[clang][powerpc][wasm][systemz][x86] Replace target vector popcount intrinsics with __builtin_elementwise_popcount

clang/include/clang/Basic/BuiltinsPPC.def

@@ -541,12 +541,6 @@ TARGET_BUILTIN(__builtin_altivec_vprtybw, "V4UiV4Ui", "", "power9-vector")
 TARGET_BUILTIN(__builtin_altivec_vprtybd, "V2ULLiV2ULLi", "", "power9-vector")
 TARGET_BUILTIN(__builtin_altivec_vprtybq, "V1ULLLiV1ULLLi", "", "power9-vector")
 
-// Vector population count built-ins
-TARGET_BUILTIN(__builtin_altivec_vpopcntb, "V16UcV16Uc", "", "power8-vector")
-TARGET_BUILTIN(__builtin_altivec_vpopcnth, "V8UsV8Us", "", "power8-vector")
-TARGET_BUILTIN(__builtin_altivec_vpopcntw, "V4UiV4Ui", "", "power8-vector")
-TARGET_BUILTIN(__builtin_altivec_vpopcntd, "V2ULLiV2ULLi", "", "power8-vector")
-
 // Absolute difference built-ins
 TARGET_BUILTIN(__builtin_altivec_vabsdub, "V16UcV16UcV16Uc", "",
                "power9-vector")

clang/include/clang/Basic/BuiltinsSystemZ.def

@@ -157,10 +157,6 @@ TARGET_BUILTIN(__builtin_s390_vmof, "V2SLLiV4SiV4Si", "nc", "vector")
 TARGET_BUILTIN(__builtin_s390_vmlob, "V8UsV16UcV16Uc", "nc", "vector")
 TARGET_BUILTIN(__builtin_s390_vmloh, "V4UiV8UsV8Us", "nc", "vector")
 TARGET_BUILTIN(__builtin_s390_vmlof, "V2ULLiV4UiV4Ui", "nc", "vector")
-TARGET_BUILTIN(__builtin_s390_vpopctb, "V16UcV16Uc", "nc", "vector")
-TARGET_BUILTIN(__builtin_s390_vpopcth, "V8UsV8Us", "nc", "vector")
-TARGET_BUILTIN(__builtin_s390_vpopctf, "V4UiV4Ui", "nc", "vector")
-TARGET_BUILTIN(__builtin_s390_vpopctg, "V2ULLiV2ULLi", "nc", "vector")
 TARGET_BUILTIN(__builtin_s390_vsq, "SLLLiSLLLiSLLLi", "nc", "vector")
 TARGET_BUILTIN(__builtin_s390_vsbcbiq, "ULLLiULLLiULLLiULLLi", "nc", "vector")
 TARGET_BUILTIN(__builtin_s390_vsbiq, "ULLLiULLLiULLLiULLLi", "nc", "vector")

clang/include/clang/Basic/BuiltinsWebAssembly.def

@@ -99,8 +99,6 @@ TARGET_BUILTIN(__builtin_wasm_max_u_i32x4, "V4UiV4UiV4Ui", "nc", "simd128")
 TARGET_BUILTIN(__builtin_wasm_avgr_u_i8x16, "V16UcV16UcV16Uc", "nc", "simd128")
 TARGET_BUILTIN(__builtin_wasm_avgr_u_i16x8, "V8UsV8UsV8Us", "nc", "simd128")
 
-TARGET_BUILTIN(__builtin_wasm_popcnt_i8x16, "V16ScV16Sc", "nc", "simd128")
-
 TARGET_BUILTIN(__builtin_wasm_q15mulr_sat_s_i16x8, "V8sV8sV8s", "nc", "simd128")
 
 TARGET_BUILTIN(__builtin_wasm_extadd_pairwise_i8x16_s_i16x8, "V8sV16Sc", "nc", "simd128")

clang/include/clang/Basic/BuiltinsX86.def

@@ -866,20 +866,6 @@ TARGET_BUILTIN(__builtin_ia32_vpconflictsi_512, "V16iV16i", "ncV:512:", "avx512c
 TARGET_BUILTIN(__builtin_ia32_vplzcntd_512, "V16iV16i", "ncV:512:", "avx512cd,evex512")
 TARGET_BUILTIN(__builtin_ia32_vplzcntq_512, "V8OiV8Oi", "ncV:512:", "avx512cd,evex512")
 
