vpternlogq $15, %ymm0, %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    retq
+;
+; BITALG_NOVLX-LABEL: ne_1_v8i32:
+; BITALG_NOVLX:       # %bb.0:
+; BITALG_NOVLX-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; BITALG_NOVLX-NEXT:    vpopcntb %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG_NOVLX-NEXT:    vpunpckhdq {{.*#+}} ymm2 = ymm0[2],ymm1[2],ymm0[3],ymm1[3],ymm0[6],ymm1[6],ymm0[7],ymm1[7]
+; BITALG_NOVLX-NEXT:    vpsadbw %ymm1, %ymm2, %ymm2
+; BITALG_NOVLX-NEXT:    vpunpckldq {{.*#+}} ymm0 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[4],ymm1[4],ymm0[5],ymm1[5]
+; BITALG_NOVLX-NEXT:    vpsadbw %ymm1, %ymm0, %ymm0
+; BITALG_NOVLX-NEXT:    vpackuswb %ymm2, %ymm0, %ymm0
+; BITALG_NOVLX-NEXT:    vpbroadcastd {{.*#+}} ymm1 = [1,1,1,1,1,1,1,1]
+; BITALG_NOVLX-NEXT:    vpcmpeqd %ymm1, %ymm0, %ymm0
+; BITALG_NOVLX-NEXT:    vpternlogq $15, %zmm0, %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    # kill: def $ymm0 killed $ymm0 killed $zmm0
+; BITALG_NOVLX-NEXT:    retq
+;
+; BITALG-LABEL: ne_1_v8i32:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntb %ymm0, %ymm0
+; BITALG-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG-NEXT:    vpunpckhdq {{.*#+}} ymm2 = ymm0[2],ymm1[2],ymm0[3],ymm1[3],ymm0[6],ymm1[6],ymm0[7],ymm1[7]
+; BITALG-NEXT:    vpsadbw %ymm1, %ymm2, %ymm2
+; BITALG-NEXT:    vpunpckldq {{.*#+}} ymm0 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[4],ymm1[4],ymm0[5],ymm1[5]
+; BITALG-NEXT:    vpsadbw %ymm1, %ymm0, %ymm0
+; BITALG-NEXT:    vpackuswb %ymm2, %ymm0, %ymm0
+; BITALG-NEXT:    vpbroadcastd {{.*#+}} ymm1 = [1,1,1,1,1,1,1,1]
+; BITALG-NEXT:    vpcmpeqd %ymm1, %ymm0, %ymm0
+; BITALG-NEXT:    vpternlogq $15, %ymm0, %ymm0, %ymm0
+; BITALG-NEXT:    retq
+  %2 = tail call <8 x i32> @llvm.ctpop.v8i32(<8 x i32> %0)
+  %3 = icmp ne <8 x i32> %2, <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
+  %4 = sext <8 x i1> %3 to <8 x i32>
+  ret <8 x i32> %4
+}
+
+define <16 x i16> @ult_2_v16i16(<16 x i16> %0) {
+; AVX1-LABEL: ult_2_v16i16:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm4
+; AVX1-NEXT:    vpand %xmm1, %xmm4, %xmm4
+; AVX1-NEXT:    vpshufb %xmm4, %xmm3, %xmm4
+; AVX1-NEXT:    vpaddb %xmm2, %xmm4, %xmm2
+; AVX1-NEXT:    vpsllw $8, %xmm2, %xmm4
+; AVX1-NEXT:    vpaddb %xmm2, %xmm4, %xmm2
+; AVX1-NEXT:    vpsrlw $8, %xmm2, %xmm2
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm4
+; AVX1-NEXT:    vpshufb %xmm4, %xmm3, %xmm4
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX1-NEXT:    vpaddb %xmm4, %xmm0, %xmm0
+; AVX1-NEXT:    vpsllw $8, %xmm0, %xmm1
+; AVX1-NEXT:    vpaddb %xmm0, %xmm1, %xmm0
+; AVX1-NEXT:    vpsrlw $8, %xmm0, %xmm0
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [2,2,2,2,2,2,2,2]
+; AVX1-NEXT:    vpcmpgtw %xmm0, %xmm1, %xmm0
+; AVX1-NEXT:    vpcmpgtw %xmm2, %xmm1, %xmm1
+; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: ult_2_v16i16:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX2-NEXT:    vpand %ymm1, %ymm0, %ymm2
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX2-NEXT:    vpshufb %ymm2, %ymm3, %ymm2
+; AVX2-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX2-NEXT:    vpand %ymm1, %ymm0, %ymm0
+; AVX2-NEXT:    vpshufb %ymm0, %ymm3, %ymm0
+; AVX2-NEXT:    vpaddb %ymm2, %ymm0, %ymm0
+; AVX2-NEXT:    vpsllw $8, %ymm0, %ymm1
+; AVX2-NEXT:    vpaddb %ymm0, %ymm1, %ymm0
+; AVX2-NEXT:    vpsrlw $8, %ymm0, %ymm0
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2]
+; AVX2-NEXT:    vpcmpgtw %ymm0, %ymm1, %ymm0
+; AVX2-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: ult_2_v16i16:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
+; AVX512VPOPCNTDQ-NEXT:    vpopcntd %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpmovdw %zmm0, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    vmovdqa {{.*#+}} ymm1 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2]
+; AVX512VPOPCNTDQ-NEXT:    vpcmpgtw %ymm0, %ymm1, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; AVX512VPOPCNTDQVL-LABEL: ult_2_v16i16:
+; AVX512VPOPCNTDQVL:       # %bb.0:
+; AVX512VPOPCNTDQVL-NEXT:    vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
+; AVX512VPOPCNTDQVL-NEXT:    vpopcntd %zmm0, %zmm0
+; AVX512VPOPCNTDQVL-NEXT:    vpmovdw %zmm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vmovdqa {{.*#+}} ymm1 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2]
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpgtw %ymm0, %ymm1, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    retq
+;
+; BITALG_NOVLX-LABEL: ult_2_v16i16:
+; BITALG_NOVLX:       # %bb.0:
+; BITALG_NOVLX-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; BITALG_NOVLX-NEXT:    vpopcntw %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    vmovdqa {{.*#+}} ymm1 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2]
+; BITALG_NOVLX-NEXT:    vpcmpgtw %ymm0, %ymm1, %ymm0
+; BITALG_NOVLX-NEXT:    retq
+;
+; BITALG-LABEL: ult_2_v16i16:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntw %ymm0, %ymm0
+; BITALG-NEXT:    vpcmpltuw {{.*}}(%rip), %ymm0, %k0
+; BITALG-NEXT:    vpmovm2w %k0, %ymm0
+; BITALG-NEXT:    retq
+  %2 = tail call <16 x i16> @llvm.ctpop.v16i16(<16 x i16> %0)
+  %3 = icmp ult <16 x i16> %2, <i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2>
+  %4 = sext <16 x i1> %3 to <16 x i16>
+  ret <16 x i16> %4
+}
+
+define <16 x i16> @ugt_1_v16i16(<16 x i16> %0) {
+; AVX1-LABEL: ugt_1_v16i16:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm4
+; AVX1-NEXT:    vpand %xmm1, %xmm4, %xmm4
+; AVX1-NEXT:    vpshufb %xmm4, %xmm3, %xmm4
+; AVX1-NEXT:    vpaddb %xmm2, %xmm4, %xmm2
+; AVX1-NEXT:    vpsllw $8, %xmm2, %xmm4
+; AVX1-NEXT:    vpaddb %xmm2, %xmm4, %xmm2
+; AVX1-NEXT:    vpsrlw $8, %xmm2, %xmm2
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm4
+; AVX1-NEXT:    vpshufb %xmm4, %xmm3, %xmm4
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX1-NEXT:    vpaddb %xmm4, %xmm0, %xmm0
+; AVX1-NEXT:    vpsllw $8, %xmm0, %xmm1
+; AVX1-NEXT:    vpaddb %xmm0, %xmm1, %xmm0
+; AVX1-NEXT:    vpsrlw $8, %xmm0, %xmm0
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [1,1,1,1,1,1,1,1]
+; AVX1-NEXT:    vpcmpgtw %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpcmpgtw %xmm1, %xmm2, %xmm1
+; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: ugt_1_v16i16:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX2-NEXT:    vpand %ymm1, %ymm0, %ymm2
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX2-NEXT:    vpshufb %ymm2, %ymm3, %ymm2
+; AVX2-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX2-NEXT:    vpand %ymm1, %ymm0, %ymm0
+; AVX2-NEXT:    vpshufb %ymm0, %ymm3, %ymm0
+; AVX2-NEXT:    vpaddb %ymm2, %ymm0, %ymm0
+; AVX2-NEXT:    vpsllw $8, %ymm0, %ymm1
+; AVX2-NEXT:    vpaddb %ymm0, %ymm1, %ymm0
+; AVX2-NEXT:    vpsrlw $8, %ymm0, %ymm0
+; AVX2-NEXT:    vpcmpgtw {{.*}}(%rip), %ymm0, %ymm0
+; AVX2-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: ugt_1_v16i16:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
+; AVX512VPOPCNTDQ-NEXT:    vpopcntd %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpmovdw %zmm0, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    vpcmpgtw {{.*}}(%rip), %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; AVX512VPOPCNTDQVL-LABEL: ugt_1_v16i16:
+; AVX512VPOPCNTDQVL:       # %bb.0:
+; AVX512VPOPCNTDQVL-NEXT:    vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
+; AVX512VPOPCNTDQVL-NEXT:    vpopcntd %zmm0, %zmm0
+; AVX512VPOPCNTDQVL-NEXT:    vpmovdw %zmm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpgtw {{.*}}(%rip), %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    retq
+;
+; BITALG_NOVLX-LABEL: ugt_1_v16i16:
+; BITALG_NOVLX:       # %bb.0:
+; BITALG_NOVLX-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; BITALG_NOVLX-NEXT:    vpopcntw %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    vpcmpgtw {{.*}}(%rip), %ymm0, %ymm0
+; BITALG_NOVLX-NEXT:    retq
+;
+; BITALG-LABEL: ugt_1_v16i16:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntw %ymm0, %ymm0
+; BITALG-NEXT:    vpcmpnleuw {{.*}}(%rip), %ymm0, %k0
+; BITALG-NEXT:    vpmovm2w %k0, %ymm0
+; BITALG-NEXT:    retq
+  %2 = tail call <16 x i16> @llvm.ctpop.v16i16(<16 x i16> %0)
+  %3 = icmp ugt <16 x i16> %2, <i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1>
+  %4 = sext <16 x i1> %3 to <16 x i16>
+  ret <16 x i16> %4
+}
+
+define <16 x i16> @eq_1_v16i16(<16 x i16> %0) {
+; AVX1-LABEL: eq_1_v16i16:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm4
+; AVX1-NEXT:    vpand %xmm1, %xmm4, %xmm4
+; AVX1-NEXT:    vpshufb %xmm4, %xmm3, %xmm4
+; AVX1-NEXT:    vpaddb %xmm2, %xmm4, %xmm2
+; AVX1-NEXT:    vpsllw $8, %xmm2, %xmm4
+; AVX1-NEXT:    vpaddb %xmm2, %xmm4, %xmm2
+; AVX1-NEXT:    vpsrlw $8, %xmm2, %xmm2
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm4
+; AVX1-NEXT:    vpshufb %xmm4, %xmm3, %xmm4
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX1-NEXT:    vpaddb %xmm4, %xmm0, %xmm0
+; AVX1-NEXT:    vpsllw $8, %xmm0, %xmm1
+; AVX1-NEXT:    vpaddb %xmm0, %xmm1, %xmm0
+; AVX1-NEXT:    vpsrlw $8, %xmm0, %xmm0
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [1,1,1,1,1,1,1,1]
+; AVX1-NEXT:    vpcmpeqw %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpcmpeqw %xmm1, %xmm2, %xmm1
+; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: eq_1_v16i16:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX2-NEXT:    vpand %ymm1, %ymm0, %ymm2
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX2-NEXT:    vpshufb %ymm2, %ymm3, %ymm2
+; AVX2-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX2-NEXT:    vpand %ymm1, %ymm0, %ymm0
+; AVX2-NEXT:    vpshufb %ymm0, %ymm3, %ymm0
+; AVX2-NEXT:    vpaddb %ymm2, %ymm0, %ymm0
+; AVX2-NEXT:    vpsllw $8, %ymm0, %ymm1
+; AVX2-NEXT:    vpaddb %ymm0, %ymm1, %ymm0
+; AVX2-NEXT:    vpsrlw $8, %ymm0, %ymm0
+; AVX2-NEXT:    vpcmpeqw {{.*}}(%rip), %ymm0, %ymm0
+; AVX2-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: eq_1_v16i16:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
+; AVX512VPOPCNTDQ-NEXT:    vpopcntd %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpmovdw %zmm0, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    vpcmpeqw {{.*}}(%rip), %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; AVX512VPOPCNTDQVL-LABEL: eq_1_v16i16:
+; AVX512VPOPCNTDQVL:       # %bb.0:
+; AVX512VPOPCNTDQVL-NEXT:    vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
+; AVX512VPOPCNTDQVL-NEXT:    vpopcntd %zmm0, %zmm0
+; AVX512VPOPCNTDQVL-NEXT:    vpmovdw %zmm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpeqw {{.*}}(%rip), %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    retq
+;
+; BITALG_NOVLX-LABEL: eq_1_v16i16:
+; BITALG_NOVLX:       # %bb.0:
+; BITALG_NOVLX-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; BITALG_NOVLX-NEXT:    vpopcntw %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    vpcmpeqw {{.*}}(%rip), %ymm0, %ymm0
+; BITALG_NOVLX-NEXT:    retq
+;
+; BITALG-LABEL: eq_1_v16i16:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntw %ymm0, %ymm0
+; BITALG-NEXT:    vpcmpeqw {{.*}}(%rip), %ymm0, %ymm0
+; BITALG-NEXT:    retq
+  %2 = tail call <16 x i16> @llvm.ctpop.v16i16(<16 x i16> %0)
+  %3 = icmp eq <16 x i16> %2, <i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1>
+  %4 = sext <16 x i1> %3 to <16 x i16>
+  ret <16 x i16> %4
+}
+
+define <16 x i16> @ne_1_v16i16(<16 x i16> %0) {
+; AVX1-LABEL: ne_1_v16i16:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm4
+; AVX1-NEXT:    vpand %xmm1, %xmm4, %xmm4
+; AVX1-NEXT:    vpshufb %xmm4, %xmm3, %xmm4
+; AVX1-NEXT:    vpaddb %xmm2, %xmm4, %xmm2
+; AVX1-NEXT:    vpsllw $8, %xmm2, %xmm4
+; AVX1-NEXT:    vpaddb %xmm2, %xmm4, %xmm2
+; AVX1-NEXT:    vpsrlw $8, %xmm2, %xmm2
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm4
+; AVX1-NEXT:    vpshufb %xmm4, %xmm3, %xmm4
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX1-NEXT:    vpaddb %xmm4, %xmm0, %xmm0
+; AVX1-NEXT:    vpsllw $8, %xmm0, %xmm1
+; AVX1-NEXT:    vpaddb %xmm0, %xmm1, %xmm0
+; AVX1-NEXT:    vpsrlw $8, %xmm0, %xmm0
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [1,1,1,1,1,1,1,1]
+; AVX1-NEXT:    vpcmpeqw %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpcmpeqd %xmm3, %xmm3, %xmm3
+; AVX1-NEXT:    vpxor %xmm3, %xmm0, %xmm0
