[clang][x86] Add constexpr support for BMI/TBM BEXTR intrinsics

clang/include/clang/Basic/BuiltinsX86.def

@@ -555,7 +555,7 @@ TARGET_BUILTIN(__builtin_ia32_lzcnt_u16, "UsUs", "nc", "lzcnt")
 TARGET_BUILTIN(__builtin_ia32_lzcnt_u32, "UiUi", "nc", "lzcnt")
 
 // BMI
-TARGET_BUILTIN(__builtin_ia32_bextr_u32, "UiUiUi", "nc", "bmi")
+TARGET_BUILTIN(__builtin_ia32_bextr_u32, "UiUiUi", "ncE", "bmi")
 TARGET_BUILTIN(__builtin_ia32_tzcnt_u16, "UsUs", "nc", "")
 TARGET_BUILTIN(__builtin_ia32_tzcnt_u32, "UiUi", "nc", "")
 
@@ -565,7 +565,7 @@ TARGET_BUILTIN(__builtin_ia32_pdep_si, "UiUiUi", "nc", "bmi2")
 TARGET_BUILTIN(__builtin_ia32_pext_si, "UiUiUi", "nc", "bmi2")
 
 // TBM
-TARGET_BUILTIN(__builtin_ia32_bextri_u32, "UiUiIUi", "nc", "tbm")
+TARGET_BUILTIN(__builtin_ia32_bextri_u32, "UiUiIUi", "ncE", "tbm")
 
 // LWP
 TARGET_BUILTIN(__builtin_ia32_llwpcb, "vv*", "n", "lwp")

clang/include/clang/Basic/BuiltinsX86_64.def

@@ -71,12 +71,12 @@ TARGET_BUILTIN(__builtin_ia32_subborrow_u64, "UcUcUOiUOiUOi*", "n", "")
 TARGET_BUILTIN(__builtin_ia32_rdrand64_step, "UiUOi*", "n", "rdrnd")
 TARGET_BUILTIN(__builtin_ia32_rdseed64_step, "UiUOi*", "n", "rdseed")
 TARGET_BUILTIN(__builtin_ia32_lzcnt_u64, "UOiUOi", "nc", "lzcnt")
-TARGET_BUILTIN(__builtin_ia32_bextr_u64, "UOiUOiUOi", "nc", "bmi")
+TARGET_BUILTIN(__builtin_ia32_bextr_u64, "UOiUOiUOi", "ncE", "bmi")
 TARGET_BUILTIN(__builtin_ia32_tzcnt_u64, "UOiUOi", "nc", "")
 TARGET_BUILTIN(__builtin_ia32_bzhi_di, "UOiUOiUOi", "nc", "bmi2")
 TARGET_BUILTIN(__builtin_ia32_pdep_di, "UOiUOiUOi", "nc", "bmi2")
 TARGET_BUILTIN(__builtin_ia32_pext_di, "UOiUOiUOi", "nc", "bmi2")
-TARGET_BUILTIN(__builtin_ia32_bextri_u64, "UOiUOiIUOi", "nc", "tbm")
+TARGET_BUILTIN(__builtin_ia32_bextri_u64, "UOiUOiIUOi", "ncE", "tbm")
 TARGET_BUILTIN(__builtin_ia32_lwpins64, "UcUOiUiIUi", "n", "lwp")
 TARGET_BUILTIN(__builtin_ia32_lwpval64, "vUOiUiIUi", "n", "lwp")
 TARGET_BUILTIN(__builtin_ia32_vcvtsd2si64, "OiV2dIi", "ncV:128:", "avx512f")