-TARGET_BUILTIN(__builtin_ia32_vpopcntd_128, "V4iV4i", "ncV:128:", "avx512vpopcntdq,avx512vl")
-TARGET_BUILTIN(__builtin_ia32_vpopcntq_128, "V2OiV2Oi", "ncV:128:", "avx512vpopcntdq,avx512vl")
-TARGET_BUILTIN(__builtin_ia32_vpopcntd_256, "V8iV8i", "ncV:256:", "avx512vpopcntdq,avx512vl")
-TARGET_BUILTIN(__builtin_ia32_vpopcntq_256, "V4OiV4Oi", "ncV:256:", "avx512vpopcntdq,avx512vl")
-TARGET_BUILTIN(__builtin_ia32_vpopcntd_512, "V16iV16i", "ncV:512:", "avx512vpopcntdq,evex512")
-TARGET_BUILTIN(__builtin_ia32_vpopcntq_512, "V8OiV8Oi", "ncV:512:", "avx512vpopcntdq,evex512")
-
-TARGET_BUILTIN(__builtin_ia32_vpopcntb_128, "V16cV16c", "ncV:128:", "avx512vl,avx512bitalg")
-TARGET_BUILTIN(__builtin_ia32_vpopcntw_128, "V8sV8s", "ncV:128:", "avx512vl,avx512bitalg")
-TARGET_BUILTIN(__builtin_ia32_vpopcntb_256, "V32cV32c", "ncV:256:", "avx512vl,avx512bitalg")
-TARGET_BUILTIN(__builtin_ia32_vpopcntw_256, "V16sV16s", "ncV:256:", "avx512vl,avx512bitalg")
-TARGET_BUILTIN(__builtin_ia32_vpopcntb_512, "V64cV64c", "ncV:512:", "avx512bitalg,evex512")
-TARGET_BUILTIN(__builtin_ia32_vpopcntw_512, "V32sV32s", "ncV:512:", "avx512bitalg,evex512")
-
 TARGET_BUILTIN(__builtin_ia32_vpshufbitqmb128_mask, "UsV16cV16cUs", "ncV:128:", "avx512vl,avx512bitalg")
 TARGET_BUILTIN(__builtin_ia32_vpshufbitqmb256_mask, "UiV32cV32cUi", "ncV:256:", "avx512vl,avx512bitalg")
 TARGET_BUILTIN(__builtin_ia32_vpshufbitqmb512_mask, "UOiV64cV64cUOi", "ncV:512:", "avx512bitalg,evex512")

clang/lib/CodeGen/CGBuiltin.cpp

@@ -14807,22 +14807,6 @@ Value *CodeGenFunction::EmitX86BuiltinExpr(unsigned BuiltinID,
   case X86::BI__builtin_ia32_storesd128_mask:
     return EmitX86MaskedStore(*this, Ops, Align(1));
 
-  case X86::BI__builtin_ia32_vpopcntb_128:
-  case X86::BI__builtin_ia32_vpopcntd_128:
-  case X86::BI__builtin_ia32_vpopcntq_128:
-  case X86::BI__builtin_ia32_vpopcntw_128:
-  case X86::BI__builtin_ia32_vpopcntb_256:
-  case X86::BI__builtin_ia32_vpopcntd_256:
-  case X86::BI__builtin_ia32_vpopcntq_256:
-  case X86::BI__builtin_ia32_vpopcntw_256:
-  case X86::BI__builtin_ia32_vpopcntb_512:
-  case X86::BI__builtin_ia32_vpopcntd_512:
-  case X86::BI__builtin_ia32_vpopcntq_512:
-  case X86::BI__builtin_ia32_vpopcntw_512: {
-    llvm::Type *ResultType = ConvertType(E->getType());
-    llvm::Function *F = CGM.getIntrinsic(Intrinsic::ctpop, ResultType);
-    return Builder.CreateCall(F, Ops);
-  }
   case X86::BI__builtin_ia32_cvtmask2b128:
   case X86::BI__builtin_ia32_cvtmask2b256:
   case X86::BI__builtin_ia32_cvtmask2b512:
@@ -17624,15 +17608,6 @@ Value *CodeGenFunction::EmitPPCBuiltinExpr(unsigned BuiltinID,
     return Builder.CreateBitCast(
         Builder.CreateCall(CGM.getIntrinsic(ID), {Op0, Op1, Op2}), ResultType);
   }
-  case PPC::BI__builtin_altivec_vpopcntb:
-  case PPC::BI__builtin_altivec_vpopcnth:
-  case PPC::BI__builtin_altivec_vpopcntw:
-  case PPC::BI__builtin_altivec_vpopcntd: {
-    llvm::Type *ResultType = ConvertType(E->getType());
-    Value *X = EmitScalarExpr(E->getArg(0));
-    llvm::Function *F = CGM.getIntrinsic(Intrinsic::ctpop, ResultType);
-    return Builder.CreateCall(F, X);
-  }
   case PPC::BI__builtin_altivec_vadduqm:
   case PPC::BI__builtin_altivec_vsubuqm: {
     Value *Op0 = EmitScalarExpr(E->getArg(0));
@@ -19702,16 +19677,6 @@ Value *CodeGenFunction::EmitSystemZBuiltinExpr(unsigned BuiltinID,
   // be represented via standard LLVM IR, which is preferable to enable common
   // LLVM optimizations.
 
