[ARM][bfloat] Removing lowering of bfloat arguments and returns from Clang's CodeGen

[stuij]

Summary

As part of moving the argument lowering handling for bfloat arguments and
returns to the backend, this patch removes the code that was responsible for
handling the coercion of those arguments in Clang's Codegen.

[stuij]

adjust arm bfloat mangle tests for these changes

[stuij]

We only remove clang-side lowering for non-vector bfloat types.

[chill]

Pretty straightforward, LGTM. I'd suggest rewording the title (presumably commit message summary) into something like "Do not coerce bfloat arguments and returns to integers", as we're obviously still lowering C and C++ to LLVM LR.§§

clang/lib/CodeGen/TargetInfo.cpp

bool IsAAPCS_VFP =
       !isVariadic && isEffectivelyAAPCS_VFP(functionCallConv, /* AAPCS16 */ false);
 
   Ty = useFirstFieldIfTransparentUnion(Ty);
 
   // Handle illegal vector types here.
   if (isIllegalVectorType(Ty))
     return coerceIllegalVector(Ty);
 
-  // __bf16 gets passed using the bfloat IR type, or using i32 but
-  // with the top 16 bits unspecified.
-  if (Ty->isBFloat16Type() && IsFloatABISoftFP) {
-    llvm::Type *ResType = llvm::Type::getInt32Ty(getVMContext());
-    return ABIArgInfo::getDirect(ResType);
-  }
-
   if (!isAggregateTypeForABI(Ty)) {
     // Treat an enum type as its underlying type.
     if (const EnumType *EnumTy = Ty->getAs<EnumType>()) {
       Ty = EnumTy->getDecl()->getIntegerType();
     }
 
     if (const auto *EIT = Ty->getAs<ExtIntType>())
       if (EIT->getNumBits() > 64)
if (const VectorType *VT = RetTy->getAs<VectorType>()) {
     if ((!getTarget().hasLegalHalfType() &&
         (VT->getElementType()->isFloat16Type() ||
          VT->getElementType()->isHalfType())) ||
         (IsFloatABISoftFP &&
          VT->getElementType()->isBFloat16Type()))
       return coerceIllegalVector(RetTy);
   }
 
-  // if we're using the softfp float abi, __bf16 get returned as if it were an
-  // int but with the top 16 bits unspecified.
-  if (RetTy->isBFloat16Type()) {
-    llvm::Type *ResType = IsAAPCS_VFP ?
-      llvm::Type::getBFloatTy(getVMContext()) :
-      llvm::Type::getInt32Ty(getVMContext());
-    return ABIArgInfo::getDirect(ResType);
-  }
-
   if (!isAggregateTypeForABI(RetTy)) {
     // Treat an enum type as its underlying type.
     if (const EnumType *EnumTy = RetTy->getAs<EnumType>())
       RetTy = EnumTy->getDecl()->getIntegerType();
 
     if (const auto *EIT = RetTy->getAs<ExtIntType>())
       if (EIT->getNumBits() > 64)
         return getNaturalAlignIndirect(RetTy, /*ByVal=*/false);

clang/test/CodeGen/arm-bf16-params-returns.c

 // RUN: %clang_cc1 -triple armv8.6a-arm-none-eabi -target-abi aapcs -mfloat-abi hard -target-feature +bf16 -target-feature +neon -emit-llvm -O2 -o - %s | opt -S -mem2reg -sroa | FileCheck %s --check-prefix=CHECK32-HARD
-// RUN: %clang_cc1 -triple aarch64-arm-none-eabi -target-abi aapcs -mfloat-abi hard -target-feature +bf16 -target-feature +neon -emit-llvm -O2 -o - %s | opt -S -mem2reg -sroa | FileCheck %s --check-prefix=CHECK64-HARD
 // RUN: %clang_cc1 -triple armv8.6a-arm-none-eabi -target-abi aapcs -mfloat-abi softfp -target-feature +bf16 -target-feature +neon -emit-llvm -O2 -o - %s | opt -S -mem2reg -sroa | FileCheck %s --check-prefix=CHECK32-SOFTFP
-// RUN: %clang_cc1 -triple aarch64-arm-none-eabi -target-abi aapcs -mfloat-abi softfp -target-feature +bf16 -target-feature +neon -emit-llvm -O2 -o - %s | opt -S -mem2reg -sroa | FileCheck %s --check-prefix=CHECK64-SOFTFP
+// RUN: %clang_cc1 -triple aarch64-arm-none-eabi -target-abi aapcs -target-feature +bf16 -target-feature +neon -emit-llvm -O2 -o - %s | opt -S -mem2reg -sroa | FileCheck %s --check-prefix=CHECK64
 