clang/lib/AST/ExprConstant.cpp

@@ -52,6 +52,7 @@
 #include "clang/AST/TypeLoc.h"
 #include "clang/Basic/Builtins.h"
 #include "clang/Basic/DiagnosticSema.h"
+#include "clang/Basic/TargetBuiltins.h"
 #include "clang/Basic/TargetInfo.h"
 #include "llvm/ADT/APFixedPoint.h"
 #include "llvm/ADT/SmallBitVector.h"
@@ -13371,6 +13372,29 @@ bool IntExprEvaluator::VisitBuiltinCallExpr(const CallExpr *E,
       return false;
     return Success(DidOverflow, E);
   }
+
+  case clang::X86::BI__builtin_ia32_bextr_u32:
+  case clang::X86::BI__builtin_ia32_bextr_u64:
+  case clang::X86::BI__builtin_ia32_bextri_u32:
+  case clang::X86::BI__builtin_ia32_bextri_u64: {
+    APSInt Val, Idx;
+    if (!EvaluateInteger(E->getArg(0), Val, Info) ||
+        !EvaluateInteger(E->getArg(1), Idx, Info))
+      return false;
+
+    unsigned BitWidth = Val.getBitWidth();
+    uint64_t Shift = Idx.extractBitsAsZExtValue(8, 0);
+    uint64_t Length = Idx.extractBitsAsZExtValue(8, 8);
+    Length = Length > BitWidth ? BitWidth : Length;
+
+    // Handle out of bounds cases.
+    if (Length == 0 || Shift >= BitWidth)
+      return Success(0, E);
+
+    uint64_t Result = Val.getZExtValue() >> Shift;
+    Result &= llvm::maskTrailingOnes<uint64_t>(Length);
+    return Success(Result, E);
+  }
   }
 }
 

clang/lib/Headers/bmiintrin.h

@@ -166,6 +166,12 @@ _mm_tzcnt_64(unsigned long long __X)
 /* Define the default attributes for the functions in this file. */
 #define __DEFAULT_FN_ATTRS __attribute__((__always_inline__, __nodebug__, __target__("bmi")))
 
+#if defined(__cplusplus) && (__cplusplus >= 201103L)
+#define __DEFAULT_FN_ATTRS_CONSTEXPR __DEFAULT_FN_ATTRS constexpr
+#else
+#define __DEFAULT_FN_ATTRS_CONSTEXPR __DEFAULT_FN_ATTRS
+#endif
+
 /// Performs a bitwise AND of the second operand with the one's
 ///    complement of the first operand.
 ///
@@ -223,9 +229,8 @@ __andn_u32(unsigned int __X, unsigned int __Y)
 /// \returns An unsigned integer whose least significant bits contain the
 ///    extracted bits.
 /// \see _bextr_u32
-static __inline__ unsigned int __DEFAULT_FN_ATTRS
-__bextr_u32(unsigned int __X, unsigned int __Y)
-{
+static __inline__ unsigned int __DEFAULT_FN_ATTRS_CONSTEXPR
+__bextr_u32(unsigned int __X, unsigned int __Y) {
   return __builtin_ia32_bextr_u32(__X, __Y);
 }
 
@@ -248,10 +253,9 @@ __bextr_u32(unsigned int __X, unsigned int __Y)
 /// \returns An unsigned integer whose least significant bits contain the
 ///    extracted bits.
 /// \see __bextr_u32
-static __inline__ unsigned int __DEFAULT_FN_ATTRS
-_bextr_u32(unsigned int __X, unsigned int __Y, unsigned int __Z)
-{
-  return __builtin_ia32_bextr_u32 (__X, ((__Y & 0xff) | ((__Z & 0xff) << 8)));
+static __inline__ unsigned int __DEFAULT_FN_ATTRS_CONSTEXPR
+_bextr_u32(unsigned int __X, unsigned int __Y, unsigned int __Z) {
+  return __builtin_ia32_bextr_u32(__X, ((__Y & 0xff) | ((__Z & 0xff) << 8)));
 }
 
 /* Intel-specified, single-leading-underscore version of BEXTR2 */
@@ -271,7 +275,7 @@ _bextr_u32(unsigned int __X, unsigned int __Y, unsigned int __Z)
 /// \returns An unsigned integer whose least significant bits contain the
 ///    extracted bits.
 /// \see __bextr_u32
-static __inline__ unsigned int __DEFAULT_FN_ATTRS
+static __inline__ unsigned int __DEFAULT_FN_ATTRS_CONSTEXPR
 _bextr2_u32(unsigned int __X, unsigned int __Y) {
   return __builtin_ia32_bextr_u32(__X, __Y);
 }
@@ -444,9 +448,8 @@ __andn_u64 (unsigned long long __X, unsigned long long __Y)
 /// \returns An unsigned 64-bit integer whose least significant bits contain the
 ///    extracted bits.
 /// \see _bextr_u64
-static __inline__ unsigned long long __DEFAULT_FN_ATTRS
-__bextr_u64(unsigned long long __X, unsigned long long __Y)
-{
+static __inline__ unsigned long long __DEFAULT_FN_ATTRS_CONSTEXPR
+__bextr_u64(unsigned long long __X, unsigned long long __Y) {
   return __builtin_ia32_bextr_u64(__X, __Y);
 }
 