+; AVX1-NEXT:    vpcmpeqw %xmm1, %xmm2, %xmm1
+; AVX1-NEXT:    vpxor %xmm3, %xmm1, %xmm1
+; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: ne_1_v16i16:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX2-NEXT:    vpand %ymm1, %ymm0, %ymm2
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX2-NEXT:    vpshufb %ymm2, %ymm3, %ymm2
+; AVX2-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX2-NEXT:    vpand %ymm1, %ymm0, %ymm0
+; AVX2-NEXT:    vpshufb %ymm0, %ymm3, %ymm0
+; AVX2-NEXT:    vpaddb %ymm2, %ymm0, %ymm0
+; AVX2-NEXT:    vpsllw $8, %ymm0, %ymm1
+; AVX2-NEXT:    vpaddb %ymm0, %ymm1, %ymm0
+; AVX2-NEXT:    vpsrlw $8, %ymm0, %ymm0
+; AVX2-NEXT:    vpcmpeqw {{.*}}(%rip), %ymm0, %ymm0
+; AVX2-NEXT:    vpcmpeqd %ymm1, %ymm1, %ymm1
+; AVX2-NEXT:    vpxor %ymm1, %ymm0, %ymm0
+; AVX2-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: ne_1_v16i16:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
+; AVX512VPOPCNTDQ-NEXT:    vpopcntd %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpmovdw %zmm0, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    vpcmpeqw {{.*}}(%rip), %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    vpternlogq $15, %zmm0, %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    # kill: def $ymm0 killed $ymm0 killed $zmm0
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; AVX512VPOPCNTDQVL-LABEL: ne_1_v16i16:
+; AVX512VPOPCNTDQVL:       # %bb.0:
+; AVX512VPOPCNTDQVL-NEXT:    vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
+; AVX512VPOPCNTDQVL-NEXT:    vpopcntd %zmm0, %zmm0
+; AVX512VPOPCNTDQVL-NEXT:    vpmovdw %zmm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpeqw {{.*}}(%rip), %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vpternlogq $15, %ymm0, %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    retq
+;
+; BITALG_NOVLX-LABEL: ne_1_v16i16:
+; BITALG_NOVLX:       # %bb.0:
+; BITALG_NOVLX-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; BITALG_NOVLX-NEXT:    vpopcntw %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    vpcmpeqw {{.*}}(%rip), %ymm0, %ymm0
+; BITALG_NOVLX-NEXT:    vpternlogq $15, %zmm0, %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    # kill: def $ymm0 killed $ymm0 killed $zmm0
+; BITALG_NOVLX-NEXT:    retq
+;
+; BITALG-LABEL: ne_1_v16i16:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntw %ymm0, %ymm0
+; BITALG-NEXT:    vpcmpeqw {{.*}}(%rip), %ymm0, %ymm0
+; BITALG-NEXT:    vpternlogq $15, %ymm0, %ymm0, %ymm0
+; BITALG-NEXT:    retq
+  %2 = tail call <16 x i16> @llvm.ctpop.v16i16(<16 x i16> %0)
+  %3 = icmp ne <16 x i16> %2, <i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1>
+  %4 = sext <16 x i1> %3 to <16 x i16>
+  ret <16 x i16> %4
+}
+
+define <32 x i8> @ult_2_v32i8(<32 x i8> %0) {
+; AVX1-LABEL: ult_2_v32i8:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm4
+; AVX1-NEXT:    vpand %xmm1, %xmm4, %xmm4
+; AVX1-NEXT:    vpshufb %xmm4, %xmm3, %xmm4
+; AVX1-NEXT:    vpaddb %xmm2, %xmm4, %xmm2
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm4
+; AVX1-NEXT:    vpshufb %xmm4, %xmm3, %xmm4
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX1-NEXT:    vpaddb %xmm4, %xmm0, %xmm0
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1]
+; AVX1-NEXT:    vpminub %xmm1, %xmm0, %xmm3
+; AVX1-NEXT:    vpcmpeqb %xmm3, %xmm0, %xmm0
+; AVX1-NEXT:    vpminub %xmm1, %xmm2, %xmm1
+; AVX1-NEXT:    vpcmpeqb %xmm1, %xmm2, %xmm1
+; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: ult_2_v32i8:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX2-NEXT:    vpand %ymm1, %ymm0, %ymm2
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX2-NEXT:    vpshufb %ymm2, %ymm3, %ymm2
+; AVX2-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX2-NEXT:    vpand %ymm1, %ymm0, %ymm0
+; AVX2-NEXT:    vpshufb %ymm0, %ymm3, %ymm0
+; AVX2-NEXT:    vpaddb %ymm2, %ymm0, %ymm0
+; AVX2-NEXT:    vpminub {{.*}}(%rip), %ymm0, %ymm1
+; AVX2-NEXT:    vpcmpeqb %ymm1, %ymm0, %ymm0
+; AVX2-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: ult_2_v32i8:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    vmovdqa {{.*#+}} ymm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512VPOPCNTDQ-NEXT:    vpand %ymm1, %ymm0, %ymm2
+; AVX512VPOPCNTDQ-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512VPOPCNTDQ-NEXT:    vpshufb %ymm2, %ymm3, %ymm2
+; AVX512VPOPCNTDQ-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    vpand %ymm1, %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    vpshufb %ymm0, %ymm3, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    vpaddb %ymm2, %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    vpminub {{.*}}(%rip), %ymm0, %ymm1
+; AVX512VPOPCNTDQ-NEXT:    vpcmpeqb %ymm1, %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; AVX512VPOPCNTDQVL-LABEL: ult_2_v32i8:
+; AVX512VPOPCNTDQVL:       # %bb.0:
+; AVX512VPOPCNTDQVL-NEXT:    vmovdqa {{.*#+}} ymm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512VPOPCNTDQVL-NEXT:    vpand %ymm1, %ymm0, %ymm2
+; AVX512VPOPCNTDQVL-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512VPOPCNTDQVL-NEXT:    vpshufb %ymm2, %ymm3, %ymm2
+; AVX512VPOPCNTDQVL-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vpand %ymm1, %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vpshufb %ymm0, %ymm3, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vpaddb %ymm2, %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vpminub {{.*}}(%rip), %ymm0, %ymm1
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpeqb %ymm1, %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    retq
+;
+; BITALG_NOVLX-LABEL: ult_2_v32i8:
+; BITALG_NOVLX:       # %bb.0:
+; BITALG_NOVLX-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; BITALG_NOVLX-NEXT:    vpopcntb %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    vmovdqa {{.*#+}} ymm1 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2]
+; BITALG_NOVLX-NEXT:    vpcmpgtb %ymm0, %ymm1, %ymm0
+; BITALG_NOVLX-NEXT:    retq
+;
+; BITALG-LABEL: ult_2_v32i8:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntb %ymm0, %ymm0
+; BITALG-NEXT:    vpcmpltub {{.*}}(%rip), %ymm0, %k0
+; BITALG-NEXT:    vpmovm2b %k0, %ymm0
+; BITALG-NEXT:    retq
+  %2 = tail call <32 x i8> @llvm.ctpop.v32i8(<32 x i8> %0)
+  %3 = icmp ult <32 x i8> %2, <i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2>
+  %4 = sext <32 x i1> %3 to <32 x i8>
+  ret <32 x i8> %4
+}
+
+define <32 x i8> @ugt_1_v32i8(<32 x i8> %0) {
+; AVX1-LABEL: ugt_1_v32i8:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm4
+; AVX1-NEXT:    vpand %xmm1, %xmm4, %xmm4
+; AVX1-NEXT:    vpshufb %xmm4, %xmm3, %xmm4
+; AVX1-NEXT:    vpaddb %xmm2, %xmm4, %xmm2
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm4
+; AVX1-NEXT:    vpshufb %xmm4, %xmm3, %xmm4
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX1-NEXT:    vpaddb %xmm4, %xmm0, %xmm0
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2]
+; AVX1-NEXT:    vpmaxub %xmm1, %xmm0, %xmm3
+; AVX1-NEXT:    vpcmpeqb %xmm3, %xmm0, %xmm0
+; AVX1-NEXT:    vpmaxub %xmm1, %xmm2, %xmm1
+; AVX1-NEXT:    vpcmpeqb %xmm1, %xmm2, %xmm1
+; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: ugt_1_v32i8:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX2-NEXT:    vpand %ymm1, %ymm0, %ymm2
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX2-NEXT:    vpshufb %ymm2, %ymm3, %ymm2
+; AVX2-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX2-NEXT:    vpand %ymm1, %ymm0, %ymm0
+; AVX2-NEXT:    vpshufb %ymm0, %ymm3, %ymm0
+; AVX2-NEXT:    vpaddb %ymm2, %ymm0, %ymm0
+; AVX2-NEXT:    vpmaxub {{.*}}(%rip), %ymm0, %ymm1
+; AVX2-NEXT:    vpcmpeqb %ymm1, %ymm0, %ymm0
+; AVX2-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: ugt_1_v32i8:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    vmovdqa {{.*#+}} ymm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512VPOPCNTDQ-NEXT:    vpand %ymm1, %ymm0, %ymm2
+; AVX512VPOPCNTDQ-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512VPOPCNTDQ-NEXT:    vpshufb %ymm2, %ymm3, %ymm2
+; AVX512VPOPCNTDQ-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    vpand %ymm1, %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    vpshufb %ymm0, %ymm3, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    vpaddb %ymm2, %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    vpmaxub {{.*}}(%rip), %ymm0, %ymm1
+; AVX512VPOPCNTDQ-NEXT:    vpcmpeqb %ymm1, %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; AVX512VPOPCNTDQVL-LABEL: ugt_1_v32i8:
+; AVX512VPOPCNTDQVL:       # %bb.0:
+; AVX512VPOPCNTDQVL-NEXT:    vmovdqa {{.*#+}} ymm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512VPOPCNTDQVL-NEXT:    vpand %ymm1, %ymm0, %ymm2
+; AVX512VPOPCNTDQVL-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512VPOPCNTDQVL-NEXT:    vpshufb %ymm2, %ymm3, %ymm2
+; AVX512VPOPCNTDQVL-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vpand %ymm1, %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vpshufb %ymm0, %ymm3, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vpaddb %ymm2, %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vpmaxub {{.*}}(%rip), %ymm0, %ymm1
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpeqb %ymm1, %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    retq
+;
+; BITALG_NOVLX-LABEL: ugt_1_v32i8:
+; BITALG_NOVLX:       # %bb.0:
+; BITALG_NOVLX-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; BITALG_NOVLX-NEXT:    vpopcntb %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    vpcmpgtb {{.*}}(%rip), %ymm0, %ymm0
+; BITALG_NOVLX-NEXT:    retq
+;
+; BITALG-LABEL: ugt_1_v32i8:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntb %ymm0, %ymm0
+; BITALG-NEXT:    vpcmpnleub {{.*}}(%rip), %ymm0, %k0
+; BITALG-NEXT:    vpmovm2b %k0, %ymm0
+; BITALG-NEXT:    retq
+  %2 = tail call <32 x i8> @llvm.ctpop.v32i8(<32 x i8> %0)
+  %3 = icmp ugt <32 x i8> %2, <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
+  %4 = sext <32 x i1> %3 to <32 x i8>
+  ret <32 x i8> %4
+}
+
+define <32 x i8> @eq_1_v32i8(<32 x i8> %0) {
+; AVX1-LABEL: eq_1_v32i8:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm4
+; AVX1-NEXT:    vpand %xmm1, %xmm4, %xmm4
+; AVX1-NEXT:    vpshufb %xmm4, %xmm3, %xmm4
+; AVX1-NEXT:    vpaddb %xmm2, %xmm4, %xmm2
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm4
+; AVX1-NEXT:    vpshufb %xmm4, %xmm3, %xmm4
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX1-NEXT:    vpaddb %xmm4, %xmm0, %xmm0
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1]
+; AVX1-NEXT:    vpcmpeqb %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpcmpeqb %xmm1, %xmm2, %xmm1
+; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: eq_1_v32i8:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX2-NEXT:    vpand %ymm1, %ymm0, %ymm2
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX2-NEXT:    vpshufb %ymm2, %ymm3, %ymm2
+; AVX2-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX2-NEXT:    vpand %ymm1, %ymm0, %ymm0
+; AVX2-NEXT:    vpshufb %ymm0, %ymm3, %ymm0
+; AVX2-NEXT:    vpaddb %ymm2, %ymm0, %ymm0
+; AVX2-NEXT:    vpcmpeqb {{.*}}(%rip), %ymm0, %ymm0
+; AVX2-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: eq_1_v32i8:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    vmovdqa {{.*#+}} ymm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512VPOPCNTDQ-NEXT:    vpand %ymm1, %ymm0, %ymm2
+; AVX512VPOPCNTDQ-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512VPOPCNTDQ-NEXT:    vpshufb %ymm2, %ymm3, %ymm2
+; AVX512VPOPCNTDQ-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    vpand %ymm1, %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    vpshufb %ymm0, %ymm3, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    vpaddb %ymm2, %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    vpcmpeqb {{.*}}(%rip), %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; AVX512VPOPCNTDQVL-LABEL: eq_1_v32i8:
+; AVX512VPOPCNTDQVL:       # %bb.0:
+; AVX512VPOPCNTDQVL-NEXT:    vmovdqa {{.*#+}} ymm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512VPOPCNTDQVL-NEXT:    vpand %ymm1, %ymm0, %ymm2
+; AVX512VPOPCNTDQVL-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512VPOPCNTDQVL-NEXT:    vpshufb %ymm2, %ymm3, %ymm2
