[clang] [llvm] [X86][AVX10.2-BF16] Remove [NE]P from intrinsic and instruction name (PR #123335)

2025-01-23 Thread Phoebe Wang via cfe-commits 

https://github.com/phoebewang closed 
https://github.com/llvm/llvm-project/pull/123335
___
cfe-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [llvm] [X86][AVX10.2-BF16] Remove [NE]P from intrinsic and instruction name (PR #123335)

2025-01-23 Thread Evgenii Kudriashov via cfe-commits 

https://github.com/e-kud approved this pull request.

LGTM. However some clang-format changes for 
`llvm/lib/Target/X86/X86InstrFMA3Info.cpp` look reasonable for me.

https://github.com/llvm/llvm-project/pull/123335
___
cfe-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [llvm] [X86][AVX10.2-BF16] Remove [NE]P from intrinsic and instruction name (PR #123335)

2025-01-22 Thread Phoebe Wang via cfe-commits 


@@ -5385,120 +5385,120 @@ let Features = "avx10.2-256", Attributes = [NoThrow, 
Const, RequiredVectorWidth<
 }
 
 let Features = "avx10.2-512", Attributes = [NoThrow, Const, 
RequiredVectorWidth<512>] in {
-  def vcmppbf16512_mask : X86Builtin<"unsigned int(_Vector<32, __bf16>, 
_Vector<32, __bf16>, _Constant int, unsigned int)">;
+  def vcmpbf16512_mask : X86Builtin<"unsigned int(_Vector<32, __bf16>, 
_Vector<32, __bf16>, _Constant int, unsigned int)">;
 }
 
 let Features = "avx10.2-256", Attributes = [NoThrow, Const, 
RequiredVectorWidth<256>] in {
-  def vcmppbf16256_mask : X86Builtin<"unsigned short(_Vector<16, __bf16>, 
_Vector<16, __bf16>, _Constant int, unsigned short)">;
+  def vcmpbf16256_mask : X86Builtin<"unsigned short(_Vector<16, __bf16>, 
_Vector<16, __bf16>, _Constant int, unsigned short)">;
 }
 
 let Features = "avx10.2-256", Attributes = [NoThrow, Const, 
RequiredVectorWidth<128>] in {
-  def vcmppbf16128_mask : X86Builtin<"unsigned char(_Vector<8, __bf16>, 
_Vector<8, __bf16>, _Constant int, unsigned char)">;
-  def vfpclasspbf16128_mask : X86Builtin<"unsigned char(_Vector<8, __bf16>, 
_Constant int, unsigned char)">;
+  def vcmpbf16128_mask : X86Builtin<"unsigned char(_Vector<8, __bf16>, 
_Vector<8, __bf16>, _Constant int, unsigned char)">;
+  def vfpclassbf16128_mask : X86Builtin<"unsigned char(_Vector<8, __bf16>, 
_Constant int, unsigned char)">;
 }
 
 let Features = "avx10.2-256", Attributes = [NoThrow, Const, 
RequiredVectorWidth<256>] in {
-  def vfpclasspbf16256_mask : X86Builtin<"unsigned short(_Vector<16, __bf16>, 
_Constant int, unsigned short)">;
+  def vfpclassbf16256_mask : X86Builtin<"unsigned short(_Vector<16, __bf16>, 
_Constant int, unsigned short)">;
 }
 
 let Features = "avx10.2-512", Attributes = [NoThrow, Const, 
RequiredVectorWidth<512>] in {
-  def vfpclasspbf16512_mask : X86Builtin<"unsigned int(_Vector<32, __bf16>, 
_Constant int, unsigned int)">;
+  def vfpclassbf16512_mask : X86Builtin<"unsigned int(_Vector<32, __bf16>, 
_Constant int, unsigned int)">;
 }
 
 let Features = "avx10.2-256", Attributes = [NoThrow, Const, 
RequiredVectorWidth<128>] in {
-  def vscalefpbf16128_mask : X86Builtin<"_Vector<8, __bf16>(_Vector<8, 
__bf16>, _Vector<8, __bf16>, _Vector<8, __bf16>, unsigned char)">;
+  def vscalefbf16128_mask : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, 
_Vector<8, __bf16>, _Vector<8, __bf16>, unsigned char)">;
 }
 