 #include <arm_neon.h>
 
 // function return types
 __bf16 test_ret_bf16(__bf16 v) {
   return v;
 }
 // CHECK32-HARD: define arm_aapcs_vfpcc bfloat @test_ret_bf16(bfloat returned %v) {{.*}} {
 // CHECK32-HARD: ret bfloat %v
-// CHECK64-HARD: define bfloat @test_ret_bf16(bfloat returned %v) {{.*}} {
-// CHECK64-HARD: ret bfloat %v
-// CHECK32-SOFTFP: define i32 @test_ret_bf16(i32 [[V0:.*]]) {{.*}} {
-// CHECK32-SOFTFP: %tmp2.0.insert.ext = and i32 [[V0]], 65535
-// CHECK32-SOFTFP: ret i32 %tmp2.0.insert.ext
-// CHECK64-SOFTFP: define bfloat @test_ret_bf16(bfloat returned %v) {{.*}} {
-// CHECK64-SOFTFP: ret bfloat %v
+// CHECK32-SOFTFP: define bfloat @test_ret_bf16(bfloat returned %v) {{.*}} {
+// CHECK32-SOFTFP: ret bfloat %v
+// CHECK64: define bfloat @test_ret_bf16(bfloat returned %v) {{.*}} {
+// CHECK64: ret bfloat %v
 
 bfloat16x4_t test_ret_bf16x4_t(bfloat16x4_t v) {
   return v;
 }
 // CHECK32-HARD: define arm_aapcs_vfpcc <4 x bfloat> @test_ret_bf16x4_t(<4 x bfloat> returned %v) {{.*}} {
 // CHECK32-HARD: ret <4 x bfloat> %v
-// CHECK64-HARD: define <4 x bfloat> @test_ret_bf16x4_t(<4 x bfloat> returned %v) {{.*}} {
-// CHECK64-HARD: ret <4 x bfloat> %v
 // CHECK32-SOFTFP: define <2 x i32> @test_ret_bf16x4_t(<2 x i32> [[V0:.*]]) {{.*}} {
 // CHECK32-SOFTFP: ret <2 x i32> %v
-// CHECK64-SOFTFP: define <4 x bfloat> @test_ret_bf16x4_t(<4 x bfloat> returned %v) {{.*}} {
-// CHECK64-SOFTFP: ret <4 x bfloat> %v
+// CHECK64: define <4 x bfloat> @test_ret_bf16x4_t(<4 x bfloat> returned %v) {{.*}} {
+// CHECK64: ret <4 x bfloat> %v

clang/test/CodeGen/arm-mangle-bf16.cpp

-// RUN: %clang_cc1 -triple aarch64-arm-none-eabi -target-feature +bf16 -emit-llvm -o - %s | FileCheck %s --check-prefix=CHECK64
-// RUN: %clang_cc1 -triple arm-arm-none-eabi -target-feature +bf16 -mfloat-abi hard -emit-llvm -o - %s | FileCheck %s --check-prefix=CHECK32-HARD
-// RUN: %clang_cc1 -triple arm-arm-none-eabi -target-feature +bf16 -mfloat-abi softfp -emit-llvm -o - %s | FileCheck %s --check-prefix=CHECK32-SOFTFP
+// RUN: %clang_cc1 -triple aarch64-arm-none-eabi -target-feature +bf16 -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -triple arm-arm-none-eabi -target-feature +bf16 -mfloat-abi hard -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -triple arm-arm-none-eabi -target-feature +bf16 -mfloat-abi softfp -emit-llvm -o - %s | FileCheck %s
 
-// CHECK64: define {{.*}}void @_Z3foou6__bf16(bfloat %b)
-// CHECK32-HARD: define {{.*}}void @_Z3foou6__bf16(bfloat %b)
-// CHECK32-SOFTFP: define {{.*}}void @_Z3foou6__bf16(i32 %b.coerce)
+// CHECK: define {{.*}}void @_Z3foou6__bf16(bfloat %b)
 void foo(__bf16 b) {}