+; AVX512VPOPCNTDQVL-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vpand %ymm1, %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vpshufb %ymm0, %ymm3, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vpaddb %ymm2, %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpeqb {{.*}}(%rip), %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    retq
+;
+; BITALG_NOVLX-LABEL: eq_1_v32i8:
+; BITALG_NOVLX:       # %bb.0:
+; BITALG_NOVLX-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; BITALG_NOVLX-NEXT:    vpopcntb %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    vpcmpeqb {{.*}}(%rip), %ymm0, %ymm0
+; BITALG_NOVLX-NEXT:    retq
+;
+; BITALG-LABEL: eq_1_v32i8:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntb %ymm0, %ymm0
+; BITALG-NEXT:    vpcmpeqb {{.*}}(%rip), %ymm0, %ymm0
+; BITALG-NEXT:    retq
+  %2 = tail call <32 x i8> @llvm.ctpop.v32i8(<32 x i8> %0)
+  %3 = icmp eq <32 x i8> %2, <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
+  %4 = sext <32 x i1> %3 to <32 x i8>
+  ret <32 x i8> %4
+}
+
+define <32 x i8> @ne_1_v32i8(<32 x i8> %0) {
+; AVX1-LABEL: ne_1_v32i8:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm2
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm4
+; AVX1-NEXT:    vpand %xmm1, %xmm4, %xmm4
+; AVX1-NEXT:    vpshufb %xmm4, %xmm3, %xmm4
+; AVX1-NEXT:    vpaddb %xmm2, %xmm4, %xmm2
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm4
+; AVX1-NEXT:    vpshufb %xmm4, %xmm3, %xmm4
+; AVX1-NEXT:    vpsrlw $4, %xmm0, %xmm0
+; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
+; AVX1-NEXT:    vpaddb %xmm4, %xmm0, %xmm0
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm1 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1]
+; AVX1-NEXT:    vpcmpeqb %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpcmpeqd %xmm3, %xmm3, %xmm3
+; AVX1-NEXT:    vpxor %xmm3, %xmm0, %xmm0
+; AVX1-NEXT:    vpcmpeqb %xmm1, %xmm2, %xmm1
+; AVX1-NEXT:    vpxor %xmm3, %xmm1, %xmm1
+; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: ne_1_v32i8:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX2-NEXT:    vpand %ymm1, %ymm0, %ymm2
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX2-NEXT:    vpshufb %ymm2, %ymm3, %ymm2
+; AVX2-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX2-NEXT:    vpand %ymm1, %ymm0, %ymm0
+; AVX2-NEXT:    vpshufb %ymm0, %ymm3, %ymm0
+; AVX2-NEXT:    vpaddb %ymm2, %ymm0, %ymm0
+; AVX2-NEXT:    vpcmpeqb {{.*}}(%rip), %ymm0, %ymm0
+; AVX2-NEXT:    vpcmpeqd %ymm1, %ymm1, %ymm1
+; AVX2-NEXT:    vpxor %ymm1, %ymm0, %ymm0
+; AVX2-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: ne_1_v32i8:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    vmovdqa {{.*#+}} ymm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512VPOPCNTDQ-NEXT:    vpand %ymm1, %ymm0, %ymm2
+; AVX512VPOPCNTDQ-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512VPOPCNTDQ-NEXT:    vpshufb %ymm2, %ymm3, %ymm2
+; AVX512VPOPCNTDQ-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    vpand %ymm1, %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    vpshufb %ymm0, %ymm3, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    vpaddb %ymm2, %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    vpcmpeqb {{.*}}(%rip), %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NEXT:    vpternlogq $15, %zmm0, %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    # kill: def $ymm0 killed $ymm0 killed $zmm0
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; AVX512VPOPCNTDQVL-LABEL: ne_1_v32i8:
+; AVX512VPOPCNTDQVL:       # %bb.0:
+; AVX512VPOPCNTDQVL-NEXT:    vmovdqa {{.*#+}} ymm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512VPOPCNTDQVL-NEXT:    vpand %ymm1, %ymm0, %ymm2
+; AVX512VPOPCNTDQVL-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512VPOPCNTDQVL-NEXT:    vpshufb %ymm2, %ymm3, %ymm2
+; AVX512VPOPCNTDQVL-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vpand %ymm1, %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vpshufb %ymm0, %ymm3, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vpaddb %ymm2, %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vpcmpeqb {{.*}}(%rip), %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    vpternlogq $15, %ymm0, %ymm0, %ymm0
+; AVX512VPOPCNTDQVL-NEXT:    retq
+;
+; BITALG_NOVLX-LABEL: ne_1_v32i8:
+; BITALG_NOVLX:       # %bb.0:
+; BITALG_NOVLX-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
+; BITALG_NOVLX-NEXT:    vpopcntb %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    vpcmpeqb {{.*}}(%rip), %ymm0, %ymm0
+; BITALG_NOVLX-NEXT:    vpternlogq $15, %zmm0, %zmm0, %zmm0
+; BITALG_NOVLX-NEXT:    # kill: def $ymm0 killed $ymm0 killed $zmm0
+; BITALG_NOVLX-NEXT:    retq
+;
+; BITALG-LABEL: ne_1_v32i8:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntb %ymm0, %ymm0
+; BITALG-NEXT:    vpcmpeqb {{.*}}(%rip), %ymm0, %ymm0
+; BITALG-NEXT:    vpternlogq $15, %ymm0, %ymm0, %ymm0
+; BITALG-NEXT:    retq
+  %2 = tail call <32 x i8> @llvm.ctpop.v32i8(<32 x i8> %0)
+  %3 = icmp ne <32 x i8> %2, <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
+  %4 = sext <32 x i1> %3 to <32 x i8>
+  ret <32 x i8> %4
+}
+
 declare <4 x i64> @llvm.ctpop.v4i64(<4 x i64>)
 declare <8 x i32> @llvm.ctpop.v8i32(<8 x i32>)
 declare <16 x i16> @llvm.ctpop.v16i16(<16 x i16>)
diff --git a/llvm/test/CodeGen/X86/vector-popcnt-512.ll b/llvm/test/CodeGen/X86/vector-popcnt-512.ll
index 721a5a62942a..b48e574854a5 100644
--- a/llvm/test/CodeGen/X86/vector-popcnt-512.ll
+++ b/llvm/test/CodeGen/X86/vector-popcnt-512.ll
@@ -277,6 +277,1298 @@ define <64 x i8> @testv64i8(<64 x i8> %in) nounwind {
   ret <64 x i8> %out
 }
 
+define <8 x i64> @ult_2_v8i64(<8 x i64> %0) {
+; AVX512F-LABEL: ult_2_v8i64:
+; AVX512F:       # %bb.0:
+; AVX512F-NEXT:    vextracti64x4 $1, %zmm0, %ymm1
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm2 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512F-NEXT:    vpand %ymm2, %ymm1, %ymm3
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm4 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512F-NEXT:    vpshufb %ymm3, %ymm4, %ymm3
+; AVX512F-NEXT:    vpsrlw $4, %ymm1, %ymm1
+; AVX512F-NEXT:    vpand %ymm2, %ymm1, %ymm1
+; AVX512F-NEXT:    vpshufb %ymm1, %ymm4, %ymm1
+; AVX512F-NEXT:    vpaddb %ymm3, %ymm1, %ymm1
+; AVX512F-NEXT:    vpxor %xmm3, %xmm3, %xmm3
+; AVX512F-NEXT:    vpsadbw %ymm3, %ymm1, %ymm1
+; AVX512F-NEXT:    vpand %ymm2, %ymm0, %ymm5
+; AVX512F-NEXT:    vpshufb %ymm5, %ymm4, %ymm5
+; AVX512F-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX512F-NEXT:    vpand %ymm2, %ymm0, %ymm0
+; AVX512F-NEXT:    vpshufb %ymm0, %ymm4, %ymm0
+; AVX512F-NEXT:    vpaddb %ymm5, %ymm0, %ymm0
+; AVX512F-NEXT:    vpsadbw %ymm3, %ymm0, %ymm0
+; AVX512F-NEXT:    vinserti64x4 $1, %ymm1, %zmm0, %zmm0
+; AVX512F-NEXT:    vpcmpltuq {{.*}}(%rip){1to8}, %zmm0, %k1
+; AVX512F-NEXT:    vpternlogq $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
+; AVX512F-NEXT:    retq
+;
+; AVX512BW-LABEL: ult_2_v8i64:
+; AVX512BW:       # %bb.0:
+; AVX512BW-NEXT:    vmovdqa64 {{.*#+}} zmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512BW-NEXT:    vpandq %zmm1, %zmm0, %zmm2
+; AVX512BW-NEXT:    vmovdqa64 {{.*#+}} zmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512BW-NEXT:    vpshufb %zmm2, %zmm3, %zmm2
+; AVX512BW-NEXT:    vpsrlw $4, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpandq %zmm1, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpshufb %zmm0, %zmm3, %zmm0
+; AVX512BW-NEXT:    vpaddb %zmm2, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX512BW-NEXT:    vpsadbw %zmm1, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpcmpltuq {{.*}}(%rip){1to8}, %zmm0, %k1
+; AVX512BW-NEXT:    vpternlogq $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
+; AVX512BW-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: ult_2_v8i64:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    vpopcntq %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpcmpltuq {{.*}}(%rip){1to8}, %zmm0, %k1
+; AVX512VPOPCNTDQ-NEXT:    vpternlogq $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; BITALG-LABEL: ult_2_v8i64:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntb %zmm0, %zmm0
+; BITALG-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG-NEXT:    vpsadbw %zmm1, %zmm0, %zmm0
+; BITALG-NEXT:    vpcmpltuq {{.*}}(%rip){1to8}, %zmm0, %k1
+; BITALG-NEXT:    vpternlogq $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
+; BITALG-NEXT:    retq
+  %2 = tail call <8 x i64> @llvm.ctpop.v8i64(<8 x i64> %0)
+  %3 = icmp ult <8 x i64> %2, <i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2, i64 2>
+  %4 = sext <8 x i1> %3 to <8 x i64>
+  ret <8 x i64> %4
+}
+
+define <8 x i64> @ugt_1_v8i64(<8 x i64> %0) {
+; AVX512F-LABEL: ugt_1_v8i64:
+; AVX512F:       # %bb.0:
+; AVX512F-NEXT:    vextracti64x4 $1, %zmm0, %ymm1
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm2 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512F-NEXT:    vpand %ymm2, %ymm1, %ymm3
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm4 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512F-NEXT:    vpshufb %ymm3, %ymm4, %ymm3
+; AVX512F-NEXT:    vpsrlw $4, %ymm1, %ymm1
+; AVX512F-NEXT:    vpand %ymm2, %ymm1, %ymm1
+; AVX512F-NEXT:    vpshufb %ymm1, %ymm4, %ymm1
+; AVX512F-NEXT:    vpaddb %ymm3, %ymm1, %ymm1
+; AVX512F-NEXT:    vpxor %xmm3, %xmm3, %xmm3
+; AVX512F-NEXT:    vpsadbw %ymm3, %ymm1, %ymm1
+; AVX512F-NEXT:    vpand %ymm2, %ymm0, %ymm5
+; AVX512F-NEXT:    vpshufb %ymm5, %ymm4, %ymm5
+; AVX512F-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX512F-NEXT:    vpand %ymm2, %ymm0, %ymm0
+; AVX512F-NEXT:    vpshufb %ymm0, %ymm4, %ymm0
+; AVX512F-NEXT:    vpaddb %ymm5, %ymm0, %ymm0
+; AVX512F-NEXT:    vpsadbw %ymm3, %ymm0, %ymm0
+; AVX512F-NEXT:    vinserti64x4 $1, %ymm1, %zmm0, %zmm0
+; AVX512F-NEXT:    vpcmpnleuq {{.*}}(%rip){1to8}, %zmm0, %k1
+; AVX512F-NEXT:    vpternlogq $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
+; AVX512F-NEXT:    retq
+;
+; AVX512BW-LABEL: ugt_1_v8i64:
+; AVX512BW:       # %bb.0:
+; AVX512BW-NEXT:    vmovdqa64 {{.*#+}} zmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512BW-NEXT:    vpandq %zmm1, %zmm0, %zmm2
+; AVX512BW-NEXT:    vmovdqa64 {{.*#+}} zmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512BW-NEXT:    vpshufb %zmm2, %zmm3, %zmm2
+; AVX512BW-NEXT:    vpsrlw $4, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpandq %zmm1, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpshufb %zmm0, %zmm3, %zmm0
+; AVX512BW-NEXT:    vpaddb %zmm2, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX512BW-NEXT:    vpsadbw %zmm1, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpcmpnleuq {{.*}}(%rip){1to8}, %zmm0, %k1
+; AVX512BW-NEXT:    vpternlogq $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
+; AVX512BW-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: ugt_1_v8i64:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    vpopcntq %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpcmpnleuq {{.*}}(%rip){1to8}, %zmm0, %k1
+; AVX512VPOPCNTDQ-NEXT:    vpternlogq $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; BITALG-LABEL: ugt_1_v8i64:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntb %zmm0, %zmm0
+; BITALG-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG-NEXT:    vpsadbw %zmm1, %zmm0, %zmm0
+; BITALG-NEXT:    vpcmpnleuq {{.*}}(%rip){1to8}, %zmm0, %k1
+; BITALG-NEXT:    vpternlogq $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
+; BITALG-NEXT:    retq
+  %2 = tail call <8 x i64> @llvm.ctpop.v8i64(<8 x i64> %0)
+  %3 = icmp ugt <8 x i64> %2, <i64 1, i64 1, i64 1, i64 1, i64 1, i64 1, i64 1, i64 1>
+  %4 = sext <8 x i1> %3 to <8 x i64>
+  ret <8 x i64> %4
+}
+
+define <8 x i64> @eq_1_v8i64(<8 x i64> %0) {
+; AVX512F-LABEL: eq_1_v8i64:
+; AVX512F:       # %bb.0:
+; AVX512F-NEXT:    vextracti64x4 $1, %zmm0, %ymm1
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm2 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512F-NEXT:    vpand %ymm2, %ymm1, %ymm3
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm4 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512F-NEXT:    vpshufb %ymm3, %ymm4, %ymm3
+; AVX512F-NEXT:    vpsrlw $4, %ymm1, %ymm1
+; AVX512F-NEXT:    vpand %ymm2, %ymm1, %ymm1