 let Features = "avx10.2-256", Attributes = [NoThrow, Const, 
RequiredVectorWidth<256>] in {
-  def vscalefpbf16256_mask : X86Builtin<"_Vector<16, __bf16>(_Vector<16, 
__bf16>, _Vector<16, __bf16>, _Vector<16, __bf16>, unsigned short)">;
+  def vscalefbf16256_mask : X86Builtin<"_Vector<16, __bf16>(_Vector<16, 
__bf16>, _Vector<16, __bf16>, _Vector<16, __bf16>, unsigned short)">;
 }
 
 let Features = "avx10.2-512", Attributes = [NoThrow, Const, 
RequiredVectorWidth<512>] in {
-  def vscalefpbf16512_mask : X86Builtin<"_Vector<32, __bf16>(_Vector<32, 
__bf16>, _Vector<32, __bf16>, _Vector<32, __bf16>, unsigned int)">;
+  def vscalefbf16512_mask : X86Builtin<"_Vector<32, __bf16>(_Vector<32, 
__bf16>, _Vector<32, __bf16>, _Vector<32, __bf16>, unsigned int)">;
 }
 
 let Features = "avx10.2-256", Attributes = [NoThrow, Const, 
RequiredVectorWidth<128>] in {
-  def vrcppbf16128_mask : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, 
_Vector<8, __bf16>, unsigned char)">;
+  def vrcpbf16128_mask : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, 
_Vector<8, __bf16>, unsigned char)">;
 }
 
 let Features = "avx10.2-256", Attributes = [NoThrow, Const, 
RequiredVectorWidth<256>] in {
-  def vrcppbf16256_mask : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, 
_Vector<16, __bf16>, unsigned short)">;
+  def vrcpbf16256_mask : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, 
_Vector<16, __bf16>, unsigned short)">;
 }
 
 let Features = "avx10.2-512", Attributes = [NoThrow, Const, 
RequiredVectorWidth<512>] in {
-  def vrcppbf16512_mask : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, 
_Vector<32, __bf16>, unsigned int)">;
+  def vrcpbf16512_mask : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, 
_Vector<32, __bf16>, unsigned int)">;
 }
 
 let Features = "avx10.2-256", Attributes = [NoThrow, Const, 
RequiredVectorWidth<128>] in {
-  def vgetexppbf16128_mask : X86Builtin<"_Vector<8, __bf16>(_Vector<8, 
__bf16>, _Vector<8, __bf16>, unsigned char)">;
+  def vgetexpbf16128_mask : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, 
_Vector<8, __bf16>, unsigned char)">;
 }
 
 let Features = "avx10.2-256", Attributes = [NoThrow, Const, 
RequiredVectorWidth<256>] in {
-  def vgetexppbf16256_mask : X86Builtin<"_Vector<16, __bf16>(_Vector<16, 
__bf16>, _Vector<16, __bf16>, unsigned short)">;
+  def vgetexpbf16256_mask : X86Builtin<"_Vector<16, __bf16>(_Vector<16, 
__bf16>, _Vector<16, __bf16>, unsigned short)">;
 }
 
 let Features = "avx10.2-512", Attributes = [NoThrow, Const, 
RequiredVectorWidth<512>] in {
-  def vgetexppbf

[clang] [llvm] [X86][AVX10.2-BF16] Remove [NE]P from intrinsic and instruction name (PR #123335)

2025-01-22 Thread Evgenii Kudriashov via cfe-commits 


@@ -5385,120 +5385,120 @@ let Features = "avx10.2-256", Attributes = [NoThrow, 
Const, RequiredVectorWidth<
 }
 
 let Features = "avx10.2-512", Attributes = [NoThrow, Const, 
RequiredVectorWidth<512>] in {
-  def vcmppbf16512_mask : X86Builtin<"unsigned int(_Vector<32, __bf16>, 
_Vector<32, __bf16>, _Constant int, unsigned int)">;
+  def vcmpbf16512_mask : X86Builtin<"unsigned int(_Vector<32, __bf16>, 
_Vector<32, __bf16>, _Constant int, unsigned int)">;
 }
 
 let Features = "avx10.2-256", Attributes = [NoThrow, Const, 
RequiredVectorWidth<256>] in {
-  def vcmppbf16256_mask : X86Builtin<"unsigned short(_Vector<16, __bf16>, 
_Vector<16, __bf16>, _Constant int, unsigned short)">;
+  def vcmpbf16256_mask : X86Builtin<"unsigned short(_Vector<16, __bf16>, 
_Vector<16, __bf16>, _Constant int, unsigned short)">;
 }
 
