[X86] Add CRC32 feature.

d8faf03 implemented general-regs-only for X86 by disabling all features
with vector instructions. But the CRC32 instruction in SSE4.2 ISA, which uses
only GPRs, also becomes unavailable. This patch adds a CRC32 feature for this
instruction and allows it to be used with general-regs-only.

Reviewed By: pengfei

Differential Revision: https://reviews.llvm.org/D105462

Author: tianqingw

clang/docs/ClangCommandLineReference.rst

@@ -3590,6 +3590,8 @@ X86
 
 .. option:: -mclzero, -mno-clzero
 
+.. option:: -mcrc32, -mno-crc32
+
 .. option:: -mcx16, -mno-cx16
 
 .. option:: -menqcmd, -mno-enqcmd

clang/include/clang/Basic/BuiltinsX86.def

@@ -421,9 +421,9 @@ TARGET_BUILTIN(__builtin_ia32_pcmpestrio128, "iV16ciV16ciIc","ncV:128:", "sse4.2
 TARGET_BUILTIN(__builtin_ia32_pcmpestris128, "iV16ciV16ciIc","ncV:128:", "sse4.2")
 TARGET_BUILTIN(__builtin_ia32_pcmpestriz128, "iV16ciV16ciIc","ncV:128:", "sse4.2")
 
-TARGET_BUILTIN(__builtin_ia32_crc32qi, "UiUiUc", "nc", "sse4.2")
-TARGET_BUILTIN(__builtin_ia32_crc32hi, "UiUiUs", "nc", "sse4.2")
-TARGET_BUILTIN(__builtin_ia32_crc32si, "UiUiUi", "nc", "sse4.2")
+TARGET_BUILTIN(__builtin_ia32_crc32qi, "UiUiUc", "nc", "crc32")
+TARGET_BUILTIN(__builtin_ia32_crc32hi, "UiUiUs", "nc", "crc32")
+TARGET_BUILTIN(__builtin_ia32_crc32si, "UiUiUi", "nc", "crc32")
 
 // SSE4a
 TARGET_BUILTIN(__builtin_ia32_extrqi, "V2OiV2OiIcIc", "ncV:128:", "sse4a")

clang/include/clang/Basic/BuiltinsX86_64.def

@@ -44,7 +44,7 @@ TARGET_BUILTIN(__builtin_ia32_cvttsd2si64, "OiV2d", "ncV:128:", "sse2")
 TARGET_BUILTIN(__builtin_ia32_movnti64, "vOi*Oi", "n", "sse2")
 TARGET_BUILTIN(__builtin_ia32_vec_ext_v2di, "OiV2OiIi", "ncV:128:", "sse2")
 TARGET_BUILTIN(__builtin_ia32_vec_set_v2di, "V2OiV2OiOiIi", "ncV:128:", "sse4.1")
-TARGET_BUILTIN(__builtin_ia32_crc32di, "UOiUOiUOi", "nc", "sse4.2")
+TARGET_BUILTIN(__builtin_ia32_crc32di, "UOiUOiUOi", "nc", "crc32")
 TARGET_BUILTIN(__builtin_ia32_vec_ext_v4di, "OiV4OiIi", "ncV:256:", "avx")
 TARGET_BUILTIN(__builtin_ia32_vec_set_v4di, "V4OiV4OiOiIi", "ncV:256:", "avx")
 TARGET_BUILTIN(__builtin_ia32_rdfsbase32, "Ui", "n", "fsgsbase")

clang/include/clang/Driver/Options.td

@@ -4206,6 +4206,8 @@ def mwbnoinvd : Flag<["-"], "mwbnoinvd">, Group<m_x86_Features_Group>;
 def mno_wbnoinvd : Flag<["-"], "mno-wbnoinvd">, Group<m_x86_Features_Group>;
 def mclzero : Flag<["-"], "mclzero">, Group<m_x86_Features_Group>;
 def mno_clzero : Flag<["-"], "mno-clzero">, Group<m_x86_Features_Group>;
+def mcrc32 : Flag<["-"], "mcrc32">, Group<m_x86_Features_Group>;
+def mno_crc32 : Flag<["-"], "mno-crc32">, Group<m_x86_Features_Group>;
 def mcx16 : Flag<["-"], "mcx16">, Group<m_x86_Features_Group>;
 def mno_cx16 : Flag<["-"], "mno-cx16">, Group<m_x86_Features_Group>;
 def menqcmd : Flag<["-"], "menqcmd">, Group<m_x86_Features_Group>;

clang/lib/Basic/Targets/X86.cpp

@@ -155,6 +155,12 @@ bool X86TargetInfo::initFeatureMap(
       llvm::find(UpdatedFeaturesVec, "-xsave") == UpdatedFeaturesVec.end())
     Features["xsave"] = true;
 
