[AArch64][SVE2] Guard while intrinsics on scalar bfloat feature macro

[c-rhodes]

Summary

svwhilerw_bf16 and svwhilewr_bf16 intrinsics use the scalar bfloat16_t
type which is predicated on __ARM_FEATURE_BF16_SCALAR_ARITHMETIC. This
patch changes the feature guard from __ARM_FEATURE_SVE_BF16 to the
scalar bfloat feature macro.

The verify tests for +bf16 are also removed in this patch. The purpose
of these checks was to match the SVE2 ACLE tests that look for an
implicit declaration warning if the feature isn't set. They worked when
the intrinsics were guarded on __ARM_FEATURE_SVE_BF16 as the bfloat16_t
was guarded on a different macro, but with both the type and intrinsic
guarded on the same macro an earlier error is triggered in the ACLE
regarding the type and we don't get a warning as we do for SVE2.

[sdesmalen]

LGTM

clang/include/clang/Basic/arm_sve.td

 def SVWHILERW_D : SInst<"svwhilerw[_{1}]", "Pcc", "lUld", MergeNone, "aarch64_sve_whilerw_d", [IsOverloadWhileRW]>;
 
 def SVWHILEWR_B : SInst<"svwhilewr[_{1}]", "Pcc", "cUc",  MergeNone, "aarch64_sve_whilewr_b", [IsOverloadWhileRW]>;
 def SVWHILEWR_H : SInst<"svwhilewr[_{1}]", "Pcc", "sUsh", MergeNone, "aarch64_sve_whilewr_h", [IsOverloadWhileRW]>;
 def SVWHILEWR_S : SInst<"svwhilewr[_{1}]", "Pcc", "iUif", MergeNone, "aarch64_sve_whilewr_s", [IsOverloadWhileRW]>;
 def SVWHILEWR_D : SInst<"svwhilewr[_{1}]", "Pcc", "lUld", MergeNone, "aarch64_sve_whilewr_d", [IsOverloadWhileRW]>;
 }
 
-let ArchGuard = "defined(__ARM_FEATURE_SVE2) && defined(__ARM_FEATURE_SVE_BF16)" in {
+let ArchGuard = "defined(__ARM_FEATURE_SVE2) && defined(__ARM_FEATURE_BF16_SCALAR_ARITHMETIC)" in {
 def SVWHILERW_H_BF16 : SInst<"svwhilerw[_{1}]", "Pcc", "b", MergeNone, "aarch64_sve_whilerw_h", [IsOverloadWhileRW]>;
 def SVWHILEWR_H_BF16 : SInst<"svwhilewr[_{1}]", "Pcc", "b", MergeNone, "aarch64_sve_whilewr_h", [IsOverloadWhileRW]>;
 }
 
 ////////////////////////////////////////////////////////////////////////////////
 // SVE2 - Extended table lookup/permute
 let ArchGuard = "defined(__ARM_FEATURE_SVE2)" in {
 def SVTBL2 : SInst<"svtbl2[_{d}]", "d2u",  "csilUcUsUiUlhfd", MergeNone>;

clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_whilerw-bfloat.c

-// RUN: %clang_cc1 -D__ARM_FEATURE_SVE -D__ARM_FEATURE_SVE2 -D__ARM_FEATURE_BF16_SCALAR_ARITHMETIC -D__ARM_FEATURE_SVE_BF16 -triple aarch64-none-linux-gnu -target-feature +sve2 -target-feature +bf16 -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
-// RUN: %clang_cc1 -D__ARM_FEATURE_SVE -D__ARM_FEATURE_SVE2 -D__ARM_FEATURE_BF16_SCALAR_ARITHMETIC -D__ARM_FEATURE_SVE_BF16 -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +sve2 -target-feature +bf16 -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
-
-// Test expected warnings for implicit declaration when +sve2 is missing
-// RUN: %clang_cc1 -D__ARM_FEATURE_SVE -D__ARM_FEATURE_BF16_SCALAR_ARITHMETIC -D__ARM_FEATURE_SVE_BF16 -triple aarch64-none-linux-gnu -target-feature +sve -target-feature +bf16 -fallow-half-arguments-and-returns -fsyntax-only -verify -verify-ignore-unexpected=error %s
-// RUN: %clang_cc1 -D__ARM_FEATURE_SVE -D__ARM_FEATURE_BF16_SCALAR_ARITHMETIC -D__ARM_FEATURE_SVE_BF16 -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +sve -target-feature +bf16 -fallow-half-arguments-and-returns -fsyntax-only -verify=overload -verify-ignore-unexpected=error %s
-
-// Test expected warnings for implicit declaration when +bf16 is missing
-// NOTE: +bf16 doesn't currently imply __ARM_FEATURE_SVE_BF16, once the
-// implementation is complete it will, at which point -target-feature +bf16
-// should be removed.
-// RUN: %clang_cc1 -D__ARM_FEATURE_SVE -D__ARM_FEATURE_SVE2 -D__ARM_FEATURE_BF16_SCALAR_ARITHMETIC -triple aarch64-none-linux-gnu -target-feature +sve2 -target-feature +bf16 -fallow-half-arguments-and-returns -fsyntax-only -verify -verify-ignore-unexpected=error %s
-
-// Test expected ambiguous call error for overloaded form when +bf16 is missing
-// RUN: %clang_cc1 -D__ARM_FEATURE_SVE -D__ARM_FEATURE_SVE2 -D__ARM_FEATURE_BF16_SCALAR_ARITHMETIC -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +sve2 -target-feature +bf16 -fallow-half-arguments-and-returns -fsyntax-only -verify=overload-bf16 -verify-ignore-unexpected=note %s
+// RUN: %clang_cc1 -D__ARM_FEATURE_SVE -D__ARM_FEATURE_SVE2 -D__ARM_FEATURE_BF16_SCALAR_ARITHMETIC -triple aarch64-none-linux-gnu -target-feature +sve2 -target-feature +bf16 -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -D__ARM_FEATURE_SVE -D__ARM_FEATURE_SVE2 -D__ARM_FEATURE_BF16_SCALAR_ARITHMETIC -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +sve2 -target-feature +bf16 -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -D__ARM_FEATURE_SVE -D__ARM_FEATURE_BF16_SCALAR_ARITHMETIC -triple aarch64-none-linux-gnu -target-feature +sve -target-feature +bf16 -fallow-half-arguments-and-returns -fsyntax-only -verify -verify-ignore-unexpected=error %s
+// RUN: %clang_cc1 -D__ARM_FEATURE_SVE -D__ARM_FEATURE_BF16_SCALAR_ARITHMETIC -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +sve -target-feature +bf16 -fallow-half-arguments-and-returns -fsyntax-only -verify=overload -verify-ignore-unexpected=error %s
 
 #include <arm_sve.h>
 
 #ifdef SVE_OVERLOADED_FORMS
 // A simple used,unused... macro, long enough to represent any SVE builtin.
 #define SVE_ACLE_FUNC(A1,A2_UNUSED,A3,A4_UNUSED) A1##A3
 #else
 #define SVE_ACLE_FUNC(A1,A2,A3,A4) A1##A2##A3##A4
 #endif
 
 svbool_t test_svwhilerw_bf16(const bfloat16_t *op1, const bfloat16_t *op2)
 {
   // CHECK-LABEL: test_svwhilerw_bf16
   // CHECK: %[[INTRINSIC:.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.whilerw.h.nxv8i1.p0bf16(bfloat* %op1, bfloat* %op2)
   // CHECK: %[[INTRINSIC_REINT:.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> %[[INTRINSIC]])
   // CHECK: ret <vscale x 16 x i1> %[[INTRINSIC_REINT]]
-  // overload-warning@+3 {{implicit declaration of function 'svwhilerw'}}
-  // expected-warning@+2 {{implicit declaration of function 'svwhilerw_bf16'}}
-  // overload-bf16-error@+1 {{call to 'svwhilerw' is ambiguous}}
+  // overload-warning@+2 {{implicit declaration of function 'svwhilerw'}}
+  // expected-warning@+1 {{implicit declaration of function 'svwhilerw_bf16'}}
   return SVE_ACLE_FUNC(svwhilerw,_bf16,,)(op1, op2);
 }

clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_whilewr-bfloat.c

-// RUN: %clang_cc1 -D__ARM_FEATURE_SVE -D__ARM_FEATURE_SVE2 -D__ARM_FEATURE_BF16_SCALAR_ARITHMETIC -D__ARM_FEATURE_SVE_BF16 -triple aarch64-none-linux-gnu -target-feature +sve2 -target-feature +bf16 -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
-// RUN: %clang_cc1 -D__ARM_FEATURE_SVE -D__ARM_FEATURE_SVE2 -D__ARM_FEATURE_BF16_SCALAR_ARITHMETIC -D__ARM_FEATURE_SVE_BF16 -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +sve2 -target-feature +bf16 -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
-
-// Test expected warnings for implicit declaration when +sve2 is missing
-// RUN: %clang_cc1 -D__ARM_FEATURE_SVE -D__ARM_FEATURE_BF16_SCALAR_ARITHMETIC -D__ARM_FEATURE_SVE_BF16 -triple aarch64-none-linux-gnu -target-feature +sve -target-feature +bf16 -fallow-half-arguments-and-returns -fsyntax-only -verify -verify-ignore-unexpected=error %s
-// RUN: %clang_cc1 -D__ARM_FEATURE_SVE -D__ARM_FEATURE_BF16_SCALAR_ARITHMETIC -D__ARM_FEATURE_SVE_BF16 -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +sve -target-feature +bf16 -fallow-half-arguments-and-returns -fsyntax-only -verify=overload -verify-ignore-unexpected=error %s
-
-// Test expected warnings for implicit declaration when +bf16 is missing
-// NOTE: +bf16 doesn't currently imply __ARM_FEATURE_SVE_BF16, once the
-// implementation is complete it will, at which point -target-feature +bf16
-// should be removed.
-// RUN: %clang_cc1 -D__ARM_FEATURE_SVE -D__ARM_FEATURE_SVE2 -D__ARM_FEATURE_BF16_SCALAR_ARITHMETIC -triple aarch64-none-linux-gnu -target-feature +sve2 -target-feature +bf16 -fallow-half-arguments-and-returns -fsyntax-only -verify -verify-ignore-unexpected=error %s
-
-// Test expected ambiguous call error for overloaded form when +bf16 is missing
-// RUN: %clang_cc1 -D__ARM_FEATURE_SVE -D__ARM_FEATURE_SVE2 -D__ARM_FEATURE_BF16_SCALAR_ARITHMETIC -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +sve2 -target-feature +bf16 -fallow-half-arguments-and-returns -fsyntax-only -verify=overload-bf16 -verify-ignore-unexpected=note %s
+// RUN: %clang_cc1 -D__ARM_FEATURE_SVE -D__ARM_FEATURE_SVE2 -D__ARM_FEATURE_BF16_SCALAR_ARITHMETIC -triple aarch64-none-linux-gnu -target-feature +sve2 -target-feature +bf16 -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -D__ARM_FEATURE_SVE -D__ARM_FEATURE_SVE2 -D__ARM_FEATURE_BF16_SCALAR_ARITHMETIC -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +sve2 -target-feature +bf16 -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -D__ARM_FEATURE_SVE -D__ARM_FEATURE_BF16_SCALAR_ARITHMETIC -triple aarch64-none-linux-gnu -target-feature +sve -target-feature +bf16 -fallow-half-arguments-and-returns -fsyntax-only -verify -verify-ignore-unexpected=error %s
+// RUN: %clang_cc1 -D__ARM_FEATURE_SVE -D__ARM_FEATURE_BF16_SCALAR_ARITHMETIC -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +sve -target-feature +bf16 -fallow-half-arguments-and-returns -fsyntax-only -verify=overload -verify-ignore-unexpected=error %s
 
 #include <arm_sve.h>
 
 #ifdef SVE_OVERLOADED_FORMS
 // A simple used,unused... macro, long enough to represent any SVE builtin.
 #define SVE_ACLE_FUNC(A1,A2_UNUSED,A3,A4_UNUSED) A1##A3
 #else
 #define SVE_ACLE_FUNC(A1,A2,A3,A4) A1##A2##A3##A4
 #endif
 
 svbool_t test_svwhilewr_bf16(const bfloat16_t *op1, const bfloat16_t *op2)
 {
   // CHECK-LABEL: test_svwhilewr_bf16
   // CHECK: %[[INTRINSIC:.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.whilewr.h.nxv8i1.p0bf16(bfloat* %op1, bfloat* %op2)
   // CHECK: %[[INTRINSIC_REINT:.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> %[[INTRINSIC]])
   // CHECK: ret <vscale x 16 x i1> %[[INTRINSIC_REINT]]
-  // overload-warning@+3 {{implicit declaration of function 'svwhilewr'}}
-  // expected-warning@+2 {{implicit declaration of function 'svwhilewr_bf16'}}
-  // overload-bf16-error@+1 {{call to 'svwhilewr' is ambiguous}}
+  // overload-warning@+2 {{implicit declaration of function 'svwhilewr'}}
+  // expected-warning@+1 {{implicit declaration of function 'svwhilewr_bf16'}}
   return SVE_ACLE_FUNC(svwhilewr,_bf16,,)(op1, op2);
 }