@@ -469,10 +472,9 @@ __bextr_u64(unsigned long long __X, unsigned long long __Y)
 /// \returns An unsigned 64-bit integer whose least significant bits contain the
 ///    extracted bits.
 /// \see __bextr_u64
-static __inline__ unsigned long long __DEFAULT_FN_ATTRS
-_bextr_u64(unsigned long long __X, unsigned int __Y, unsigned int __Z)
-{
-  return __builtin_ia32_bextr_u64 (__X, ((__Y & 0xff) | ((__Z & 0xff) << 8)));
+static __inline__ unsigned long long __DEFAULT_FN_ATTRS_CONSTEXPR
+_bextr_u64(unsigned long long __X, unsigned int __Y, unsigned int __Z) {
+  return __builtin_ia32_bextr_u64(__X, ((__Y & 0xff) | ((__Z & 0xff) << 8)));
 }
 
 /* Intel-specified, single-leading-underscore version of BEXTR2 */
@@ -492,7 +494,7 @@ _bextr_u64(unsigned long long __X, unsigned int __Y, unsigned int __Z)
 /// \returns An unsigned 64-bit integer whose least significant bits contain the
 ///    extracted bits.
 /// \see __bextr_u64
-static __inline__ unsigned long long __DEFAULT_FN_ATTRS
+static __inline__ unsigned long long __DEFAULT_FN_ATTRS_CONSTEXPR
 _bextr2_u64(unsigned long long __X, unsigned long long __Y) {
   return __builtin_ia32_bextr_u64(__X, __Y);
 }

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

@@ -1,5 +1,7 @@
-// RUN: %clang_cc1 -ffreestanding %s -triple=x86_64-apple-darwin -target-feature +bmi -emit-llvm -o - -Wall -Werror | FileCheck %s --check-prefixes=CHECK,TZCNT
-// RUN: %clang_cc1 -fms-extensions -fms-compatibility -fms-compatibility-version=17.00 -ffreestanding %s -triple=x86_64-windows-msvc -emit-llvm -o - -Wall -Werror -DTEST_TZCNT | FileCheck %s --check-prefix=TZCNT
+// RUN: %clang_cc1 -x c -ffreestanding %s -triple=x86_64-apple-darwin -target-feature +bmi -emit-llvm -o - -Wall -Werror | FileCheck %s --check-prefixes=CHECK,TZCNT
+// RUN: %clang_cc1 -x c -fms-extensions -fms-compatibility -fms-compatibility-version=17.00 -ffreestanding %s -triple=x86_64-windows-msvc -emit-llvm -o - -Wall -Werror -DTEST_TZCNT | FileCheck %s --check-prefix=TZCNT
+// RUN: %clang_cc1 -x c++ -std=c++11 -ffreestanding %s -triple=x86_64-apple-darwin -target-feature +bmi -emit-llvm -o - -Wall -Werror | FileCheck %s --check-prefixes=CHECK,TZCNT
+// RUN: %clang_cc1 -x c++ -std=c++11 -fms-extensions -fms-compatibility -fms-compatibility-version=17.00 -ffreestanding %s -triple=x86_64-windows-msvc -emit-llvm -o - -Wall -Werror -DTEST_TZCNT | FileCheck %s --check-prefix=TZCNT
 
 
 #include <immintrin.h>
@@ -232,3 +234,32 @@ unsigned long long test_blsr_u64(unsigned long long __X) {
 #endif
 