+; AVX512F-NEXT:    vpshufb %ymm1, %ymm4, %ymm1
+; AVX512F-NEXT:    vpaddb %ymm3, %ymm1, %ymm1
+; AVX512F-NEXT:    vpxor %xmm3, %xmm3, %xmm3
+; AVX512F-NEXT:    vpsadbw %ymm3, %ymm1, %ymm1
+; AVX512F-NEXT:    vpand %ymm2, %ymm0, %ymm5
+; AVX512F-NEXT:    vpshufb %ymm5, %ymm4, %ymm5
+; AVX512F-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX512F-NEXT:    vpand %ymm2, %ymm0, %ymm0
+; AVX512F-NEXT:    vpshufb %ymm0, %ymm4, %ymm0
+; AVX512F-NEXT:    vpaddb %ymm5, %ymm0, %ymm0
+; AVX512F-NEXT:    vpsadbw %ymm3, %ymm0, %ymm0
+; AVX512F-NEXT:    vinserti64x4 $1, %ymm1, %zmm0, %zmm0
+; AVX512F-NEXT:    vpcmpeqq {{.*}}(%rip){1to8}, %zmm0, %k1
+; AVX512F-NEXT:    vpternlogq $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
+; AVX512F-NEXT:    retq
+;
+; AVX512BW-LABEL: eq_1_v8i64:
+; AVX512BW:       # %bb.0:
+; AVX512BW-NEXT:    vmovdqa64 {{.*#+}} zmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512BW-NEXT:    vpandq %zmm1, %zmm0, %zmm2
+; AVX512BW-NEXT:    vmovdqa64 {{.*#+}} zmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512BW-NEXT:    vpshufb %zmm2, %zmm3, %zmm2
+; AVX512BW-NEXT:    vpsrlw $4, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpandq %zmm1, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpshufb %zmm0, %zmm3, %zmm0
+; AVX512BW-NEXT:    vpaddb %zmm2, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX512BW-NEXT:    vpsadbw %zmm1, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpcmpeqq {{.*}}(%rip){1to8}, %zmm0, %k1
+; AVX512BW-NEXT:    vpternlogq $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
+; AVX512BW-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: eq_1_v8i64:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    vpopcntq %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpcmpeqq {{.*}}(%rip){1to8}, %zmm0, %k1
+; AVX512VPOPCNTDQ-NEXT:    vpternlogq $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; BITALG-LABEL: eq_1_v8i64:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntb %zmm0, %zmm0
+; BITALG-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG-NEXT:    vpsadbw %zmm1, %zmm0, %zmm0
+; BITALG-NEXT:    vpcmpeqq {{.*}}(%rip){1to8}, %zmm0, %k1
+; BITALG-NEXT:    vpternlogq $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
+; BITALG-NEXT:    retq
+  %2 = tail call <8 x i64> @llvm.ctpop.v8i64(<8 x i64> %0)
+  %3 = icmp eq <8 x i64> %2, <i64 1, i64 1, i64 1, i64 1, i64 1, i64 1, i64 1, i64 1>
+  %4 = sext <8 x i1> %3 to <8 x i64>
+  ret <8 x i64> %4
+}
+
+define <8 x i64> @ne_1_v8i64(<8 x i64> %0) {
+; AVX512F-LABEL: ne_1_v8i64:
+; AVX512F:       # %bb.0:
+; AVX512F-NEXT:    vextracti64x4 $1, %zmm0, %ymm1
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm2 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512F-NEXT:    vpand %ymm2, %ymm1, %ymm3
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm4 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512F-NEXT:    vpshufb %ymm3, %ymm4, %ymm3
+; AVX512F-NEXT:    vpsrlw $4, %ymm1, %ymm1
+; AVX512F-NEXT:    vpand %ymm2, %ymm1, %ymm1
+; AVX512F-NEXT:    vpshufb %ymm1, %ymm4, %ymm1
+; AVX512F-NEXT:    vpaddb %ymm3, %ymm1, %ymm1
+; AVX512F-NEXT:    vpxor %xmm3, %xmm3, %xmm3
+; AVX512F-NEXT:    vpsadbw %ymm3, %ymm1, %ymm1
+; AVX512F-NEXT:    vpand %ymm2, %ymm0, %ymm5
+; AVX512F-NEXT:    vpshufb %ymm5, %ymm4, %ymm5
+; AVX512F-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX512F-NEXT:    vpand %ymm2, %ymm0, %ymm0
+; AVX512F-NEXT:    vpshufb %ymm0, %ymm4, %ymm0
+; AVX512F-NEXT:    vpaddb %ymm5, %ymm0, %ymm0
+; AVX512F-NEXT:    vpsadbw %ymm3, %ymm0, %ymm0
+; AVX512F-NEXT:    vinserti64x4 $1, %ymm1, %zmm0, %zmm0
+; AVX512F-NEXT:    vpcmpneqq {{.*}}(%rip){1to8}, %zmm0, %k1
+; AVX512F-NEXT:    vpternlogq $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
+; AVX512F-NEXT:    retq
+;
+; AVX512BW-LABEL: ne_1_v8i64:
+; AVX512BW:       # %bb.0:
+; AVX512BW-NEXT:    vmovdqa64 {{.*#+}} zmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512BW-NEXT:    vpandq %zmm1, %zmm0, %zmm2
+; AVX512BW-NEXT:    vmovdqa64 {{.*#+}} zmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512BW-NEXT:    vpshufb %zmm2, %zmm3, %zmm2
+; AVX512BW-NEXT:    vpsrlw $4, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpandq %zmm1, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpshufb %zmm0, %zmm3, %zmm0
+; AVX512BW-NEXT:    vpaddb %zmm2, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX512BW-NEXT:    vpsadbw %zmm1, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpcmpneqq {{.*}}(%rip){1to8}, %zmm0, %k1
+; AVX512BW-NEXT:    vpternlogq $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
+; AVX512BW-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: ne_1_v8i64:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    vpopcntq %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpcmpneqq {{.*}}(%rip){1to8}, %zmm0, %k1
+; AVX512VPOPCNTDQ-NEXT:    vpternlogq $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; BITALG-LABEL: ne_1_v8i64:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntb %zmm0, %zmm0
+; BITALG-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG-NEXT:    vpsadbw %zmm1, %zmm0, %zmm0
+; BITALG-NEXT:    vpcmpneqq {{.*}}(%rip){1to8}, %zmm0, %k1
+; BITALG-NEXT:    vpternlogq $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
+; BITALG-NEXT:    retq
+  %2 = tail call <8 x i64> @llvm.ctpop.v8i64(<8 x i64> %0)
+  %3 = icmp ne <8 x i64> %2, <i64 1, i64 1, i64 1, i64 1, i64 1, i64 1, i64 1, i64 1>
+  %4 = sext <8 x i1> %3 to <8 x i64>
+  ret <8 x i64> %4
+}
+
+define <16 x i32> @ult_2_v16i32(<16 x i32> %0) {
+; AVX512F-LABEL: ult_2_v16i32:
+; AVX512F:       # %bb.0:
+; AVX512F-NEXT:    vextracti64x4 $1, %zmm0, %ymm1
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm2 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512F-NEXT:    vpand %ymm2, %ymm1, %ymm3
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm4 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512F-NEXT:    vpshufb %ymm3, %ymm4, %ymm3
+; AVX512F-NEXT:    vpsrlw $4, %ymm1, %ymm1
+; AVX512F-NEXT:    vpand %ymm2, %ymm1, %ymm1
+; AVX512F-NEXT:    vpshufb %ymm1, %ymm4, %ymm1
+; AVX512F-NEXT:    vpaddb %ymm3, %ymm1, %ymm1
+; AVX512F-NEXT:    vpxor %xmm3, %xmm3, %xmm3
+; AVX512F-NEXT:    vpunpckhdq {{.*#+}} ymm5 = ymm1[2],ymm3[2],ymm1[3],ymm3[3],ymm1[6],ymm3[6],ymm1[7],ymm3[7]
+; AVX512F-NEXT:    vpsadbw %ymm3, %ymm5, %ymm5
+; AVX512F-NEXT:    vpunpckldq {{.*#+}} ymm1 = ymm1[0],ymm3[0],ymm1[1],ymm3[1],ymm1[4],ymm3[4],ymm1[5],ymm3[5]
+; AVX512F-NEXT:    vpsadbw %ymm3, %ymm1, %ymm1
+; AVX512F-NEXT:    vpackuswb %ymm5, %ymm1, %ymm1
+; AVX512F-NEXT:    vpand %ymm2, %ymm0, %ymm5
+; AVX512F-NEXT:    vpshufb %ymm5, %ymm4, %ymm5
+; AVX512F-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX512F-NEXT:    vpand %ymm2, %ymm0, %ymm0
+; AVX512F-NEXT:    vpshufb %ymm0, %ymm4, %ymm0
+; AVX512F-NEXT:    vpaddb %ymm5, %ymm0, %ymm0
+; AVX512F-NEXT:    vpunpckhdq {{.*#+}} ymm2 = ymm0[2],ymm3[2],ymm0[3],ymm3[3],ymm0[6],ymm3[6],ymm0[7],ymm3[7]
+; AVX512F-NEXT:    vpsadbw %ymm3, %ymm2, %ymm2
+; AVX512F-NEXT:    vpunpckldq {{.*#+}} ymm0 = ymm0[0],ymm3[0],ymm0[1],ymm3[1],ymm0[4],ymm3[4],ymm0[5],ymm3[5]
+; AVX512F-NEXT:    vpsadbw %ymm3, %ymm0, %ymm0
+; AVX512F-NEXT:    vpackuswb %ymm2, %ymm0, %ymm0
+; AVX512F-NEXT:    vinserti64x4 $1, %ymm1, %zmm0, %zmm0
+; AVX512F-NEXT:    vpcmpltud {{.*}}(%rip){1to16}, %zmm0, %k1
+; AVX512F-NEXT:    vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
+; AVX512F-NEXT:    retq
+;
+; AVX512BW-LABEL: ult_2_v16i32:
+; AVX512BW:       # %bb.0:
+; AVX512BW-NEXT:    vmovdqa64 {{.*#+}} zmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512BW-NEXT:    vpandq %zmm1, %zmm0, %zmm2
+; AVX512BW-NEXT:    vmovdqa64 {{.*#+}} zmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512BW-NEXT:    vpshufb %zmm2, %zmm3, %zmm2
+; AVX512BW-NEXT:    vpsrlw $4, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpandq %zmm1, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpshufb %zmm0, %zmm3, %zmm0
+; AVX512BW-NEXT:    vpaddb %zmm2, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX512BW-NEXT:    vpunpckhdq {{.*#+}} zmm2 = zmm0[2],zmm1[2],zmm0[3],zmm1[3],zmm0[6],zmm1[6],zmm0[7],zmm1[7],zmm0[10],zmm1[10],zmm0[11],zmm1[11],zmm0[14],zmm1[14],zmm0[15],zmm1[15]
+; AVX512BW-NEXT:    vpsadbw %zmm1, %zmm2, %zmm2
+; AVX512BW-NEXT:    vpunpckldq {{.*#+}} zmm0 = zmm0[0],zmm1[0],zmm0[1],zmm1[1],zmm0[4],zmm1[4],zmm0[5],zmm1[5],zmm0[8],zmm1[8],zmm0[9],zmm1[9],zmm0[12],zmm1[12],zmm0[13],zmm1[13]
+; AVX512BW-NEXT:    vpsadbw %zmm1, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpackuswb %zmm2, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpcmpltud {{.*}}(%rip){1to16}, %zmm0, %k1
+; AVX512BW-NEXT:    vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
+; AVX512BW-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: ult_2_v16i32:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    vpopcntd %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpcmpltud {{.*}}(%rip){1to16}, %zmm0, %k1
+; AVX512VPOPCNTDQ-NEXT:    vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; BITALG-LABEL: ult_2_v16i32:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntb %zmm0, %zmm0
+; BITALG-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG-NEXT:    vpunpckhdq {{.*#+}} zmm2 = zmm0[2],zmm1[2],zmm0[3],zmm1[3],zmm0[6],zmm1[6],zmm0[7],zmm1[7],zmm0[10],zmm1[10],zmm0[11],zmm1[11],zmm0[14],zmm1[14],zmm0[15],zmm1[15]
+; BITALG-NEXT:    vpsadbw %zmm1, %zmm2, %zmm2
+; BITALG-NEXT:    vpunpckldq {{.*#+}} zmm0 = zmm0[0],zmm1[0],zmm0[1],zmm1[1],zmm0[4],zmm1[4],zmm0[5],zmm1[5],zmm0[8],zmm1[8],zmm0[9],zmm1[9],zmm0[12],zmm1[12],zmm0[13],zmm1[13]
+; BITALG-NEXT:    vpsadbw %zmm1, %zmm0, %zmm0
+; BITALG-NEXT:    vpackuswb %zmm2, %zmm0, %zmm0
+; BITALG-NEXT:    vpcmpltud {{.*}}(%rip){1to16}, %zmm0, %k1
+; BITALG-NEXT:    vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
+; BITALG-NEXT:    retq
+  %2 = tail call <16 x i32> @llvm.ctpop.v16i32(<16 x i32> %0)
+  %3 = icmp ult <16 x i32> %2, <i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2>
+  %4 = sext <16 x i1> %3 to <16 x i32>
+  ret <16 x i32> %4
+}
+
+define <16 x i32> @ugt_1_v16i32(<16 x i32> %0) {
+; AVX512F-LABEL: ugt_1_v16i32:
+; AVX512F:       # %bb.0:
+; AVX512F-NEXT:    vextracti64x4 $1, %zmm0, %ymm1
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm2 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512F-NEXT:    vpand %ymm2, %ymm1, %ymm3
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm4 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512F-NEXT:    vpshufb %ymm3, %ymm4, %ymm3
+; AVX512F-NEXT:    vpsrlw $4, %ymm1, %ymm1
+; AVX512F-NEXT:    vpand %ymm2, %ymm1, %ymm1
+; AVX512F-NEXT:    vpshufb %ymm1, %ymm4, %ymm1
+; AVX512F-NEXT:    vpaddb %ymm3, %ymm1, %ymm1
+; AVX512F-NEXT:    vpxor %xmm3, %xmm3, %xmm3
+; AVX512F-NEXT:    vpunpckhdq {{.*#+}} ymm5 = ymm1[2],ymm3[2],ymm1[3],ymm3[3],ymm1[6],ymm3[6],ymm1[7],ymm3[7]
+; AVX512F-NEXT:    vpsadbw %ymm3, %ymm5, %ymm5
+; AVX512F-NEXT:    vpunpckldq {{.*#+}} ymm1 = ymm1[0],ymm3[0],ymm1[1],ymm3[1],ymm1[4],ymm3[4],ymm1[5],ymm3[5]
+; AVX512F-NEXT:    vpsadbw %ymm3, %ymm1, %ymm1
+; AVX512F-NEXT:    vpackuswb %ymm5, %ymm1, %ymm1
+; AVX512F-NEXT:    vpand %ymm2, %ymm0, %ymm5
+; AVX512F-NEXT:    vpshufb %ymm5, %ymm4, %ymm5
+; AVX512F-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX512F-NEXT:    vpand %ymm2, %ymm0, %ymm0
+; AVX512F-NEXT:    vpshufb %ymm0, %ymm4, %ymm0
+; AVX512F-NEXT:    vpaddb %ymm5, %ymm0, %ymm0
+; AVX512F-NEXT:    vpunpckhdq {{.*#+}} ymm2 = ymm0[2],ymm3[2],ymm0[3],ymm3[3],ymm0[6],ymm3[6],ymm0[7],ymm3[7]
+; AVX512F-NEXT:    vpsadbw %ymm3, %ymm2, %ymm2
+; AVX512F-NEXT:    vpunpckldq {{.*#+}} ymm0 = ymm0[0],ymm3[0],ymm0[1],ymm3[1],ymm0[4],ymm3[4],ymm0[5],ymm3[5]
+; AVX512F-NEXT:    vpsadbw %ymm3, %ymm0, %ymm0
+; AVX512F-NEXT:    vpackuswb %ymm2, %ymm0, %ymm0
+; AVX512F-NEXT:    vinserti64x4 $1, %ymm1, %zmm0, %zmm0
+; AVX512F-NEXT:    vpcmpnleud {{.*}}(%rip){1to16}, %zmm0, %k1
+; AVX512F-NEXT:    vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
+; AVX512F-NEXT:    retq
+;
+; AVX512BW-LABEL: ugt_1_v16i32:
+; AVX512BW:       # %bb.0:
+; AVX512BW-NEXT:    vmovdqa64 {{.*#+}} zmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512BW-NEXT:    vpandq %zmm1, %zmm0, %zmm2