 let Features = "avx10.2-256", Attributes = [NoThrow, Const, 
RequiredVectorWidth<128>] in {
-  def vcmppbf16128_mask : X86Builtin<"unsigned char(_Vector<8, __bf16>, 
_Vector<8, __bf16>, _Constant int, unsigned char)">;
-  def vfpclasspbf16128_mask : X86Builtin<"unsigned char(_Vector<8, __bf16>, 
_Constant int, unsigned char)">;
+  def vcmpbf16128_mask : X86Builtin<"unsigned char(_Vector<8, __bf16>, 
_Vector<8, __bf16>, _Constant int, unsigned char)">;
+  def vfpclassbf16128_mask : X86Builtin<"unsigned char(_Vector<8, __bf16>, 
_Constant int, unsigned char)">;
 }
 
 let Features = "avx10.2-256", Attributes = [NoThrow, Const, 
RequiredVectorWidth<256>] in {
-  def vfpclasspbf16256_mask : X86Builtin<"unsigned short(_Vector<16, __bf16>, 
_Constant int, unsigned short)">;
+  def vfpclassbf16256_mask : X86Builtin<"unsigned short(_Vector<16, __bf16>, 
_Constant int, unsigned short)">;
 }
 
 let Features = "avx10.2-512", Attributes = [NoThrow, Const, 
RequiredVectorWidth<512>] in {
-  def vfpclasspbf16512_mask : X86Builtin<"unsigned int(_Vector<32, __bf16>, 
_Constant int, unsigned int)">;
+  def vfpclassbf16512_mask : X86Builtin<"unsigned int(_Vector<32, __bf16>, 
_Constant int, unsigned int)">;
 }
 
 let Features = "avx10.2-256", Attributes = [NoThrow, Const, 
RequiredVectorWidth<128>] in {
-  def vscalefpbf16128_mask : X86Builtin<"_Vector<8, __bf16>(_Vector<8, 
__bf16>, _Vector<8, __bf16>, _Vector<8, __bf16>, unsigned char)">;
+  def vscalefbf16128_mask : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, 
_Vector<8, __bf16>, _Vector<8, __bf16>, unsigned char)">;
 }
 
 let Features = "avx10.2-256", Attributes = [NoThrow, Const, 
RequiredVectorWidth<256>] in {
-  def vscalefpbf16256_mask : X86Builtin<"_Vector<16, __bf16>(_Vector<16, 
__bf16>, _Vector<16, __bf16>, _Vector<16, __bf16>, unsigned short)">;
+  def vscalefbf16256_mask : X86Builtin<"_Vector<16, __bf16>(_Vector<16, 
__bf16>, _Vector<16, __bf16>, _Vector<16, __bf16>, unsigned short)">;
 }
 
 let Features = "avx10.2-512", Attributes = [NoThrow, Const, 
RequiredVectorWidth<512>] in {
-  def vscalefpbf16512_mask : X86Builtin<"_Vector<32, __bf16>(_Vector<32, 
__bf16>, _Vector<32, __bf16>, _Vector<32, __bf16>, unsigned int)">;
+  def vscalefbf16512_mask : X86Builtin<"_Vector<32, __bf16>(_Vector<32, 
__bf16>, _Vector<32, __bf16>, _Vector<32, __bf16>, unsigned int)">;
 }
 
 let Features = "avx10.2-256", Attributes = [NoThrow, Const, 
RequiredVectorWidth<128>] in {
-  def vrcppbf16128_mask : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, 
_Vector<8, __bf16>, unsigned char)">;
+  def vrcpbf16128_mask : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, 
_Vector<8, __bf16>, unsigned char)">;
 }
 
 let Features = "avx10.2-256", Attributes = [NoThrow, Const, 
RequiredVectorWidth<256>] in {
-  def vrcppbf16256_mask : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, 
_Vector<16, __bf16>, unsigned short)">;
+  def vrcpbf16256_mask : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, 
_Vector<16, __bf16>, unsigned short)">;
 }
 