+  // Enable CRC32 if SSE4.2 is enabled and CRC32 is not explicitly disabled.
+  I = Features.find("sse4.2");
+  if (I != Features.end() && I->getValue() &&
+      llvm::find(UpdatedFeaturesVec, "-crc32") == UpdatedFeaturesVec.end())
+    Features["crc32"] = true;
+
   return true;
 }
 
@@ -330,6 +336,8 @@ bool X86TargetInfo::handleTargetFeatures(std::vector<std::string> &Features,
       HasTSXLDTRK = true;
     } else if (Feature == "+uintr") {
       HasUINTR = true;
+    } else if (Feature == "+crc32") {
+      HasCRC32 = true;
     }
 
     X86SSEEnum Level = llvm::StringSwitch<X86SSEEnum>(Feature)
@@ -758,6 +766,8 @@ void X86TargetInfo::getTargetDefines(const LangOptions &Opts,
     Builder.defineMacro("__TSXLDTRK__");
   if (HasUINTR)
     Builder.defineMacro("__UINTR__");
+  if (HasCRC32)
+    Builder.defineMacro("__CRC32__");
 
   // Each case falls through to the previous one here.
   switch (SSELevel) {
@@ -878,6 +888,7 @@ bool X86TargetInfo::isValidFeatureName(StringRef Name) const {
       .Case("clflushopt", true)
       .Case("clwb", true)
       .Case("clzero", true)
+      .Case("crc32", true)
       .Case("cx16", true)
       .Case("enqcmd", true)
       .Case("f16c", true)
@@ -970,6 +981,7 @@ bool X86TargetInfo::hasFeature(StringRef Feature) const {
       .Case("clflushopt", HasCLFLUSHOPT)
       .Case("clwb", HasCLWB)
       .Case("clzero", HasCLZERO)
+      .Case("crc32", HasCRC32)
       .Case("cx8", HasCX8)
       .Case("cx16", HasCX16)
       .Case("enqcmd", HasENQCMD)

clang/lib/Basic/Targets/X86.h

@@ -143,6 +143,7 @@ class LLVM_LIBRARY_VISIBILITY X86TargetInfo : public TargetInfo {
   bool HasSERIALIZE = false;
   bool HasTSXLDTRK = false;
   bool HasUINTR = false;
+  bool HasCRC32 = false;
 
 protected:
   llvm::X86::CPUKind CPU = llvm::X86::CK_None;

clang/lib/Headers/CMakeLists.txt

@@ -58,6 +58,7 @@ set(files
   cet.h
   cldemoteintrin.h
   clzerointrin.h
+  crc32intrin.h
   cpuid.h
   clflushoptintrin.h
   clwbintrin.h

clang/lib/Headers/crc32intrin.h

@@ -0,0 +1,100 @@
+/*===---- crc32intrin.h - SSE4.2 Accumulate CRC32 intrinsics ---------------===
+ *
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+ *
+ *===-----------------------------------------------------------------------===
+ */
+
+#ifndef __CRC32INTRIN_H
+#define __CRC32INTRIN_H
+
+#define __DEFAULT_FN_ATTRS                                                     \
+  __attribute__((__always_inline__, __nodebug__, __target__("crc32")))
+
+/// Adds the unsigned integer operand to the CRC-32C checksum of the
+///    unsigned char operand.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> CRC32B </c> instruction.
+///
+/// \param __C
+///    An unsigned integer operand to add to the CRC-32C checksum of operand
+///    \a  __D.
+/// \param __D
+///    An unsigned 8-bit integer operand used to compute the CRC-32C checksum.
+/// \returns The result of adding operand \a __C to the CRC-32C checksum of
+///    operand \a __D.
+static __inline__ unsigned int __DEFAULT_FN_ATTRS
+_mm_crc32_u8(unsigned int __C, unsigned char __D)
+{
+  return __builtin_ia32_crc32qi(__C, __D);
+}
+
+/// Adds the unsigned integer operand to the CRC-32C checksum of the
+///    unsigned short operand.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> CRC32W </c> instruction.
+///
+/// \param __C
+///    An unsigned integer operand to add to the CRC-32C checksum of operand
+///    \a __D.
+/// \param __D
+///    An unsigned 16-bit integer operand used to compute the CRC-32C checksum.
+/// \returns The result of adding operand \a __C to the CRC-32C checksum of
+///    operand \a __D.
+static __inline__ unsigned int __DEFAULT_FN_ATTRS
+_mm_crc32_u16(unsigned int __C, unsigned short __D)
+{
+  return __builtin_ia32_crc32hi(__C, __D);
+}
+
+/// Adds the first unsigned integer operand to the CRC-32C checksum of
+///    the second unsigned integer operand.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> CRC32L </c> instruction.
+///
+/// \param __C
+///    An unsigned integer operand to add to the CRC-32C checksum of operand
+///    \a __D.
+/// \param __D
+///    An unsigned 32-bit integer operand used to compute the CRC-32C checksum.
+/// \returns The result of adding operand \a __C to the CRC-32C checksum of
+///    operand \a __D.
+static __inline__ unsigned int __DEFAULT_FN_ATTRS
+_mm_crc32_u32(unsigned int __C, unsigned int __D)
+{
+  return __builtin_ia32_crc32si(__C, __D);
+}
+
+#ifdef __x86_64__
+/// Adds the unsigned integer operand to the CRC-32C checksum of the
+///    unsigned 64-bit integer operand.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> CRC32Q </c> instruction.
+///
+/// \param __C
+///    An unsigned integer operand to add to the CRC-32C checksum of operand
+///    \a __D.
+/// \param __D
+///    An unsigned 64-bit integer operand used to compute the CRC-32C checksum.
+/// \returns The result of adding operand \a __C to the CRC-32C checksum of
+///    operand \a __D.
+static __inline__ unsigned long long __DEFAULT_FN_ATTRS
+_mm_crc32_u64(unsigned long long __C, unsigned long long __D)
+{
+  return __builtin_ia32_crc32di(__C, __D);
+}
+#endif /* __x86_64__ */
+
+#undef __DEFAULT_FN_ATTRS
+
+#endif /* __CRC32INTRIN_H */

