[ARM] Add __ARM_FEATURE_DOTPROD pre-defined macro

[olista01]

Summary

This adds a pre-defined macro to test if the compiler has support for the v8.2-A dot rpoduct intrinsics in AArch32 mode.

The AAcrh64 equivalent has already been added by rL330229.

The ACLE spec which describes this macro hasn't been published yet, but this is based on the final internal draft, and GCC has already implemented this.

[SjoerdMeijer]

Looks like a straight forward fix/addition to me.

lib/Basic/Targets/ARM.cpp

737

Nit: do we a comment here too that this is Armv8.2-A?

lib/Basic/Targets/ARM.h

class LLVM_LIBRARY_VISIBILITY ARMTargetInfo : public TargetInfo {
   // Initialized via features.
   unsigned SoftFloat : 1;
   unsigned SoftFloatABI : 1;
 
   unsigned CRC : 1;
   unsigned Crypto : 1;
   unsigned DSP : 1;
   unsigned Unaligned : 1;
+  unsigned DotProd : 1;
 
   enum {
     LDREX_B = (1 << 0), /// byte (8-bit)
     LDREX_H = (1 << 1), /// half (16-bit)
     LDREX_W = (1 << 2), /// word (32-bit)
     LDREX_D = (1 << 3), /// double (64-bit)
   };
 

lib/Basic/Targets/ARM.cpp

bool ARMTargetInfo::handleTargetFeatures(std::vector<std::string> &Features,
                                          DiagnosticsEngine &Diags) {
   FPU = 0;
   CRC = 0;
   Crypto = 0;
   DSP = 0;
   Unaligned = 1;
   SoftFloat = SoftFloatABI = false;
   HWDiv = 0;
+  DotProd = 0;
 
   // This does not diagnose illegal cases like having both
   // "+vfpv2" and "+vfpv3" or having "+neon" and "+fp-only-sp".
   uint32_t HW_FP_remove = 0;
   for (const auto &Feature : Features) {
     if (Feature == "+soft-float") {
       SoftFloat = true;
     } else if (Feature == "+soft-float-abi") {
for (const auto &Feature : Features) {
     } else if (Feature == "+fp-only-sp") {
       HW_FP_remove |= HW_FP_DP;
     } else if (Feature == "+strict-align") {
       Unaligned = 0;
     } else if (Feature == "+fp16") {
       HW_FP |= HW_FP_HP;
     } else if (Feature == "+fullfp16") {
       HasLegalHalfType = true;
+    } else if (Feature == "+dotprod") {
+      DotProd = true;
     }
   }
   HW_FP &= ~HW_FP_remove;
 
   switch (ArchVersion) {
   case 6:
     if (ArchProfile == llvm::ARM::ProfileKind::M)
       LDREX = 0;
void ARMTargetInfo::getTargetDefines(const LangOptions &Opts,
   // Armv8.2-A FP16 vector intrinsic
   if ((FPU & NeonFPU) && HasLegalHalfType)
     Builder.defineMacro("__ARM_FEATURE_FP16_VECTOR_ARITHMETIC", "1");
 
   // Armv8.2-A FP16 scalar intrinsics
   if (HasLegalHalfType)
     Builder.defineMacro("__ARM_FEATURE_FP16_SCALAR_ARITHMETIC", "1");
 
+  // Armv8.2-A dot product intrinsics
+  if (DotProd)
+    Builder.defineMacro("__ARM_FEATURE_DOTPROD", "1");
 
   switch (ArchKind) {
   default:
     break;
   case llvm::ARM::ArchKind::ARMV8_1A:
     getTargetDefinesARMV81A(Opts, Builder);
     break;
   case llvm::ARM::ArchKind::ARMV8_2A:

test/Preprocessor/arm-target-features.c

 // RUN: %clang -target armv8a-none-linux-gnu -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-V8A %s
 // CHECK-V8A: #define __ARMEL__ 1
 // CHECK-V8A: #define __ARM_ARCH 8
 // CHECK-V8A: #define __ARM_ARCH_8A__ 1
 // CHECK-V8A: #define __ARM_FEATURE_CRC32 1
 // CHECK-V8A: #define __ARM_FEATURE_DIRECTED_ROUNDING 1
 // CHECK-V8A: #define __ARM_FEATURE_NUMERIC_MAXMIN 1
 // CHECK-V8A-NOT: #define __ARM_FP 0x
+// CHECK-V8A-NOT: #define __ARM_FEATURE_DOTPROD
 