 let Features = "avx10.2-512", Attributes = [NoThrow, Const, 
RequiredVectorWidth<512>] in {
-  def vrcppbf16512_mask : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, 
_Vector<32, __bf16>, unsigned int)">;
+  def vrcpbf16512_mask : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, 
_Vector<32, __bf16>, unsigned int)">;
 }
 
 let Features = "avx10.2-256", Attributes = [NoThrow, Const, 
RequiredVectorWidth<128>] in {
-  def vgetexppbf16128_mask : X86Builtin<"_Vector<8, __bf16>(_Vector<8, 
__bf16>, _Vector<8, __bf16>, unsigned char)">;
+  def vgetexpbf16128_mask : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, 
_Vector<8, __bf16>, unsigned char)">;
 }
 
 let Features = "avx10.2-256", Attributes = [NoThrow, Const, 
RequiredVectorWidth<256>] in {
-  def vgetexppbf16256_mask : X86Builtin<"_Vector<16, __bf16>(_Vector<16, 
__bf16>, _Vector<16, __bf16>, unsigned short)">;
+  def vgetexpbf16256_mask : X86Builtin<"_Vector<16, __bf16>(_Vector<16, 
__bf16>, _Vector<16, __bf16>, unsigned short)">;
 }
 
 let Features = "avx10.2-512", Attributes = [NoThrow, Const, 
RequiredVectorWidth<512>] in {
-  def vgetexppbf

[clang] [llvm] [X86][AVX10.2-BF16] Remove [NE]P from intrinsic and instruction name (PR #123335)

2025-01-17 Thread via cfe-commits 

github-actions[bot] wrote:




:warning: C/C++ code formatter, clang-format found issues in your code. 
:warning:



You can test this locally with the following command:


``bash
git-clang-format --diff 1274bca2ad5befe56d82ef76100e2c294ca57ce2 
ef979383a507277247d36b97572f4bf558e84305 --extensions inc,cpp,h,c -- 
clang/lib/CodeGen/CGBuiltin.cpp clang/lib/Headers/avx10_2_512bf16intrin.h 
clang/lib/Headers/avx10_2bf16intrin.h clang/lib/Sema/SemaX86.cpp 
clang/test/CodeGen/X86/avx10_2_512bf16-builtins.c 
clang/test/CodeGen/X86/avx10_2bf16-builtins.c 
llvm/lib/Target/X86/AsmParser/X86AsmParser.cpp 
llvm/lib/Target/X86/MCTargetDesc/X86ATTInstPrinter.cpp 
llvm/lib/Target/X86/MCTargetDesc/X86InstComments.cpp 
llvm/lib/Target/X86/MCTargetDesc/X86InstPrinterCommon.cpp 
llvm/lib/Target/X86/MCTargetDesc/X86IntelInstPrinter.cpp 
llvm/lib/Target/X86/X86InstrFMA3Info.cpp 
llvm/lib/Target/X86/X86IntrinsicsInfo.h llvm/test/TableGen/x86-fold-tables.inc
``





View the diff from clang-format here.