clang/lib/Headers/ia32intrin.h

@@ -16,7 +16,7 @@
 
 /* Define the default attributes for the functions in this file. */
 #define __DEFAULT_FN_ATTRS __attribute__((__always_inline__, __nodebug__))
-#define __DEFAULT_FN_ATTRS_SSE42 __attribute__((__always_inline__, __nodebug__, __target__("sse4.2")))
+#define __DEFAULT_FN_ATTRS_CRC32 __attribute__((__always_inline__, __nodebug__, __target__("crc32")))
 
 #if defined(__cplusplus) && (__cplusplus >= 201103L)
 #define __DEFAULT_FN_ATTRS_CAST __attribute__((__always_inline__)) constexpr
@@ -282,7 +282,7 @@ _castu64_f64(unsigned long long __A) {
  *  \returns The result of adding operand \a __C to the CRC-32C checksum of
  *     operand \a __D.
  */
-static __inline__ unsigned int __DEFAULT_FN_ATTRS_SSE42
+static __inline__ unsigned int __DEFAULT_FN_ATTRS_CRC32
 __crc32b(unsigned int __C, unsigned char __D)
 {
   return __builtin_ia32_crc32qi(__C, __D);
@@ -303,7 +303,7 @@ __crc32b(unsigned int __C, unsigned char __D)
  *  \returns The result of adding operand \a __C to the CRC-32C checksum of
  *     operand \a __D.
  */
-static __inline__ unsigned int __DEFAULT_FN_ATTRS_SSE42
+static __inline__ unsigned int __DEFAULT_FN_ATTRS_CRC32
 __crc32w(unsigned int __C, unsigned short __D)
 {
   return __builtin_ia32_crc32hi(__C, __D);
@@ -324,7 +324,7 @@ __crc32w(unsigned int __C, unsigned short __D)
  *  \returns The result of adding operand \a __C to the CRC-32C checksum of
  *     operand \a __D.
  */
-static __inline__ unsigned int __DEFAULT_FN_ATTRS_SSE42
+static __inline__ unsigned int __DEFAULT_FN_ATTRS_CRC32
 __crc32d(unsigned int __C, unsigned int __D)
 {
   return __builtin_ia32_crc32si(__C, __D);
@@ -346,7 +346,7 @@ __crc32d(unsigned int __C, unsigned int __D)
  *  \returns The result of adding operand \a __C to the CRC-32C checksum of
  *     operand \a __D.
  */
-static __inline__ unsigned long long __DEFAULT_FN_ATTRS_SSE42
+static __inline__ unsigned long long __DEFAULT_FN_ATTRS_CRC32
 __crc32q(unsigned long long __C, unsigned long long __D)
 {
   return __builtin_ia32_crc32di(__C, __D);
@@ -435,7 +435,7 @@ __rorq(unsigned long long __X, int __C) {
 