+; AVX512BW-NEXT:    vmovdqa64 {{.*#+}} zmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512BW-NEXT:    vpshufb %zmm2, %zmm3, %zmm2
+; AVX512BW-NEXT:    vpsrlw $4, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpandq %zmm1, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpshufb %zmm0, %zmm3, %zmm0
+; AVX512BW-NEXT:    vpaddb %zmm2, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX512BW-NEXT:    vpunpckhdq {{.*#+}} zmm2 = zmm0[2],zmm1[2],zmm0[3],zmm1[3],zmm0[6],zmm1[6],zmm0[7],zmm1[7],zmm0[10],zmm1[10],zmm0[11],zmm1[11],zmm0[14],zmm1[14],zmm0[15],zmm1[15]
+; AVX512BW-NEXT:    vpsadbw %zmm1, %zmm2, %zmm2
+; AVX512BW-NEXT:    vpunpckldq {{.*#+}} zmm0 = zmm0[0],zmm1[0],zmm0[1],zmm1[1],zmm0[4],zmm1[4],zmm0[5],zmm1[5],zmm0[8],zmm1[8],zmm0[9],zmm1[9],zmm0[12],zmm1[12],zmm0[13],zmm1[13]
+; AVX512BW-NEXT:    vpsadbw %zmm1, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpackuswb %zmm2, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpcmpnleud {{.*}}(%rip){1to16}, %zmm0, %k1
+; AVX512BW-NEXT:    vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
+; AVX512BW-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: ugt_1_v16i32:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    vpopcntd %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpcmpnleud {{.*}}(%rip){1to16}, %zmm0, %k1
+; AVX512VPOPCNTDQ-NEXT:    vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; BITALG-LABEL: ugt_1_v16i32:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntb %zmm0, %zmm0
+; BITALG-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG-NEXT:    vpunpckhdq {{.*#+}} zmm2 = zmm0[2],zmm1[2],zmm0[3],zmm1[3],zmm0[6],zmm1[6],zmm0[7],zmm1[7],zmm0[10],zmm1[10],zmm0[11],zmm1[11],zmm0[14],zmm1[14],zmm0[15],zmm1[15]
+; BITALG-NEXT:    vpsadbw %zmm1, %zmm2, %zmm2
+; BITALG-NEXT:    vpunpckldq {{.*#+}} zmm0 = zmm0[0],zmm1[0],zmm0[1],zmm1[1],zmm0[4],zmm1[4],zmm0[5],zmm1[5],zmm0[8],zmm1[8],zmm0[9],zmm1[9],zmm0[12],zmm1[12],zmm0[13],zmm1[13]
+; BITALG-NEXT:    vpsadbw %zmm1, %zmm0, %zmm0
+; BITALG-NEXT:    vpackuswb %zmm2, %zmm0, %zmm0
+; BITALG-NEXT:    vpcmpnleud {{.*}}(%rip){1to16}, %zmm0, %k1
+; BITALG-NEXT:    vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
+; BITALG-NEXT:    retq
+  %2 = tail call <16 x i32> @llvm.ctpop.v16i32(<16 x i32> %0)
+  %3 = icmp ugt <16 x i32> %2, <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
+  %4 = sext <16 x i1> %3 to <16 x i32>
+  ret <16 x i32> %4
+}
+
+define <16 x i32> @eq_1_v16i32(<16 x i32> %0) {
+; AVX512F-LABEL: eq_1_v16i32:
+; AVX512F:       # %bb.0:
+; AVX512F-NEXT:    vextracti64x4 $1, %zmm0, %ymm1
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm2 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512F-NEXT:    vpand %ymm2, %ymm1, %ymm3
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm4 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512F-NEXT:    vpshufb %ymm3, %ymm4, %ymm3
+; AVX512F-NEXT:    vpsrlw $4, %ymm1, %ymm1
+; AVX512F-NEXT:    vpand %ymm2, %ymm1, %ymm1
+; AVX512F-NEXT:    vpshufb %ymm1, %ymm4, %ymm1
+; AVX512F-NEXT:    vpaddb %ymm3, %ymm1, %ymm1
+; AVX512F-NEXT:    vpxor %xmm3, %xmm3, %xmm3
+; AVX512F-NEXT:    vpunpckhdq {{.*#+}} ymm5 = ymm1[2],ymm3[2],ymm1[3],ymm3[3],ymm1[6],ymm3[6],ymm1[7],ymm3[7]
+; AVX512F-NEXT:    vpsadbw %ymm3, %ymm5, %ymm5
+; AVX512F-NEXT:    vpunpckldq {{.*#+}} ymm1 = ymm1[0],ymm3[0],ymm1[1],ymm3[1],ymm1[4],ymm3[4],ymm1[5],ymm3[5]
+; AVX512F-NEXT:    vpsadbw %ymm3, %ymm1, %ymm1
+; AVX512F-NEXT:    vpackuswb %ymm5, %ymm1, %ymm1
+; AVX512F-NEXT:    vpand %ymm2, %ymm0, %ymm5
+; AVX512F-NEXT:    vpshufb %ymm5, %ymm4, %ymm5
+; AVX512F-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX512F-NEXT:    vpand %ymm2, %ymm0, %ymm0
+; AVX512F-NEXT:    vpshufb %ymm0, %ymm4, %ymm0
+; AVX512F-NEXT:    vpaddb %ymm5, %ymm0, %ymm0
+; AVX512F-NEXT:    vpunpckhdq {{.*#+}} ymm2 = ymm0[2],ymm3[2],ymm0[3],ymm3[3],ymm0[6],ymm3[6],ymm0[7],ymm3[7]
+; AVX512F-NEXT:    vpsadbw %ymm3, %ymm2, %ymm2
+; AVX512F-NEXT:    vpunpckldq {{.*#+}} ymm0 = ymm0[0],ymm3[0],ymm0[1],ymm3[1],ymm0[4],ymm3[4],ymm0[5],ymm3[5]
+; AVX512F-NEXT:    vpsadbw %ymm3, %ymm0, %ymm0
+; AVX512F-NEXT:    vpackuswb %ymm2, %ymm0, %ymm0
+; AVX512F-NEXT:    vinserti64x4 $1, %ymm1, %zmm0, %zmm0
+; AVX512F-NEXT:    vpcmpeqd {{.*}}(%rip){1to16}, %zmm0, %k1
+; AVX512F-NEXT:    vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
+; AVX512F-NEXT:    retq
+;
+; AVX512BW-LABEL: eq_1_v16i32:
+; AVX512BW:       # %bb.0:
+; AVX512BW-NEXT:    vmovdqa64 {{.*#+}} zmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512BW-NEXT:    vpandq %zmm1, %zmm0, %zmm2
+; AVX512BW-NEXT:    vmovdqa64 {{.*#+}} zmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512BW-NEXT:    vpshufb %zmm2, %zmm3, %zmm2
+; AVX512BW-NEXT:    vpsrlw $4, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpandq %zmm1, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpshufb %zmm0, %zmm3, %zmm0
+; AVX512BW-NEXT:    vpaddb %zmm2, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX512BW-NEXT:    vpunpckhdq {{.*#+}} zmm2 = zmm0[2],zmm1[2],zmm0[3],zmm1[3],zmm0[6],zmm1[6],zmm0[7],zmm1[7],zmm0[10],zmm1[10],zmm0[11],zmm1[11],zmm0[14],zmm1[14],zmm0[15],zmm1[15]
+; AVX512BW-NEXT:    vpsadbw %zmm1, %zmm2, %zmm2
+; AVX512BW-NEXT:    vpunpckldq {{.*#+}} zmm0 = zmm0[0],zmm1[0],zmm0[1],zmm1[1],zmm0[4],zmm1[4],zmm0[5],zmm1[5],zmm0[8],zmm1[8],zmm0[9],zmm1[9],zmm0[12],zmm1[12],zmm0[13],zmm1[13]
+; AVX512BW-NEXT:    vpsadbw %zmm1, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpackuswb %zmm2, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpcmpeqd {{.*}}(%rip){1to16}, %zmm0, %k1
+; AVX512BW-NEXT:    vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
+; AVX512BW-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: eq_1_v16i32:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    vpopcntd %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpcmpeqd {{.*}}(%rip){1to16}, %zmm0, %k1
+; AVX512VPOPCNTDQ-NEXT:    vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; BITALG-LABEL: eq_1_v16i32:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntb %zmm0, %zmm0
+; BITALG-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG-NEXT:    vpunpckhdq {{.*#+}} zmm2 = zmm0[2],zmm1[2],zmm0[3],zmm1[3],zmm0[6],zmm1[6],zmm0[7],zmm1[7],zmm0[10],zmm1[10],zmm0[11],zmm1[11],zmm0[14],zmm1[14],zmm0[15],zmm1[15]
+; BITALG-NEXT:    vpsadbw %zmm1, %zmm2, %zmm2
+; BITALG-NEXT:    vpunpckldq {{.*#+}} zmm0 = zmm0[0],zmm1[0],zmm0[1],zmm1[1],zmm0[4],zmm1[4],zmm0[5],zmm1[5],zmm0[8],zmm1[8],zmm0[9],zmm1[9],zmm0[12],zmm1[12],zmm0[13],zmm1[13]
+; BITALG-NEXT:    vpsadbw %zmm1, %zmm0, %zmm0
+; BITALG-NEXT:    vpackuswb %zmm2, %zmm0, %zmm0
+; BITALG-NEXT:    vpcmpeqd {{.*}}(%rip){1to16}, %zmm0, %k1
+; BITALG-NEXT:    vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
+; BITALG-NEXT:    retq
+  %2 = tail call <16 x i32> @llvm.ctpop.v16i32(<16 x i32> %0)
+  %3 = icmp eq <16 x i32> %2, <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
+  %4 = sext <16 x i1> %3 to <16 x i32>
+  ret <16 x i32> %4
+}
+
+define <16 x i32> @ne_1_v16i32(<16 x i32> %0) {
+; AVX512F-LABEL: ne_1_v16i32:
+; AVX512F:       # %bb.0:
+; AVX512F-NEXT:    vextracti64x4 $1, %zmm0, %ymm1
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm2 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512F-NEXT:    vpand %ymm2, %ymm1, %ymm3
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm4 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512F-NEXT:    vpshufb %ymm3, %ymm4, %ymm3
+; AVX512F-NEXT:    vpsrlw $4, %ymm1, %ymm1
+; AVX512F-NEXT:    vpand %ymm2, %ymm1, %ymm1
+; AVX512F-NEXT:    vpshufb %ymm1, %ymm4, %ymm1
+; AVX512F-NEXT:    vpaddb %ymm3, %ymm1, %ymm1
+; AVX512F-NEXT:    vpxor %xmm3, %xmm3, %xmm3
+; AVX512F-NEXT:    vpunpckhdq {{.*#+}} ymm5 = ymm1[2],ymm3[2],ymm1[3],ymm3[3],ymm1[6],ymm3[6],ymm1[7],ymm3[7]
+; AVX512F-NEXT:    vpsadbw %ymm3, %ymm5, %ymm5
+; AVX512F-NEXT:    vpunpckldq {{.*#+}} ymm1 = ymm1[0],ymm3[0],ymm1[1],ymm3[1],ymm1[4],ymm3[4],ymm1[5],ymm3[5]
+; AVX512F-NEXT:    vpsadbw %ymm3, %ymm1, %ymm1
+; AVX512F-NEXT:    vpackuswb %ymm5, %ymm1, %ymm1
+; AVX512F-NEXT:    vpand %ymm2, %ymm0, %ymm5
+; AVX512F-NEXT:    vpshufb %ymm5, %ymm4, %ymm5
+; AVX512F-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX512F-NEXT:    vpand %ymm2, %ymm0, %ymm0
+; AVX512F-NEXT:    vpshufb %ymm0, %ymm4, %ymm0
+; AVX512F-NEXT:    vpaddb %ymm5, %ymm0, %ymm0
+; AVX512F-NEXT:    vpunpckhdq {{.*#+}} ymm2 = ymm0[2],ymm3[2],ymm0[3],ymm3[3],ymm0[6],ymm3[6],ymm0[7],ymm3[7]
+; AVX512F-NEXT:    vpsadbw %ymm3, %ymm2, %ymm2
+; AVX512F-NEXT:    vpunpckldq {{.*#+}} ymm0 = ymm0[0],ymm3[0],ymm0[1],ymm3[1],ymm0[4],ymm3[4],ymm0[5],ymm3[5]
+; AVX512F-NEXT:    vpsadbw %ymm3, %ymm0, %ymm0
+; AVX512F-NEXT:    vpackuswb %ymm2, %ymm0, %ymm0
+; AVX512F-NEXT:    vinserti64x4 $1, %ymm1, %zmm0, %zmm0
+; AVX512F-NEXT:    vpcmpneqd {{.*}}(%rip){1to16}, %zmm0, %k1
+; AVX512F-NEXT:    vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
+; AVX512F-NEXT:    retq
+;
+; AVX512BW-LABEL: ne_1_v16i32:
+; AVX512BW:       # %bb.0:
+; AVX512BW-NEXT:    vmovdqa64 {{.*#+}} zmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512BW-NEXT:    vpandq %zmm1, %zmm0, %zmm2
+; AVX512BW-NEXT:    vmovdqa64 {{.*#+}} zmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512BW-NEXT:    vpshufb %zmm2, %zmm3, %zmm2
+; AVX512BW-NEXT:    vpsrlw $4, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpandq %zmm1, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpshufb %zmm0, %zmm3, %zmm0
+; AVX512BW-NEXT:    vpaddb %zmm2, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX512BW-NEXT:    vpunpckhdq {{.*#+}} zmm2 = zmm0[2],zmm1[2],zmm0[3],zmm1[3],zmm0[6],zmm1[6],zmm0[7],zmm1[7],zmm0[10],zmm1[10],zmm0[11],zmm1[11],zmm0[14],zmm1[14],zmm0[15],zmm1[15]
+; AVX512BW-NEXT:    vpsadbw %zmm1, %zmm2, %zmm2
+; AVX512BW-NEXT:    vpunpckldq {{.*#+}} zmm0 = zmm0[0],zmm1[0],zmm0[1],zmm1[1],zmm0[4],zmm1[4],zmm0[5],zmm1[5],zmm0[8],zmm1[8],zmm0[9],zmm1[9],zmm0[12],zmm1[12],zmm0[13],zmm1[13]
+; AVX512BW-NEXT:    vpsadbw %zmm1, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpackuswb %zmm2, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpcmpneqd {{.*}}(%rip){1to16}, %zmm0, %k1
+; AVX512BW-NEXT:    vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
+; AVX512BW-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-LABEL: ne_1_v16i32:
+; AVX512VPOPCNTDQ:       # %bb.0:
+; AVX512VPOPCNTDQ-NEXT:    vpopcntd %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NEXT:    vpcmpneqd {{.*}}(%rip){1to16}, %zmm0, %k1
+; AVX512VPOPCNTDQ-NEXT:    vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
+; AVX512VPOPCNTDQ-NEXT:    retq
+;
+; BITALG-LABEL: ne_1_v16i32:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntb %zmm0, %zmm0
+; BITALG-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; BITALG-NEXT:    vpunpckhdq {{.*#+}} zmm2 = zmm0[2],zmm1[2],zmm0[3],zmm1[3],zmm0[6],zmm1[6],zmm0[7],zmm1[7],zmm0[10],zmm1[10],zmm0[11],zmm1[11],zmm0[14],zmm1[14],zmm0[15],zmm1[15]
+; BITALG-NEXT:    vpsadbw %zmm1, %zmm2, %zmm2
+; BITALG-NEXT:    vpunpckldq {{.*#+}} zmm0 = zmm0[0],zmm1[0],zmm0[1],zmm1[1],zmm0[4],zmm1[4],zmm0[5],zmm1[5],zmm0[8],zmm1[8],zmm0[9],zmm1[9],zmm0[12],zmm1[12],zmm0[13],zmm1[13]
+; BITALG-NEXT:    vpsadbw %zmm1, %zmm0, %zmm0
+; BITALG-NEXT:    vpackuswb %zmm2, %zmm0, %zmm0
+; BITALG-NEXT:    vpcmpneqd {{.*}}(%rip){1to16}, %zmm0, %k1
+; BITALG-NEXT:    vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
+; BITALG-NEXT:    retq
+  %2 = tail call <16 x i32> @llvm.ctpop.v16i32(<16 x i32> %0)
+  %3 = icmp ne <16 x i32> %2, <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
+  %4 = sext <16 x i1> %3 to <16 x i32>
+  ret <16 x i32> %4
+}
+
+define <32 x i16> @ult_2_v32i16(<32 x i16> %0) {
+; AVX512F-LABEL: ult_2_v32i16:
+; AVX512F:       # %bb.0:
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512F-NEXT:    vpand %ymm1, %ymm0, %ymm2
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512F-NEXT:    vpshufb %ymm2, %ymm3, %ymm2
+; AVX512F-NEXT:    vpsrlw $4, %ymm0, %ymm4
+; AVX512F-NEXT:    vpand %ymm1, %ymm4, %ymm4
+; AVX512F-NEXT:    vpshufb %ymm4, %ymm3, %ymm4
+; AVX512F-NEXT:    vpaddb %ymm2, %ymm4, %ymm2
+; AVX512F-NEXT:    vpsllw $8, %ymm2, %ymm4
+; AVX512F-NEXT:    vpaddb %ymm2, %ymm4, %ymm2