-  case SystemZ::BI__builtin_s390_vpopctb:
-  case SystemZ::BI__builtin_s390_vpopcth:
-  case SystemZ::BI__builtin_s390_vpopctf:
-  case SystemZ::BI__builtin_s390_vpopctg: {
-    llvm::Type *ResultType = ConvertType(E->getType());
-    Value *X = EmitScalarExpr(E->getArg(0));
-    Function *F = CGM.getIntrinsic(Intrinsic::ctpop, ResultType);
-    return Builder.CreateCall(F, X);
-  }
-
   case SystemZ::BI__builtin_s390_vclzb:
   case SystemZ::BI__builtin_s390_vclzh:
   case SystemZ::BI__builtin_s390_vclzf:
@@ -21613,12 +21578,6 @@ Value *CodeGenFunction::EmitWebAssemblyBuiltinExpr(unsigned BuiltinID,
     Function *Callee = CGM.getIntrinsic(Intrinsic::wasm_dot);
     return Builder.CreateCall(Callee, {LHS, RHS});
   }
-  case WebAssembly::BI__builtin_wasm_popcnt_i8x16: {
-    Value *Vec = EmitScalarExpr(E->getArg(0));
-    Function *Callee =
-        CGM.getIntrinsic(Intrinsic::ctpop, ConvertType(E->getType()));
-    return Builder.CreateCall(Callee, {Vec});
-  }
   case WebAssembly::BI__builtin_wasm_any_true_v128:
   case WebAssembly::BI__builtin_wasm_all_true_i8x16:
   case WebAssembly::BI__builtin_wasm_all_true_i16x8:

clang/lib/Headers/altivec.h

@@ -2502,37 +2502,37 @@ vec_cmplt(vector unsigned long long __a, vector unsigned long long __b) {
 
 static __inline__ vector unsigned char __ATTRS_o_ai
 vec_popcnt(vector signed char __a) {
-  return (vector unsigned char)__builtin_altivec_vpopcntb(
+  return (vector unsigned char)__builtin_elementwise_popcount(
       (vector unsigned char)__a);
 }
 static __inline__ vector unsigned char __ATTRS_o_ai
 vec_popcnt(vector unsigned char __a) {
-  return __builtin_altivec_vpopcntb(__a);
+  return __builtin_elementwise_popcount(__a);
 }
 static __inline__ vector unsigned short __ATTRS_o_ai
 vec_popcnt(vector signed short __a) {
-  return (vector unsigned short)__builtin_altivec_vpopcnth(
+  return (vector unsigned short)__builtin_elementwise_popcount(
       (vector unsigned short)__a);
 }
 static __inline__ vector unsigned short __ATTRS_o_ai
 vec_popcnt(vector unsigned short __a) {
-  return __builtin_altivec_vpopcnth(__a);
+  return __builtin_elementwise_popcount(__a);
 }
 static __inline__ vector unsigned int __ATTRS_o_ai
 vec_popcnt(vector signed int __a) {
-  return __builtin_altivec_vpopcntw((vector unsigned int)__a);
+  return __builtin_elementwise_popcount((vector unsigned int)__a);
 }
 static __inline__ vector unsigned int __ATTRS_o_ai
 vec_popcnt(vector unsigned int __a) {
-  return __builtin_altivec_vpopcntw(__a);
+  return __builtin_elementwise_popcount(__a);
 }
 static __inline__ vector unsigned long long __ATTRS_o_ai
 vec_popcnt(vector signed long long __a) {
-  return __builtin_altivec_vpopcntd((vector unsigned long long)__a);
+  return __builtin_elementwise_popcount((vector unsigned long long)__a);
 }
 static __inline__ vector unsigned long long __ATTRS_o_ai
 vec_popcnt(vector unsigned long long __a) {
-  return __builtin_altivec_vpopcntd(__a);
+  return __builtin_elementwise_popcount(__a);
 }
 