 #undef __DEFAULT_FN_ATTRS
 #undef __DEFAULT_FN_ATTRS_CAST
-#undef __DEFAULT_FN_ATTRS_SSE42
+#undef __DEFAULT_FN_ATTRS_CRC32
 #undef __DEFAULT_FN_ATTRS_CONSTEXPR
 
 #endif /* __IA32INTRIN_H */

clang/lib/Headers/smmintrin.h

@@ -2338,91 +2338,10 @@ _mm_cmpgt_epi64(__m128i __V1, __m128i __V2)
   return (__m128i)((__v2di)__V1 > (__v2di)__V2);
 }
 
-/* SSE4.2 Accumulate CRC32.  */
-/// Adds the unsigned integer operand to the CRC-32C checksum of the
-///    unsigned char operand.
-///
-/// \headerfile <x86intrin.h>
-///
-/// This intrinsic corresponds to the <c> CRC32B </c> instruction.
-///
-/// \param __C
-///    An unsigned integer operand to add to the CRC-32C checksum of operand
-///    \a  __D.
-/// \param __D
-///    An unsigned 8-bit integer operand used to compute the CRC-32C checksum.
-/// \returns The result of adding operand \a __C to the CRC-32C checksum of
-///    operand \a __D.
-static __inline__ unsigned int __DEFAULT_FN_ATTRS
-_mm_crc32_u8(unsigned int __C, unsigned char __D)
-{
-  return __builtin_ia32_crc32qi(__C, __D);
-}
-
-/// Adds the unsigned integer operand to the CRC-32C checksum of the
-///    unsigned short operand.
-///
-/// \headerfile <x86intrin.h>
-///
-/// This intrinsic corresponds to the <c> CRC32W </c> instruction.
-///
-/// \param __C
-///    An unsigned integer operand to add to the CRC-32C checksum of operand
-///    \a __D.
-/// \param __D
-///    An unsigned 16-bit integer operand used to compute the CRC-32C checksum.
-/// \returns The result of adding operand \a __C to the CRC-32C checksum of
-///    operand \a __D.
-static __inline__ unsigned int __DEFAULT_FN_ATTRS
-_mm_crc32_u16(unsigned int __C, unsigned short __D)
-{
-  return __builtin_ia32_crc32hi(__C, __D);
-}
-
-/// Adds the first unsigned integer operand to the CRC-32C checksum of
-///    the second unsigned integer operand.
-///
-/// \headerfile <x86intrin.h>
-///
-/// This intrinsic corresponds to the <c> CRC32L </c> instruction.
-///
-/// \param __C
-///    An unsigned integer operand to add to the CRC-32C checksum of operand
-///    \a __D.
-/// \param __D
-///    An unsigned 32-bit integer operand used to compute the CRC-32C checksum.
-/// \returns The result of adding operand \a __C to the CRC-32C checksum of
-///    operand \a __D.
-static __inline__ unsigned int __DEFAULT_FN_ATTRS
-_mm_crc32_u32(unsigned int __C, unsigned int __D)
-{
-  return __builtin_ia32_crc32si(__C, __D);
-}
-
-#ifdef __x86_64__
-/// Adds the unsigned integer operand to the CRC-32C checksum of the
-///    unsigned 64-bit integer operand.
-///
-/// \headerfile <x86intrin.h>
-///
-/// This intrinsic corresponds to the <c> CRC32Q </c> instruction.
-///
-/// \param __C
-///    An unsigned integer operand to add to the CRC-32C checksum of operand
-///    \a __D.
-/// \param __D
-///    An unsigned 64-bit integer operand used to compute the CRC-32C checksum.
-/// \returns The result of adding operand \a __C to the CRC-32C checksum of
-///    operand \a __D.
-static __inline__ unsigned long long __DEFAULT_FN_ATTRS
-_mm_crc32_u64(unsigned long long __C, unsigned long long __D)
-{
-  return __builtin_ia32_crc32di(__C, __D);
-}
-#endif /* __x86_64__ */
-
 #undef __DEFAULT_FN_ATTRS
 
 #include <popcntintrin.h>
 
+#include <crc32intrin.h>
+
 #endif /* __SMMINTRIN_H */

clang/lib/Headers/x86gprintrin.h

@@ -20,6 +20,11 @@
 #include <uintrintrin.h>
 #endif
 
+#if !(defined(_MSC_VER) || defined(__SCE__)) || __has_feature(modules) ||      \
+    defined(__CRC32__)
+#include <crc32intrin.h>
+#endif
+
 #define __SSC_MARK(Tag)                                                        \
   __asm__ __volatile__("movl %%ebx, %%eax; movl %0, %%ebx; .byte 0x64, 0x67, " \
                        "0x90; movl %%eax, %%ebx;" ::"i"(Tag)                   \