+; AVX512F-NEXT:    vpsrlw $8, %ymm2, %ymm2
+; AVX512F-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
+; AVX512F-NEXT:    vpand %ymm1, %ymm0, %ymm4
+; AVX512F-NEXT:    vpshufb %ymm4, %ymm3, %ymm4
+; AVX512F-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX512F-NEXT:    vpand %ymm1, %ymm0, %ymm0
+; AVX512F-NEXT:    vpshufb %ymm0, %ymm3, %ymm0
+; AVX512F-NEXT:    vpaddb %ymm4, %ymm0, %ymm0
+; AVX512F-NEXT:    vpsllw $8, %ymm0, %ymm1
+; AVX512F-NEXT:    vpaddb %ymm0, %ymm1, %ymm0
+; AVX512F-NEXT:    vpsrlw $8, %ymm0, %ymm0
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm1 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2]
+; AVX512F-NEXT:    vpcmpgtw %ymm0, %ymm1, %ymm0
+; AVX512F-NEXT:    vpcmpgtw %ymm2, %ymm1, %ymm1
+; AVX512F-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
+; AVX512F-NEXT:    retq
+;
+; AVX512BW-LABEL: ult_2_v32i16:
+; AVX512BW:       # %bb.0:
+; AVX512BW-NEXT:    vmovdqa64 {{.*#+}} zmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512BW-NEXT:    vpandq %zmm1, %zmm0, %zmm2
+; AVX512BW-NEXT:    vmovdqa64 {{.*#+}} zmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512BW-NEXT:    vpshufb %zmm2, %zmm3, %zmm2
+; AVX512BW-NEXT:    vpsrlw $4, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpandq %zmm1, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpshufb %zmm0, %zmm3, %zmm0
+; AVX512BW-NEXT:    vpaddb %zmm2, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpsllw $8, %zmm0, %zmm1
+; AVX512BW-NEXT:    vpaddb %zmm0, %zmm1, %zmm0
+; AVX512BW-NEXT:    vpsrlw $8, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpcmpltuw {{.*}}(%rip), %zmm0, %k0
+; AVX512BW-NEXT:    vpmovm2w %k0, %zmm0
+; AVX512BW-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-NOBW-LABEL: ult_2_v32i16:
+; AVX512VPOPCNTDQ-NOBW:       # %bb.0:
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpmovzxwd {{.*#+}} zmm1 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpopcntd %zmm1, %zmm1
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpmovdw %zmm1, %ymm1
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpopcntd %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpmovdw %zmm0, %ymm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vmovdqa {{.*#+}} ymm2 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2]
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpcmpgtw %ymm0, %ymm2, %ymm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpcmpgtw %ymm1, %ymm2, %ymm1
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-BW-LABEL: ult_2_v32i16:
+; AVX512VPOPCNTDQ-BW:       # %bb.0:
+; AVX512VPOPCNTDQ-BW-NEXT:    vmovdqa64 {{.*#+}} zmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512VPOPCNTDQ-BW-NEXT:    vpandq %zmm1, %zmm0, %zmm2
+; AVX512VPOPCNTDQ-BW-NEXT:    vmovdqa64 {{.*#+}} zmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512VPOPCNTDQ-BW-NEXT:    vpshufb %zmm2, %zmm3, %zmm2
+; AVX512VPOPCNTDQ-BW-NEXT:    vpsrlw $4, %zmm0, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpandq %zmm1, %zmm0, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpshufb %zmm0, %zmm3, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpaddb %zmm2, %zmm0, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpsllw $8, %zmm0, %zmm1
+; AVX512VPOPCNTDQ-BW-NEXT:    vpaddb %zmm0, %zmm1, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpsrlw $8, %zmm0, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpcmpltuw {{.*}}(%rip), %zmm0, %k0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpmovm2w %k0, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    retq
+;
+; BITALG-LABEL: ult_2_v32i16:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntw %zmm0, %zmm0
+; BITALG-NEXT:    vpcmpltuw {{.*}}(%rip), %zmm0, %k0
+; BITALG-NEXT:    vpmovm2w %k0, %zmm0
+; BITALG-NEXT:    retq
+  %2 = tail call <32 x i16> @llvm.ctpop.v32i16(<32 x i16> %0)
+  %3 = icmp ult <32 x i16> %2, <i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2, i16 2>
+  %4 = sext <32 x i1> %3 to <32 x i16>
+  ret <32 x i16> %4
+}
+
+define <32 x i16> @ugt_1_v32i16(<32 x i16> %0) {
+; AVX512F-LABEL: ugt_1_v32i16:
+; AVX512F:       # %bb.0:
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512F-NEXT:    vpand %ymm1, %ymm0, %ymm2
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512F-NEXT:    vpshufb %ymm2, %ymm3, %ymm2
+; AVX512F-NEXT:    vpsrlw $4, %ymm0, %ymm4
+; AVX512F-NEXT:    vpand %ymm1, %ymm4, %ymm4
+; AVX512F-NEXT:    vpshufb %ymm4, %ymm3, %ymm4
+; AVX512F-NEXT:    vpaddb %ymm2, %ymm4, %ymm2
+; AVX512F-NEXT:    vpsllw $8, %ymm2, %ymm4
+; AVX512F-NEXT:    vpaddb %ymm2, %ymm4, %ymm2
+; AVX512F-NEXT:    vpsrlw $8, %ymm2, %ymm2
+; AVX512F-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
+; AVX512F-NEXT:    vpand %ymm1, %ymm0, %ymm4
+; AVX512F-NEXT:    vpshufb %ymm4, %ymm3, %ymm4
+; AVX512F-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX512F-NEXT:    vpand %ymm1, %ymm0, %ymm0
+; AVX512F-NEXT:    vpshufb %ymm0, %ymm3, %ymm0
+; AVX512F-NEXT:    vpaddb %ymm4, %ymm0, %ymm0
+; AVX512F-NEXT:    vpsllw $8, %ymm0, %ymm1
+; AVX512F-NEXT:    vpaddb %ymm0, %ymm1, %ymm0
+; AVX512F-NEXT:    vpsrlw $8, %ymm0, %ymm0
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm1 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1]
+; AVX512F-NEXT:    vpcmpgtw %ymm1, %ymm0, %ymm0
+; AVX512F-NEXT:    vpcmpgtw %ymm1, %ymm2, %ymm1
+; AVX512F-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
+; AVX512F-NEXT:    retq
+;
+; AVX512BW-LABEL: ugt_1_v32i16:
+; AVX512BW:       # %bb.0:
+; AVX512BW-NEXT:    vmovdqa64 {{.*#+}} zmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512BW-NEXT:    vpandq %zmm1, %zmm0, %zmm2
+; AVX512BW-NEXT:    vmovdqa64 {{.*#+}} zmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512BW-NEXT:    vpshufb %zmm2, %zmm3, %zmm2
+; AVX512BW-NEXT:    vpsrlw $4, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpandq %zmm1, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpshufb %zmm0, %zmm3, %zmm0
+; AVX512BW-NEXT:    vpaddb %zmm2, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpsllw $8, %zmm0, %zmm1
+; AVX512BW-NEXT:    vpaddb %zmm0, %zmm1, %zmm0
+; AVX512BW-NEXT:    vpsrlw $8, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpcmpnleuw {{.*}}(%rip), %zmm0, %k0
+; AVX512BW-NEXT:    vpmovm2w %k0, %zmm0
+; AVX512BW-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-NOBW-LABEL: ugt_1_v32i16:
+; AVX512VPOPCNTDQ-NOBW:       # %bb.0:
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpmovzxwd {{.*#+}} zmm1 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpopcntd %zmm1, %zmm1
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpmovdw %zmm1, %ymm1
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpopcntd %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpmovdw %zmm0, %ymm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vmovdqa {{.*#+}} ymm2 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1]
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpcmpgtw %ymm2, %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpcmpgtw %ymm2, %ymm1, %ymm1
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-BW-LABEL: ugt_1_v32i16:
+; AVX512VPOPCNTDQ-BW:       # %bb.0:
+; AVX512VPOPCNTDQ-BW-NEXT:    vmovdqa64 {{.*#+}} zmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512VPOPCNTDQ-BW-NEXT:    vpandq %zmm1, %zmm0, %zmm2
+; AVX512VPOPCNTDQ-BW-NEXT:    vmovdqa64 {{.*#+}} zmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512VPOPCNTDQ-BW-NEXT:    vpshufb %zmm2, %zmm3, %zmm2
+; AVX512VPOPCNTDQ-BW-NEXT:    vpsrlw $4, %zmm0, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpandq %zmm1, %zmm0, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpshufb %zmm0, %zmm3, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpaddb %zmm2, %zmm0, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpsllw $8, %zmm0, %zmm1
+; AVX512VPOPCNTDQ-BW-NEXT:    vpaddb %zmm0, %zmm1, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpsrlw $8, %zmm0, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpcmpnleuw {{.*}}(%rip), %zmm0, %k0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpmovm2w %k0, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    retq
+;
+; BITALG-LABEL: ugt_1_v32i16:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntw %zmm0, %zmm0
+; BITALG-NEXT:    vpcmpnleuw {{.*}}(%rip), %zmm0, %k0
+; BITALG-NEXT:    vpmovm2w %k0, %zmm0
+; BITALG-NEXT:    retq
+  %2 = tail call <32 x i16> @llvm.ctpop.v32i16(<32 x i16> %0)
+  %3 = icmp ugt <32 x i16> %2, <i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1>
+  %4 = sext <32 x i1> %3 to <32 x i16>
+  ret <32 x i16> %4
+}
+
+define <32 x i16> @eq_1_v32i16(<32 x i16> %0) {
+; AVX512F-LABEL: eq_1_v32i16:
+; AVX512F:       # %bb.0:
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512F-NEXT:    vpand %ymm1, %ymm0, %ymm2
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512F-NEXT:    vpshufb %ymm2, %ymm3, %ymm2
+; AVX512F-NEXT:    vpsrlw $4, %ymm0, %ymm4
+; AVX512F-NEXT:    vpand %ymm1, %ymm4, %ymm4
+; AVX512F-NEXT:    vpshufb %ymm4, %ymm3, %ymm4
+; AVX512F-NEXT:    vpaddb %ymm2, %ymm4, %ymm2
+; AVX512F-NEXT:    vpsllw $8, %ymm2, %ymm4
+; AVX512F-NEXT:    vpaddb %ymm2, %ymm4, %ymm2
+; AVX512F-NEXT:    vpsrlw $8, %ymm2, %ymm2
+; AVX512F-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
+; AVX512F-NEXT:    vpand %ymm1, %ymm0, %ymm4
+; AVX512F-NEXT:    vpshufb %ymm4, %ymm3, %ymm4
+; AVX512F-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX512F-NEXT:    vpand %ymm1, %ymm0, %ymm0
+; AVX512F-NEXT:    vpshufb %ymm0, %ymm3, %ymm0
+; AVX512F-NEXT:    vpaddb %ymm4, %ymm0, %ymm0
+; AVX512F-NEXT:    vpsllw $8, %ymm0, %ymm1
+; AVX512F-NEXT:    vpaddb %ymm0, %ymm1, %ymm0
+; AVX512F-NEXT:    vpsrlw $8, %ymm0, %ymm0
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm1 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1]
+; AVX512F-NEXT:    vpcmpeqw %ymm1, %ymm0, %ymm0
+; AVX512F-NEXT:    vpcmpeqw %ymm1, %ymm2, %ymm1
+; AVX512F-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
+; AVX512F-NEXT:    retq
+;
+; AVX512BW-LABEL: eq_1_v32i16:
+; AVX512BW:       # %bb.0:
+; AVX512BW-NEXT:    vmovdqa64 {{.*#+}} zmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512BW-NEXT:    vpandq %zmm1, %zmm0, %zmm2
+; AVX512BW-NEXT:    vmovdqa64 {{.*#+}} zmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512BW-NEXT:    vpshufb %zmm2, %zmm3, %zmm2
+; AVX512BW-NEXT:    vpsrlw $4, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpandq %zmm1, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpshufb %zmm0, %zmm3, %zmm0
+; AVX512BW-NEXT:    vpaddb %zmm2, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpsllw $8, %zmm0, %zmm1
+; AVX512BW-NEXT:    vpaddb %zmm0, %zmm1, %zmm0
+; AVX512BW-NEXT:    vpsrlw $8, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpcmpeqw {{.*}}(%rip), %zmm0, %k0
+; AVX512BW-NEXT:    vpmovm2w %k0, %zmm0
+; AVX512BW-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-NOBW-LABEL: eq_1_v32i16:
+; AVX512VPOPCNTDQ-NOBW:       # %bb.0:
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpmovzxwd {{.*#+}} zmm1 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpopcntd %zmm1, %zmm1
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpmovdw %zmm1, %ymm1
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpopcntd %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpmovdw %zmm0, %ymm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vmovdqa {{.*#+}} ymm2 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1]
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpcmpeqw %ymm2, %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpcmpeqw %ymm2, %ymm1, %ymm1
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-BW-LABEL: eq_1_v32i16:
+; AVX512VPOPCNTDQ-BW:       # %bb.0:
+; AVX512VPOPCNTDQ-BW-NEXT:    vmovdqa64 {{.*#+}} zmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512VPOPCNTDQ-BW-NEXT:    vpandq %zmm1, %zmm0, %zmm2
+; AVX512VPOPCNTDQ-BW-NEXT:    vmovdqa64 {{.*#+}} zmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512VPOPCNTDQ-BW-NEXT:    vpshufb %zmm2, %zmm3, %zmm2
+; AVX512VPOPCNTDQ-BW-NEXT:    vpsrlw $4, %zmm0, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpandq %zmm1, %zmm0, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpshufb %zmm0, %zmm3, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpaddb %zmm2, %zmm0, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpsllw $8, %zmm0, %zmm1