 #define vec_vclz vec_cntlz

clang/lib/Headers/avx512bitalgintrin.h

@@ -23,7 +23,7 @@
 static __inline__ __m512i __DEFAULT_FN_ATTRS
 _mm512_popcnt_epi16(__m512i __A)
 {
-  return (__m512i) __builtin_ia32_vpopcntw_512((__v32hi) __A);
+  return (__m512i)__builtin_elementwise_popcount((__v32hu)__A);
 }
 
 static __inline__ __m512i __DEFAULT_FN_ATTRS
@@ -45,7 +45,7 @@ _mm512_maskz_popcnt_epi16(__mmask32 __U, __m512i __B)
 static __inline__ __m512i __DEFAULT_FN_ATTRS
 _mm512_popcnt_epi8(__m512i __A)
 {
-  return (__m512i) __builtin_ia32_vpopcntb_512((__v64qi) __A);
+  return (__m512i)__builtin_elementwise_popcount((__v64qu)__A);
 }
 
 static __inline__ __m512i __DEFAULT_FN_ATTRS

clang/lib/Headers/avx512vlbitalgintrin.h

@@ -27,7 +27,7 @@
 static __inline__ __m256i __DEFAULT_FN_ATTRS256
 _mm256_popcnt_epi16(__m256i __A)
 {
-  return (__m256i) __builtin_ia32_vpopcntw_256((__v16hi) __A);
+  return (__m256i)__builtin_elementwise_popcount((__v16hu)__A);
 }
 
 static __inline__ __m256i __DEFAULT_FN_ATTRS256
@@ -49,7 +49,7 @@ _mm256_maskz_popcnt_epi16(__mmask16 __U, __m256i __B)
 static __inline__ __m128i __DEFAULT_FN_ATTRS128
 _mm_popcnt_epi16(__m128i __A)
 {
-  return (__m128i) __builtin_ia32_vpopcntw_128((__v8hi) __A);
+  return (__m128i)__builtin_elementwise_popcount((__v8hu)__A);
 }
 
 static __inline__ __m128i __DEFAULT_FN_ATTRS128
@@ -71,7 +71,7 @@ _mm_maskz_popcnt_epi16(__mmask8 __U, __m128i __B)
 static __inline__ __m256i __DEFAULT_FN_ATTRS256
 _mm256_popcnt_epi8(__m256i __A)
 {
-  return (__m256i) __builtin_ia32_vpopcntb_256((__v32qi) __A);
+  return (__m256i)__builtin_elementwise_popcount((__v32qu)__A);
 }
 
 static __inline__ __m256i __DEFAULT_FN_ATTRS256
@@ -93,7 +93,7 @@ _mm256_maskz_popcnt_epi8(__mmask32 __U, __m256i __B)
 static __inline__ __m128i __DEFAULT_FN_ATTRS128
 _mm_popcnt_epi8(__m128i __A)
 {
-  return (__m128i) __builtin_ia32_vpopcntb_128((__v16qi) __A);
+  return (__m128i)__builtin_elementwise_popcount((__v16qu)__A);
 }
 
 static __inline__ __m128i __DEFAULT_FN_ATTRS128

clang/lib/Headers/avx512vpopcntdqintrin.h

@@ -22,7 +22,7 @@
                  __min_vector_width__(512)))
 
 static __inline__ __m512i __DEFAULT_FN_ATTRS _mm512_popcnt_epi64(__m512i __A) {
-  return (__m512i)__builtin_ia32_vpopcntq_512((__v8di)__A);
+  return (__m512i)__builtin_elementwise_popcount((__v8du)__A);
 }
 
 static __inline__ __m512i __DEFAULT_FN_ATTRS
@@ -37,7 +37,7 @@ _mm512_maskz_popcnt_epi64(__mmask8 __U, __m512i __A) {
 }
 
 static __inline__ __m512i __DEFAULT_FN_ATTRS _mm512_popcnt_epi32(__m512i __A) {
-  return (__m512i)__builtin_ia32_vpopcntd_512((__v16si)__A);
+  return (__m512i)__builtin_elementwise_popcount((__v16su)__A);
 }
 