``diff
diff --git a/llvm/lib/Target/X86/MCTargetDesc/X86ATTInstPrinter.cpp 
b/llvm/lib/Target/X86/MCTargetDesc/X86ATTInstPrinter.cpp
index cd89b88f46..6b9527502b 100644
--- a/llvm/lib/Target/X86/MCTargetDesc/X86ATTInstPrinter.cpp
+++ b/llvm/lib/Target/X86/MCTargetDesc/X86ATTInstPrinter.cpp
@@ -166,15 +166,24 @@ bool X86ATTInstPrinter::printVecCompareInstr(const MCInst 
*MI,
   case X86::VCMPPHZrmbi: case X86::VCMPPHZrmbik:
   case X86::VCMPPHZrrib: case X86::VCMPPHZrribk:
   case X86::VCMPSHZrrib_Int: case X86::VCMPSHZrribk_Int:
-  case X86::VCMPBF16Z128rmi:  case X86::VCMPBF16Z128rri:
-  case X86::VCMPBF16Z256rmi:  case X86::VCMPBF16Z256rri:
-  case X86::VCMPBF16Zrmi: case X86::VCMPBF16Zrri:
-  case X86::VCMPBF16Z128rmik: case X86::VCMPBF16Z128rrik:
-  case X86::VCMPBF16Z256rmik: case X86::VCMPBF16Z256rrik:
-  case X86::VCMPBF16Zrmik:case X86::VCMPBF16Zrrik:
-  case X86::VCMPBF16Z128rmbi: case X86::VCMPBF16Z128rmbik:
-  case X86::VCMPBF16Z256rmbi: case X86::VCMPBF16Z256rmbik:
-  case X86::VCMPBF16Zrmbi:case X86::VCMPBF16Zrmbik:
+  case X86::VCMPBF16Z128rmi:
+  case X86::VCMPBF16Z128rri:
+  case X86::VCMPBF16Z256rmi:
+  case X86::VCMPBF16Z256rri:
+  case X86::VCMPBF16Zrmi:
+  case X86::VCMPBF16Zrri:
+  case X86::VCMPBF16Z128rmik:
+  case X86::VCMPBF16Z128rrik:
+  case X86::VCMPBF16Z256rmik:
+  case X86::VCMPBF16Z256rrik:
+  case X86::VCMPBF16Zrmik:
+  case X86::VCMPBF16Zrrik:
+  case X86::VCMPBF16Z128rmbi:
+  case X86::VCMPBF16Z128rmbik:
+  case X86::VCMPBF16Z256rmbi:
+  case X86::VCMPBF16Z256rmbik:
+  case X86::VCMPBF16Zrmbi:
+  case X86::VCMPBF16Zrmbik:
 if (Imm >= 0 && Imm <= 31) {
   OS << '\t';
   printCMPMnemonic(MI, /*IsVCMP*/true, OS);
diff --git a/llvm/lib/Target/X86/MCTargetDesc/X86InstPrinterCommon.cpp 
b/llvm/lib/Target/X86/MCTargetDesc/X86InstPrinterCommon.cpp
index 8470d26011..8d9fa806a2 100644
--- a/llvm/lib/Target/X86/MCTargetDesc/X86InstPrinterCommon.cpp
+++ b/llvm/lib/Target/X86/MCTargetDesc/X86InstPrinterCommon.cpp
@@ -309,15 +309,24 @@ void X86InstPrinterCommon::printCMPMnemonic(const MCInst 
*MI, bool IsVCmp,
   case X86::VCMPSHZrmik_Int: case X86::VCMPSHZrrik_Int:
 OS << "sh\t";
 break;
-  case X86::VCMPBF16Z128rmi:  case X86::VCMPBF16Z128rri:
-  case X86::VCMPBF16Z256rmi:  case X86::VCMPBF16Z256rri:
-  case X86::VCMPBF16Zrmi: case X86::VCMPBF16Zrri:
-  case X86::VCMPBF16Z128rmik: case X86::VCMPBF16Z128rrik:
-  case X86::VCMPBF16Z256rmik: case X86::VCMPBF16Z256rrik:
-  case X86::VCMPBF16Zrmik:case X86::VCMPBF16Zrrik:
-  case X86::VCMPBF16Z128rmbi: case X86::VCMPBF16Z128rmbik:
-  case X86::VCMPBF16Z256rmbi: case X86::VCMPBF16Z256rmbik:
-  case X86::VCMPBF16Zrmbi:case X86::VCMPBF16Zrmbik:
+  case X86::VCMPBF16Z128rmi:
+  case X86::VCMPBF16Z128rri:
+  case X86::VCMPBF16Z256rmi:
+  case X86::VCMPBF16Z256rri:
+  case X86::VCMPBF16Zrmi:
+  case X86::VCMPBF16Zrri:
+  case X86::VCMPBF16Z128rmik:
+  case X86::VCMPBF16Z128rrik:
+  case X86::VCMPBF16Z256rmik:
+  case X86::VCMPBF16Z256rrik:
+  case X86::VCMPBF16Zrmik:
+  case X86::VCMPBF16Zrrik:
+  case X86::VCMPBF16Z128rmbi:
+  case X86::VCMPBF16Z128rmbik:
+  case X86::VCMPBF16Z256rmbi:
+  case X86::VCMPBF16Z256rmbik:
+  case X86::VCMPBF16Zrmbi:
+  case X86::VCMPBF16Zrmbik:
 OS << "bf16\t";
 break;
   }
diff --git a/llvm/lib/Target/X86/MCTargetDesc/X86IntelInstPrinter.cpp 
b/llvm/lib/Target/X86/MCTargetDesc/X86IntelInstPrinter.cpp
index 0d92609b3a..5a814fce46 100644
--- a/llvm/lib/Target/X86/MCTargetDesc/X86IntelInstPrinter.cpp
+++ b/llvm/lib/Target/X86/MCTargetDesc/X86IntelInstPrinter.cpp
@@ -145,15 +145,24 @@ bool X86IntelInstPrinter::printVecCompareInstr(const 
MCInst *MI, raw_ostream &OS
   case X86::VCMPPHZrmbi: case X86::VCMPPHZrmbik:
   case X86::VCMPPHZrrib: case X86::VCMPPHZrribk:
   case X86::VCMPSHZrrib_Int: case X86::VCMPSHZrribk_Int:
-  case X86::VCMPBF16Z128rmi:  case X86::VCMPBF16Z128rri:
-  case X86::VCMPBF16Z256rmi:  case X86::VCMPBF16Z256rri:
-  case X86::V