+; AVX512VPOPCNTDQ-BW-NEXT:    vpaddb %zmm0, %zmm1, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpsrlw $8, %zmm0, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpcmpeqw {{.*}}(%rip), %zmm0, %k0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpmovm2w %k0, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    retq
+;
+; BITALG-LABEL: eq_1_v32i16:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntw %zmm0, %zmm0
+; BITALG-NEXT:    vpcmpeqw {{.*}}(%rip), %zmm0, %k0
+; BITALG-NEXT:    vpmovm2w %k0, %zmm0
+; BITALG-NEXT:    retq
+  %2 = tail call <32 x i16> @llvm.ctpop.v32i16(<32 x i16> %0)
+  %3 = icmp eq <32 x i16> %2, <i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1>
+  %4 = sext <32 x i1> %3 to <32 x i16>
+  ret <32 x i16> %4
+}
+
+define <32 x i16> @ne_1_v32i16(<32 x i16> %0) {
+; AVX512F-LABEL: ne_1_v32i16:
+; AVX512F:       # %bb.0:
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512F-NEXT:    vpand %ymm1, %ymm0, %ymm2
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512F-NEXT:    vpshufb %ymm2, %ymm3, %ymm2
+; AVX512F-NEXT:    vpsrlw $4, %ymm0, %ymm4
+; AVX512F-NEXT:    vpand %ymm1, %ymm4, %ymm4
+; AVX512F-NEXT:    vpshufb %ymm4, %ymm3, %ymm4
+; AVX512F-NEXT:    vpaddb %ymm2, %ymm4, %ymm2
+; AVX512F-NEXT:    vpsllw $8, %ymm2, %ymm4
+; AVX512F-NEXT:    vpaddb %ymm2, %ymm4, %ymm2
+; AVX512F-NEXT:    vpsrlw $8, %ymm2, %ymm2
+; AVX512F-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
+; AVX512F-NEXT:    vpand %ymm1, %ymm0, %ymm4
+; AVX512F-NEXT:    vpshufb %ymm4, %ymm3, %ymm4
+; AVX512F-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX512F-NEXT:    vpand %ymm1, %ymm0, %ymm0
+; AVX512F-NEXT:    vpshufb %ymm0, %ymm3, %ymm0
+; AVX512F-NEXT:    vpaddb %ymm4, %ymm0, %ymm0
+; AVX512F-NEXT:    vpsllw $8, %ymm0, %ymm1
+; AVX512F-NEXT:    vpaddb %ymm0, %ymm1, %ymm0
+; AVX512F-NEXT:    vpsrlw $8, %ymm0, %ymm0
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm1 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1]
+; AVX512F-NEXT:    vpcmpeqw %ymm1, %ymm0, %ymm0
+; AVX512F-NEXT:    vpcmpeqw %ymm1, %ymm2, %ymm1
+; AVX512F-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
+; AVX512F-NEXT:    vpternlogq $15, %zmm0, %zmm0, %zmm0
+; AVX512F-NEXT:    retq
+;
+; AVX512BW-LABEL: ne_1_v32i16:
+; AVX512BW:       # %bb.0:
+; AVX512BW-NEXT:    vmovdqa64 {{.*#+}} zmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512BW-NEXT:    vpandq %zmm1, %zmm0, %zmm2
+; AVX512BW-NEXT:    vmovdqa64 {{.*#+}} zmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512BW-NEXT:    vpshufb %zmm2, %zmm3, %zmm2
+; AVX512BW-NEXT:    vpsrlw $4, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpandq %zmm1, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpshufb %zmm0, %zmm3, %zmm0
+; AVX512BW-NEXT:    vpaddb %zmm2, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpsllw $8, %zmm0, %zmm1
+; AVX512BW-NEXT:    vpaddb %zmm0, %zmm1, %zmm0
+; AVX512BW-NEXT:    vpsrlw $8, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpcmpneqw {{.*}}(%rip), %zmm0, %k0
+; AVX512BW-NEXT:    vpmovm2w %k0, %zmm0
+; AVX512BW-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-NOBW-LABEL: ne_1_v32i16:
+; AVX512VPOPCNTDQ-NOBW:       # %bb.0:
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpmovzxwd {{.*#+}} zmm1 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpopcntd %zmm1, %zmm1
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpmovdw %zmm1, %ymm1
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpopcntd %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpmovdw %zmm0, %ymm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vmovdqa {{.*#+}} ymm2 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1]
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpcmpeqw %ymm2, %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpcmpeqw %ymm2, %ymm1, %ymm1
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpternlogq $15, %zmm0, %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-BW-LABEL: ne_1_v32i16:
+; AVX512VPOPCNTDQ-BW:       # %bb.0:
+; AVX512VPOPCNTDQ-BW-NEXT:    vmovdqa64 {{.*#+}} zmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512VPOPCNTDQ-BW-NEXT:    vpandq %zmm1, %zmm0, %zmm2
+; AVX512VPOPCNTDQ-BW-NEXT:    vmovdqa64 {{.*#+}} zmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512VPOPCNTDQ-BW-NEXT:    vpshufb %zmm2, %zmm3, %zmm2
+; AVX512VPOPCNTDQ-BW-NEXT:    vpsrlw $4, %zmm0, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpandq %zmm1, %zmm0, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpshufb %zmm0, %zmm3, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpaddb %zmm2, %zmm0, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpsllw $8, %zmm0, %zmm1
+; AVX512VPOPCNTDQ-BW-NEXT:    vpaddb %zmm0, %zmm1, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpsrlw $8, %zmm0, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpcmpneqw {{.*}}(%rip), %zmm0, %k0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpmovm2w %k0, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    retq
+;
+; BITALG-LABEL: ne_1_v32i16:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntw %zmm0, %zmm0
+; BITALG-NEXT:    vpcmpneqw {{.*}}(%rip), %zmm0, %k0
+; BITALG-NEXT:    vpmovm2w %k0, %zmm0
+; BITALG-NEXT:    retq
+  %2 = tail call <32 x i16> @llvm.ctpop.v32i16(<32 x i16> %0)
+  %3 = icmp ne <32 x i16> %2, <i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1>
+  %4 = sext <32 x i1> %3 to <32 x i16>
+  ret <32 x i16> %4
+}
+
+define <64 x i8> @ult_2_v64i8(<64 x i8> %0) {
+; AVX512F-LABEL: ult_2_v64i8:
+; AVX512F:       # %bb.0:
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512F-NEXT:    vpand %ymm1, %ymm0, %ymm2
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512F-NEXT:    vpshufb %ymm2, %ymm3, %ymm2
+; AVX512F-NEXT:    vpsrlw $4, %ymm0, %ymm4
+; AVX512F-NEXT:    vpand %ymm1, %ymm4, %ymm4
+; AVX512F-NEXT:    vpshufb %ymm4, %ymm3, %ymm4
+; AVX512F-NEXT:    vpaddb %ymm2, %ymm4, %ymm2
+; AVX512F-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
+; AVX512F-NEXT:    vpand %ymm1, %ymm0, %ymm4
+; AVX512F-NEXT:    vpshufb %ymm4, %ymm3, %ymm4
+; AVX512F-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX512F-NEXT:    vpand %ymm1, %ymm0, %ymm0
+; AVX512F-NEXT:    vpshufb %ymm0, %ymm3, %ymm0
+; AVX512F-NEXT:    vpaddb %ymm4, %ymm0, %ymm0
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm1 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1]
+; AVX512F-NEXT:    vpminub %ymm1, %ymm0, %ymm3
+; AVX512F-NEXT:    vpcmpeqb %ymm3, %ymm0, %ymm0
+; AVX512F-NEXT:    vpminub %ymm1, %ymm2, %ymm1
+; AVX512F-NEXT:    vpcmpeqb %ymm1, %ymm2, %ymm1
+; AVX512F-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
+; AVX512F-NEXT:    retq
+;
+; AVX512BW-LABEL: ult_2_v64i8:
+; AVX512BW:       # %bb.0:
+; AVX512BW-NEXT:    vmovdqa64 {{.*#+}} zmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512BW-NEXT:    vpandq %zmm1, %zmm0, %zmm2
+; AVX512BW-NEXT:    vmovdqa64 {{.*#+}} zmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512BW-NEXT:    vpshufb %zmm2, %zmm3, %zmm2
+; AVX512BW-NEXT:    vpsrlw $4, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpandq %zmm1, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpshufb %zmm0, %zmm3, %zmm0
+; AVX512BW-NEXT:    vpaddb %zmm2, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpcmpltub {{.*}}(%rip), %zmm0, %k0
+; AVX512BW-NEXT:    vpmovm2b %k0, %zmm0
+; AVX512BW-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-NOBW-LABEL: ult_2_v64i8:
+; AVX512VPOPCNTDQ-NOBW:       # %bb.0:
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vmovdqa {{.*#+}} ymm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpand %ymm1, %ymm0, %ymm2
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpshufb %ymm2, %ymm3, %ymm2
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpsrlw $4, %ymm0, %ymm4
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpand %ymm1, %ymm4, %ymm4
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpshufb %ymm4, %ymm3, %ymm4
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpaddb %ymm2, %ymm4, %ymm2
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpand %ymm1, %ymm0, %ymm4
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpshufb %ymm4, %ymm3, %ymm4
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpand %ymm1, %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpshufb %ymm0, %ymm3, %ymm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpaddb %ymm4, %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vmovdqa {{.*#+}} ymm1 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1]
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpminub %ymm1, %ymm0, %ymm3
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpcmpeqb %ymm3, %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpminub %ymm1, %ymm2, %ymm1
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpcmpeqb %ymm1, %ymm2, %ymm1
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-BW-LABEL: ult_2_v64i8:
+; AVX512VPOPCNTDQ-BW:       # %bb.0:
+; AVX512VPOPCNTDQ-BW-NEXT:    vmovdqa64 {{.*#+}} zmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512VPOPCNTDQ-BW-NEXT:    vpandq %zmm1, %zmm0, %zmm2
+; AVX512VPOPCNTDQ-BW-NEXT:    vmovdqa64 {{.*#+}} zmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512VPOPCNTDQ-BW-NEXT:    vpshufb %zmm2, %zmm3, %zmm2
+; AVX512VPOPCNTDQ-BW-NEXT:    vpsrlw $4, %zmm0, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpandq %zmm1, %zmm0, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpshufb %zmm0, %zmm3, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpaddb %zmm2, %zmm0, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpcmpltub {{.*}}(%rip), %zmm0, %k0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpmovm2b %k0, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    retq
+;
+; BITALG-LABEL: ult_2_v64i8:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntb %zmm0, %zmm0
+; BITALG-NEXT:    vpcmpltub {{.*}}(%rip), %zmm0, %k0
+; BITALG-NEXT:    vpmovm2b %k0, %zmm0
+; BITALG-NEXT:    retq
+  %2 = tail call <64 x i8> @llvm.ctpop.v64i8(<64 x i8> %0)
+  %3 = icmp ult <64 x i8> %2, <i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2>
+  %4 = sext <64 x i1> %3 to <64 x i8>
+  ret <64 x i8> %4
+}
+
+define <64 x i8> @ugt_1_v64i8(<64 x i8> %0) {
+; AVX512F-LABEL: ugt_1_v64i8:
+; AVX512F:       # %bb.0:
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512F-NEXT:    vpand %ymm1, %ymm0, %ymm2
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512F-NEXT:    vpshufb %ymm2, %ymm3, %ymm2
+; AVX512F-NEXT:    vpsrlw $4, %ymm0, %ymm4
+; AVX512F-NEXT:    vpand %ymm1, %ymm4, %ymm4
+; AVX512F-NEXT:    vpshufb %ymm4, %ymm3, %ymm4
+; AVX512F-NEXT:    vpaddb %ymm2, %ymm4, %ymm2
+; AVX512F-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
+; AVX512F-NEXT:    vpand %ymm1, %ymm0, %ymm4
+; AVX512F-NEXT:    vpshufb %ymm4, %ymm3, %ymm4
+; AVX512F-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX512F-NEXT:    vpand %ymm1, %ymm0, %ymm0
+; AVX512F-NEXT:    vpshufb %ymm0, %ymm3, %ymm0
+; AVX512F-NEXT:    vpaddb %ymm4, %ymm0, %ymm0
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm1 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2]
+; AVX512F-NEXT:    vpmaxub %ymm1, %ymm0, %ymm3
+; AVX512F-NEXT:    vpcmpeqb %ymm3, %ymm0, %ymm0
+; AVX512F-NEXT:    vpmaxub %ymm1, %ymm2, %ymm1
+; AVX512F-NEXT:    vpcmpeqb %ymm1, %ymm2, %ymm1
+; AVX512F-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
+; AVX512F-NEXT:    retq
+;
+; AVX512BW-LABEL: ugt_1_v64i8:
+; AVX512BW:       # %bb.0:
+; AVX512BW-NEXT:    vmovdqa64 {{.*#+}} zmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512BW-NEXT:    vpandq %zmm1, %zmm0, %zmm2
+; AVX512BW-NEXT:    vmovdqa64 {{.*#+}} zmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512BW-NEXT:    vpshufb %zmm2, %zmm3, %zmm2
+; AVX512BW-NEXT:    vpsrlw $4, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpandq %zmm1, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpshufb %zmm0, %zmm3, %zmm0
+; AVX512BW-NEXT:    vpaddb %zmm2, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpcmpnleub {{.*}}(%rip), %zmm0, %k0
+; AVX512BW-NEXT:    vpmovm2b %k0, %zmm0