 static __inline__ __m512i __DEFAULT_FN_ATTRS

clang/lib/Headers/avx512vpopcntdqvlintrin.h

@@ -27,7 +27,7 @@
 
 static __inline__ __m128i __DEFAULT_FN_ATTRS128
 _mm_popcnt_epi64(__m128i __A) {
-  return (__m128i)__builtin_ia32_vpopcntq_128((__v2di)__A);
+  return (__m128i)__builtin_elementwise_popcount((__v2du)__A);
 }
 
 static __inline__ __m128i __DEFAULT_FN_ATTRS128
@@ -43,7 +43,7 @@ _mm_maskz_popcnt_epi64(__mmask8 __U, __m128i __A) {
 
 static __inline__ __m128i __DEFAULT_FN_ATTRS128
 _mm_popcnt_epi32(__m128i __A) {
-  return (__m128i)__builtin_ia32_vpopcntd_128((__v4si)__A);
+  return (__m128i)__builtin_elementwise_popcount((__v4su)__A);
 }
 
 static __inline__ __m128i __DEFAULT_FN_ATTRS128
@@ -59,7 +59,7 @@ _mm_maskz_popcnt_epi32(__mmask8 __U, __m128i __A) {
 
 static __inline__ __m256i __DEFAULT_FN_ATTRS256
 _mm256_popcnt_epi64(__m256i __A) {
-  return (__m256i)__builtin_ia32_vpopcntq_256((__v4di)__A);
+  return (__m256i)__builtin_elementwise_popcount((__v4du)__A);
 }
 
 static __inline__ __m256i __DEFAULT_FN_ATTRS256
@@ -75,7 +75,7 @@ _mm256_maskz_popcnt_epi64(__mmask8 __U, __m256i __A) {
 
 static __inline__ __m256i __DEFAULT_FN_ATTRS256
 _mm256_popcnt_epi32(__m256i __A) {
-  return (__m256i)__builtin_ia32_vpopcntd_256((__v8si)__A);
+  return (__m256i)__builtin_elementwise_popcount((__v8su)__A);
 }
 
 static __inline__ __m256i __DEFAULT_FN_ATTRS256

clang/lib/Headers/vecintrin.h

@@ -6477,42 +6477,42 @@ vec_cnttz(__vector unsigned long long __a) {
 
 static inline __ATTRS_o_ai __vector unsigned char
 vec_popcnt(__vector signed char __a) {
-  return __builtin_s390_vpopctb((__vector unsigned char)__a);
+  return __builtin_elementwise_popcount((__vector unsigned char)__a);
 }
 
 static inline __ATTRS_o_ai __vector unsigned char
 vec_popcnt(__vector unsigned char __a) {
-  return __builtin_s390_vpopctb(__a);
+  return __builtin_elementwise_popcount(__a);
 }
 
 static inline __ATTRS_o_ai __vector unsigned short
 vec_popcnt(__vector signed short __a) {
-  return __builtin_s390_vpopcth((__vector unsigned short)__a);
+  return __builtin_elementwise_popcount((__vector unsigned short)__a);
 }
 
 static inline __ATTRS_o_ai __vector unsigned short
 vec_popcnt(__vector unsigned short __a) {
-  return __builtin_s390_vpopcth(__a);
+  return __builtin_elementwise_popcount(__a);
 }
 
 static inline __ATTRS_o_ai __vector unsigned int
 vec_popcnt(__vector signed int __a) {
-  return __builtin_s390_vpopctf((__vector unsigned int)__a);
+  return __builtin_elementwise_popcount((__vector unsigned int)__a);
 }
 
 static inline __ATTRS_o_ai __vector unsigned int
 vec_popcnt(__vector unsigned int __a) {
-  return __builtin_s390_vpopctf(__a);
+  return __builtin_elementwise_popcount(__a);
 }
 
 static inline __ATTRS_o_ai __vector unsigned long long
 vec_popcnt(__vector signed long long __a) {
-  return __builtin_s390_vpopctg((__vector unsigned long long)__a);
+  return __builtin_elementwise_popcount((__vector unsigned long long)__a);
 }
 
 static inline __ATTRS_o_ai __vector unsigned long long
 vec_popcnt(__vector unsigned long long __a) {
-  return __builtin_s390_vpopctg(__a);
+  return __builtin_elementwise_popcount(__a);
 }
 