 #endif // !defined(TEST_TZCNT)
+
+// Test constexpr handling.
+#if defined(__cplusplus) && (__cplusplus >= 201103L)
+char bextr32_0[__bextr_u32(0x00000000, 0x00000000) == 0x00000000 ? 1 : -1];
+char bextr32_1[__bextr_u32(0x000003F0, 0xFFFF1004) == 0x0000003F ? 1 : -1];
+char bextr32_2[__bextr_u32(0x000003F0, 0xFFFF3008) == 0x00000003 ? 1 : -1];
+
+char bextr32_3[_bextr2_u32(0x00000000, 0x00000000) == 0x00000000 ? 1 : -1];
+char bextr32_4[_bextr2_u32(0x000003F0, 0xFFFF1004) == 0x0000003F ? 1 : -1];
+char bextr32_5[_bextr2_u32(0x000003F0, 0xFFFF3008) == 0x00000003 ? 1 : -1];
+
+char bextr32_6[_bextr_u32(0x00000000, 0x00000000, 0x00000000) == 0x00000000 ? 1 : -1];
+char bextr32_7[_bextr_u32(0x000003F0, 0xFFFFFF04, 0xFFFFFF10) == 0x0000003F ? 1 : -1];
+char bextr32_8[_bextr_u32(0x000003F0, 0xFFFFFF08, 0xFFFFFF30) == 0x00000003 ? 1 : -1];
+
+#ifdef __x86_64__
+char bextr64_0[__bextr_u64(0x0000000000000000ULL, 0x0000000000000000ULL) == 0x0000000000000000ULL ? 1 : -1];
+char bextr64_1[__bextr_u64(0xF000000000000001ULL, 0x0000000000004001ULL) == 0x7800000000000000ULL ? 1 : -1];
+char bextr64_2[__bextr_u64(0xF000000000000001ULL, 0xFFFFFFFFFFFF1001ULL) == 0x0000000000000000ULL ? 1 : -1];
+
+char bextr64_3[_bextr2_u64(0x0000000000000000ULL, 0x0000000000000000ULL) == 0x0000000000000000ULL ? 1 : -1];
+char bextr64_4[_bextr2_u64(0xF000000000000001ULL, 0x0000000000004001ULL) == 0x7800000000000000ULL ? 1 : -1];
+char bextr64_5[_bextr2_u64(0xF000000000000001ULL, 0xFFFFFFFFFFFF1001ULL) == 0x0000000000000000ULL ? 1 : -1];
+
+char bextr64_6[_bextr_u64(0x0000000000000000ULL, 0x0000000000000000ULL, 0x0000000000000000ULL) == 0x0000000000000000ULL ? 1 : -1];
+char bextr64_7[_bextr_u64(0xF000000000000001ULL, 0x0000000000000001ULL, 0x0000000000000040ULL) == 0x7800000000000000ULL ? 1 : -1];
+char bextr64_8[_bextr_u64(0xF000000000000001ULL, 0xFFFFFFFFFFFFFF01ULL, 0xFFFFFFFFFFFFFF10ULL) == 0x0000000000000000ULL ? 1 : -1];
+#endif
+#endif

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

@@ -1,4 +1,5 @@
-// RUN: %clang_cc1 -ffreestanding %s -triple=x86_64-unknown-unknown -target-feature +tbm -emit-llvm -o - | FileCheck %s
+// RUN: %clang_cc1 -x c -ffreestanding %s -triple=x86_64-unknown-unknown -target-feature +tbm -emit-llvm -o - | FileCheck %s
+// RUN: %clang_cc1 -x c++ -std=c++11 -ffreestanding %s -triple=x86_64-unknown-unknown -target-feature +tbm -emit-llvm -o - | FileCheck %s
 
 #include <x86intrin.h>
 
@@ -177,3 +178,16 @@ unsigned long long test__tzmsk_u64(unsigned long long a) {
   return __tzmsk_u64(a);
 }
 #endif
+
+// Test constexpr handling.
+#if defined(__cplusplus) && (__cplusplus >= 201103L)
+char bextri32_0[__bextri_u32(0x00000000, 0x00000000) == 0x00000000 ? 1 : -1];
+char bextri32_1[__bextri_u32(0x000003F0, 0xFFFF1004) == 0x0000003F ? 1 : -1];
+char bextri32_2[__bextri_u32(0x000003F0, 0xFFFF3008) == 0x00000003 ? 1 : -1];
+
+#ifdef __x86_64__
+char bextri64_0[__bextri_u64(0x0000000000000000ULL, 0x0000000000000000ULL) == 0x0000000000000000ULL ? 1 : -1];
+char bextri64_1[__bextri_u64(0xF000000000000001ULL, 0x0000000000004001ULL) == 0x7800000000000000ULL ? 1 : -1];
+char bextri64_2[__bextri_u64(0xF000000000000001ULL, 0xFFFFFFFFFFFF1001ULL) == 0x0000000000000000ULL ? 1 : -1];
+#endif
+#endif