+; AVX512BW-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-NOBW-LABEL: ugt_1_v64i8:
+; AVX512VPOPCNTDQ-NOBW:       # %bb.0:
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vmovdqa {{.*#+}} ymm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpand %ymm1, %ymm0, %ymm2
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpshufb %ymm2, %ymm3, %ymm2
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpsrlw $4, %ymm0, %ymm4
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpand %ymm1, %ymm4, %ymm4
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpshufb %ymm4, %ymm3, %ymm4
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpaddb %ymm2, %ymm4, %ymm2
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpand %ymm1, %ymm0, %ymm4
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpshufb %ymm4, %ymm3, %ymm4
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpand %ymm1, %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpshufb %ymm0, %ymm3, %ymm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpaddb %ymm4, %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vmovdqa {{.*#+}} ymm1 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2]
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpmaxub %ymm1, %ymm0, %ymm3
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpcmpeqb %ymm3, %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpmaxub %ymm1, %ymm2, %ymm1
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpcmpeqb %ymm1, %ymm2, %ymm1
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-BW-LABEL: ugt_1_v64i8:
+; AVX512VPOPCNTDQ-BW:       # %bb.0:
+; AVX512VPOPCNTDQ-BW-NEXT:    vmovdqa64 {{.*#+}} zmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512VPOPCNTDQ-BW-NEXT:    vpandq %zmm1, %zmm0, %zmm2
+; AVX512VPOPCNTDQ-BW-NEXT:    vmovdqa64 {{.*#+}} zmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512VPOPCNTDQ-BW-NEXT:    vpshufb %zmm2, %zmm3, %zmm2
+; AVX512VPOPCNTDQ-BW-NEXT:    vpsrlw $4, %zmm0, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpandq %zmm1, %zmm0, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpshufb %zmm0, %zmm3, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpaddb %zmm2, %zmm0, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpcmpnleub {{.*}}(%rip), %zmm0, %k0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpmovm2b %k0, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    retq
+;
+; BITALG-LABEL: ugt_1_v64i8:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntb %zmm0, %zmm0
+; BITALG-NEXT:    vpcmpnleub {{.*}}(%rip), %zmm0, %k0
+; BITALG-NEXT:    vpmovm2b %k0, %zmm0
+; BITALG-NEXT:    retq
+  %2 = tail call <64 x i8> @llvm.ctpop.v64i8(<64 x i8> %0)
+  %3 = icmp ugt <64 x i8> %2, <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
+  %4 = sext <64 x i1> %3 to <64 x i8>
+  ret <64 x i8> %4
+}
+
+define <64 x i8> @eq_1_v64i8(<64 x i8> %0) {
+; AVX512F-LABEL: eq_1_v64i8:
+; AVX512F:       # %bb.0:
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512F-NEXT:    vpand %ymm1, %ymm0, %ymm2
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512F-NEXT:    vpshufb %ymm2, %ymm3, %ymm2
+; AVX512F-NEXT:    vpsrlw $4, %ymm0, %ymm4
+; AVX512F-NEXT:    vpand %ymm1, %ymm4, %ymm4
+; AVX512F-NEXT:    vpshufb %ymm4, %ymm3, %ymm4
+; AVX512F-NEXT:    vpaddb %ymm2, %ymm4, %ymm2
+; AVX512F-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
+; AVX512F-NEXT:    vpand %ymm1, %ymm0, %ymm4
+; AVX512F-NEXT:    vpshufb %ymm4, %ymm3, %ymm4
+; AVX512F-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX512F-NEXT:    vpand %ymm1, %ymm0, %ymm0
+; AVX512F-NEXT:    vpshufb %ymm0, %ymm3, %ymm0
+; AVX512F-NEXT:    vpaddb %ymm4, %ymm0, %ymm0
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm1 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1]
+; AVX512F-NEXT:    vpcmpeqb %ymm1, %ymm0, %ymm0
+; AVX512F-NEXT:    vpcmpeqb %ymm1, %ymm2, %ymm1
+; AVX512F-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
+; AVX512F-NEXT:    retq
+;
+; AVX512BW-LABEL: eq_1_v64i8:
+; AVX512BW:       # %bb.0:
+; AVX512BW-NEXT:    vmovdqa64 {{.*#+}} zmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512BW-NEXT:    vpandq %zmm1, %zmm0, %zmm2
+; AVX512BW-NEXT:    vmovdqa64 {{.*#+}} zmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512BW-NEXT:    vpshufb %zmm2, %zmm3, %zmm2
+; AVX512BW-NEXT:    vpsrlw $4, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpandq %zmm1, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpshufb %zmm0, %zmm3, %zmm0
+; AVX512BW-NEXT:    vpaddb %zmm2, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpcmpeqb {{.*}}(%rip), %zmm0, %k0
+; AVX512BW-NEXT:    vpmovm2b %k0, %zmm0
+; AVX512BW-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-NOBW-LABEL: eq_1_v64i8:
+; AVX512VPOPCNTDQ-NOBW:       # %bb.0:
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vmovdqa {{.*#+}} ymm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpand %ymm1, %ymm0, %ymm2
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpshufb %ymm2, %ymm3, %ymm2
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpsrlw $4, %ymm0, %ymm4
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpand %ymm1, %ymm4, %ymm4
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpshufb %ymm4, %ymm3, %ymm4
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpaddb %ymm2, %ymm4, %ymm2
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpand %ymm1, %ymm0, %ymm4
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpshufb %ymm4, %ymm3, %ymm4
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpand %ymm1, %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpshufb %ymm0, %ymm3, %ymm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpaddb %ymm4, %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vmovdqa {{.*#+}} ymm1 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1]
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpcmpeqb %ymm1, %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpcmpeqb %ymm1, %ymm2, %ymm1
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-BW-LABEL: eq_1_v64i8:
+; AVX512VPOPCNTDQ-BW:       # %bb.0:
+; AVX512VPOPCNTDQ-BW-NEXT:    vmovdqa64 {{.*#+}} zmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512VPOPCNTDQ-BW-NEXT:    vpandq %zmm1, %zmm0, %zmm2
+; AVX512VPOPCNTDQ-BW-NEXT:    vmovdqa64 {{.*#+}} zmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512VPOPCNTDQ-BW-NEXT:    vpshufb %zmm2, %zmm3, %zmm2
+; AVX512VPOPCNTDQ-BW-NEXT:    vpsrlw $4, %zmm0, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpandq %zmm1, %zmm0, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpshufb %zmm0, %zmm3, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpaddb %zmm2, %zmm0, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpcmpeqb {{.*}}(%rip), %zmm0, %k0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpmovm2b %k0, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    retq
+;
+; BITALG-LABEL: eq_1_v64i8:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntb %zmm0, %zmm0
+; BITALG-NEXT:    vpcmpeqb {{.*}}(%rip), %zmm0, %k0
+; BITALG-NEXT:    vpmovm2b %k0, %zmm0
+; BITALG-NEXT:    retq
+  %2 = tail call <64 x i8> @llvm.ctpop.v64i8(<64 x i8> %0)
+  %3 = icmp eq <64 x i8> %2, <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
+  %4 = sext <64 x i1> %3 to <64 x i8>
+  ret <64 x i8> %4
+}
+
+define <64 x i8> @ne_1_v64i8(<64 x i8> %0) {
+; AVX512F-LABEL: ne_1_v64i8:
+; AVX512F:       # %bb.0:
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512F-NEXT:    vpand %ymm1, %ymm0, %ymm2
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512F-NEXT:    vpshufb %ymm2, %ymm3, %ymm2
+; AVX512F-NEXT:    vpsrlw $4, %ymm0, %ymm4
+; AVX512F-NEXT:    vpand %ymm1, %ymm4, %ymm4
+; AVX512F-NEXT:    vpshufb %ymm4, %ymm3, %ymm4
+; AVX512F-NEXT:    vpaddb %ymm2, %ymm4, %ymm2
+; AVX512F-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
+; AVX512F-NEXT:    vpand %ymm1, %ymm0, %ymm4
+; AVX512F-NEXT:    vpshufb %ymm4, %ymm3, %ymm4
+; AVX512F-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX512F-NEXT:    vpand %ymm1, %ymm0, %ymm0
+; AVX512F-NEXT:    vpshufb %ymm0, %ymm3, %ymm0
+; AVX512F-NEXT:    vpaddb %ymm4, %ymm0, %ymm0
+; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm1 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1]
+; AVX512F-NEXT:    vpcmpeqb %ymm1, %ymm0, %ymm0
+; AVX512F-NEXT:    vpcmpeqb %ymm1, %ymm2, %ymm1
+; AVX512F-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
+; AVX512F-NEXT:    vpternlogq $15, %zmm0, %zmm0, %zmm0
+; AVX512F-NEXT:    retq
+;
+; AVX512BW-LABEL: ne_1_v64i8:
+; AVX512BW:       # %bb.0:
+; AVX512BW-NEXT:    vmovdqa64 {{.*#+}} zmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512BW-NEXT:    vpandq %zmm1, %zmm0, %zmm2
+; AVX512BW-NEXT:    vmovdqa64 {{.*#+}} zmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512BW-NEXT:    vpshufb %zmm2, %zmm3, %zmm2
+; AVX512BW-NEXT:    vpsrlw $4, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpandq %zmm1, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpshufb %zmm0, %zmm3, %zmm0
+; AVX512BW-NEXT:    vpaddb %zmm2, %zmm0, %zmm0
+; AVX512BW-NEXT:    vpcmpneqb {{.*}}(%rip), %zmm0, %k0
+; AVX512BW-NEXT:    vpmovm2b %k0, %zmm0
+; AVX512BW-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-NOBW-LABEL: ne_1_v64i8:
+; AVX512VPOPCNTDQ-NOBW:       # %bb.0:
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vmovdqa {{.*#+}} ymm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpand %ymm1, %ymm0, %ymm2
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vmovdqa {{.*#+}} ymm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpshufb %ymm2, %ymm3, %ymm2
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpsrlw $4, %ymm0, %ymm4
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpand %ymm1, %ymm4, %ymm4
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpshufb %ymm4, %ymm3, %ymm4
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpaddb %ymm2, %ymm4, %ymm2
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpand %ymm1, %ymm0, %ymm4
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpshufb %ymm4, %ymm3, %ymm4
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpsrlw $4, %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpand %ymm1, %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpshufb %ymm0, %ymm3, %ymm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpaddb %ymm4, %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vmovdqa {{.*#+}} ymm1 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1]
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpcmpeqb %ymm1, %ymm0, %ymm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpcmpeqb %ymm1, %ymm2, %ymm1
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    vpternlogq $15, %zmm0, %zmm0, %zmm0
+; AVX512VPOPCNTDQ-NOBW-NEXT:    retq
+;
+; AVX512VPOPCNTDQ-BW-LABEL: ne_1_v64i8:
+; AVX512VPOPCNTDQ-BW:       # %bb.0:
+; AVX512VPOPCNTDQ-BW-NEXT:    vmovdqa64 {{.*#+}} zmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX512VPOPCNTDQ-BW-NEXT:    vpandq %zmm1, %zmm0, %zmm2
+; AVX512VPOPCNTDQ-BW-NEXT:    vmovdqa64 {{.*#+}} zmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4,0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
+; AVX512VPOPCNTDQ-BW-NEXT:    vpshufb %zmm2, %zmm3, %zmm2
+; AVX512VPOPCNTDQ-BW-NEXT:    vpsrlw $4, %zmm0, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpandq %zmm1, %zmm0, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpshufb %zmm0, %zmm3, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpaddb %zmm2, %zmm0, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpcmpneqb {{.*}}(%rip), %zmm0, %k0
+; AVX512VPOPCNTDQ-BW-NEXT:    vpmovm2b %k0, %zmm0
+; AVX512VPOPCNTDQ-BW-NEXT:    retq
+;
+; BITALG-LABEL: ne_1_v64i8:
+; BITALG:       # %bb.0:
+; BITALG-NEXT:    vpopcntb %zmm0, %zmm0
+; BITALG-NEXT:    vpcmpneqb {{.*}}(%rip), %zmm0, %k0
+; BITALG-NEXT:    vpmovm2b %k0, %zmm0
+; BITALG-NEXT:    retq
+  %2 = tail call <64 x i8> @llvm.ctpop.v64i8(<64 x i8> %0)
+  %3 = icmp ne <64 x i8> %2, <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
+  %4 = sext <64 x i1> %3 to <64 x i8>
+  ret <64 x i8> %4
+}
+
 declare <8 x i64> @llvm.ctpop.v8i64(<8 x i64>)
 declare <16 x i32> @llvm.ctpop.v16i32(<16 x i32>)
 declare <32 x i16> @llvm.ctpop.v32i16(<32 x i16>)