 /*-- vec_rl -----------------------------------------------------------------*/

clang/lib/Headers/wasm_simd128.h

@@ -957,7 +957,7 @@ static __inline__ uint32_t __DEFAULT_FN_ATTRS wasm_i8x16_bitmask(v128_t __a) {
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i8x16_popcnt(v128_t __a) {
-  return (v128_t)__builtin_wasm_popcnt_i8x16((__i8x16)__a);
+  return (v128_t)__builtin_elementwise_popcount((__i8x16)__a);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i8x16_shl(v128_t __a,

clang/test/CodeGen/SystemZ/builtins-systemz-vector.c

@@ -301,15 +301,6 @@ void test_integer(void) {
   vul = __builtin_s390_vmlof(vui, vui);
   // CHECK: call <2 x i64> @llvm.s390.vmlof(<4 x i32> %{{.*}}, <4 x i32> %{{.*}})
 
-  vuc = __builtin_s390_vpopctb(vuc);
-  // CHECK: call <16 x i8> @llvm.ctpop.v16i8(<16 x i8> %{{.*}})
-  vus = __builtin_s390_vpopcth(vus);
-  // CHECK: call <8 x i16> @llvm.ctpop.v8i16(<8 x i16> %{{.*}})
-  vui = __builtin_s390_vpopctf(vui);
-  // CHECK: call <4 x i32> @llvm.ctpop.v4i32(<4 x i32> %{{.*}})
-  vul = __builtin_s390_vpopctg(vul);
-  // CHECK: call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %{{.*}})
-
   si128 = __builtin_s390_vsq(si128, si128);
   // CHECK: call i128 @llvm.s390.vsq(i128 %{{.*}}, i128 %{{.*}})
   ui128 = __builtin_s390_vsbiq(ui128, ui128, ui128);

clang/test/CodeGen/X86/avx512bitalg-builtins.c

@@ -11,13 +11,13 @@ __m512i test_mm512_popcnt_epi16(__m512i __A) {
 __m512i test_mm512_mask_popcnt_epi16(__m512i __A, __mmask32 __U, __m512i __B) {
   // CHECK-LABEL: @test_mm512_mask_popcnt_epi16
   // CHECK: @llvm.ctpop.v32i16
-  // CHECK: select <32 x i1> %{{[0-9]+}}, <32 x i16> %{{[0-9]+}}, <32 x i16> {{.*}}
+  // CHECK: select <32 x i1> %{{[0-9]+}}, <32 x i16> %{{.*}}, <32 x i16> %{{.*}}
   return _mm512_mask_popcnt_epi16(__A, __U, __B);
 }
 __m512i test_mm512_maskz_popcnt_epi16(__mmask32 __U, __m512i __B) {
   // CHECK-LABEL: @test_mm512_maskz_popcnt_epi16
   // CHECK: @llvm.ctpop.v32i16
-  // CHECK: select <32 x i1> %{{[0-9]+}}, <32 x i16> %{{[0-9]+}}, <32 x i16> {{.*}}
+  // CHECK: select <32 x i1> %{{[0-9]+}}, <32 x i16> %{{.*}}, <32 x i16> %{{.*}}
   return _mm512_maskz_popcnt_epi16(__U, __B);
 }
 
@@ -30,13 +30,13 @@ __m512i test_mm512_popcnt_epi8(__m512i __A) {
 __m512i test_mm512_mask_popcnt_epi8(__m512i __A, __mmask64 __U, __m512i __B) {
   // CHECK-LABEL: @test_mm512_mask_popcnt_epi8
   // CHECK: @llvm.ctpop.v64i8
-  // CHECK: select <64 x i1> %{{[0-9]+}}, <64 x i8> %{{[0-9]+}}, <64 x i8> {{.*}}
+  // CHECK: select <64 x i1> %{{[0-9]+}}, <64 x i8> %{{.*}}, <64 x i8> %{{.*}}
   return _mm512_mask_popcnt_epi8(__A, __U, __B);
 }
 __m512i test_mm512_maskz_popcnt_epi8(__mmask64 __U, __m512i __B) {
   // CHECK-LABEL: @test_mm512_maskz_popcnt_epi8
   // CHECK: @llvm.ctpop.v64i8
-  // CHECK: select <64 x i1> %{{[0-9]+}}, <64 x i8> %{{[0-9]+}}, <64 x i8> {{.*}}
+  // CHECK: select <64 x i1> %{{[0-9]+}}, <64 x i8> %{{.*}}, <64 x i8> %{{.*}}
   return _mm512_maskz_popcnt_epi8(__U, __B);
 }