 // RUN: %clang -target armv8a-none-linux-gnueabi -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-V8A-ALLOW-FP-INSTR %s
 // RUN: %clang -target armv8a-none-linux-gnueabihf -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-V8A-ALLOW-FP-INSTR %s
 // CHECK-V8A-ALLOW-FP-INSTR: #define __ARMEL__ 1
 // CHECK-V8A-ALLOW-FP-INSTR: #define __ARM_ARCH 8
 // CHECK-V8A-ALLOW-FP-INSTR: #define __ARM_ARCH_8A__ 1
 // CHECK-V8A-ALLOW-FP-INSTR: #define __ARM_FEATURE_CRC32 1
 // CHECK-V8A-ALLOW-FP-INSTR: #define __ARM_FEATURE_DIRECTED_ROUNDING 1
 // CHECK-V8A-ALLOW-FP-INSTR: #define __ARM_FEATURE_NUMERIC_MAXMIN 1
 // CHECK-V8A-ALLOW-FP-INSTR: #define __ARM_FP 0xe
 // CHECK-V8A-ALLOW-FP-INSTR: #define __ARM_FP16_ARGS 1
 // CHECK-V8A-ALLOW-FP-INSTR: #define __ARM_FP16_FORMAT_IEEE 1
+// CHECK-V8A-ALLOW-FP-INSTR-V8A-NOT: #define __ARM_FEATURE_DOTPROD
 
 // RUN: %clang -target arm-none-linux-gnueabi -march=armv8.2a+fp16 -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-VECTOR-SCALAR %s
 // CHECK-FULLFP16-VECTOR-SCALAR: #define __ARM_FEATURE_FP16_SCALAR_ARITHMETIC 1
 // CHECK-FULLFP16-VECTOR-SCALAR: #define __ARM_FEATURE_FP16_VECTOR_ARITHMETIC 1
 // CHECK-FULLFP16-VECTOR-SCALAR: #define __ARM_FP 0xe
 // CHECK-FULLFP16-VECTOR-SCALAR: #define __ARM_FP16_FORMAT_IEEE 1
 
 // RUN: %clang -target arm-none-linux-gnueabi -march=armv8.2a+fp16 -mfpu=vfp4 -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-FULLFP16-SCALAR %s
 // CHECK-FULLFP16-SCALAR:       #define __ARM_FEATURE_FP16_SCALAR_ARITHMETIC 1
 // CHECK-FULLFP16-SCALAR-NOT:   #define __ARM_FEATURE_FP16_VECTOR_ARITHMETIC 1
 // CHECK-FULLFP16-SCALAR:       #define __ARM_FP 0xe
 // CHECK-FULLFP16-SCALAR:       #define __ARM_FP16_FORMAT_IEEE 1
+//
+// RUN: %clang -target arm-none-linux-gnueabi -march=armv8.2a+dotprod -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-DOTPROD %s
+// CHECK-DOTPROD: #define __ARM_FEATURE_DOTPROD 1
 
 // RUN: %clang -target armv8r-none-linux-gnu -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-V8R %s
 // CHECK-V8R: #define __ARMEL__ 1
 // CHECK-V8R: #define __ARM_ARCH 8
 // CHECK-V8R: #define __ARM_ARCH_8R__ 1
 // CHECK-V8R: #define __ARM_FEATURE_CRC32 1
 // CHECK-V8R: #define __ARM_FEATURE_DIRECTED_ROUNDING 1
 // CHECK-V8R: #define __ARM_FEATURE_NUMERIC_MAXMIN 1