[clang] [llvm] [X86][AVX10.2-BF16] Remove [NE]P from intrinsic and instruction name (PR #123335)

2025-01-17 Thread via cfe-commits 

llvmbot wrote:




@llvm/pr-subscribers-llvm-ir

Author: Phoebe Wang (phoebewang)


Changes

Ref.: https://cdrdv2.intel.com/v1/dl/getContent/828965

---

Patch is 1.81 MiB, truncated to 20.00 KiB below, full version: 
https://github.com/llvm/llvm-project/pull/123335.diff


29 Files Affected:

- (modified) clang/include/clang/Basic/BuiltinsX86.td (+48-48) 
- (modified) clang/lib/CodeGen/CGBuiltin.cpp (+15-15) 
- (modified) clang/lib/Headers/avx10_2_512bf16intrin.h (+103-107) 
- (modified) clang/lib/Headers/avx10_2bf16intrin.h (+210-216) 
- (modified) clang/lib/Sema/SemaX86.cpp (+9-9) 
- (modified) clang/test/CodeGen/X86/avx10_2_512bf16-builtins.c (+150-150) 
- (modified) clang/test/CodeGen/X86/avx10_2bf16-builtins.c (+273-273) 
- (modified) llvm/include/llvm/IR/IntrinsicsX86.td (+78-78) 
- (modified) llvm/lib/Target/X86/AsmParser/X86AsmParser.cpp (+4-4) 
- (modified) llvm/lib/Target/X86/MCTargetDesc/X86ATTInstPrinter.cpp (+9-9) 
- (modified) llvm/lib/Target/X86/MCTargetDesc/X86InstComments.cpp (+2-2) 
- (modified) llvm/lib/Target/X86/MCTargetDesc/X86InstPrinterCommon.cpp (+10-10) 
- (modified) llvm/lib/Target/X86/MCTargetDesc/X86IntelInstPrinter.cpp (+9-9) 
- (modified) llvm/lib/Target/X86/X86InstrAVX10.td (+70-70) 
- (modified) llvm/lib/Target/X86/X86InstrFMA3Info.cpp (+2-2) 
- (modified) llvm/lib/Target/X86/X86InstrUtils.td (+3-3) 
- (modified) llvm/lib/Target/X86/X86IntrinsicsInfo.h (+27-27) 
- (modified) llvm/test/CodeGen/X86/avx10.2-fma-commute.ll (+108-108) 
- (modified) llvm/test/CodeGen/X86/avx10_2_512bf16-arith.ll (+110-110) 
- (modified) llvm/test/CodeGen/X86/avx10_2_512bf16-intrinsics.ll (+97-97) 
- (modified) llvm/test/CodeGen/X86/avx10_2bf16-arith.ll (+222-222) 
- (modified) llvm/test/CodeGen/X86/avx10_2bf16-intrinsics.ll (+222-222) 
- (modified) llvm/test/MC/Disassembler/X86/avx10.2-bf16-32.txt (+1492-1492) 
- (modified) llvm/test/MC/Disassembler/X86/avx10.2-bf16-64.txt (+1492-1492) 
- (modified) llvm/test/MC/X86/avx10.2-bf16-32-att.s (+1492-1492) 
- (modified) llvm/test/MC/X86/avx10.2-bf16-32-intel.s (+1492-1492) 
- (modified) llvm/test/MC/X86/avx10.2-bf16-64-att.s (+1492-1492) 
- (modified) llvm/test/MC/X86/avx10.2-bf16-64-intel.s (+1492-1492) 
- (modified) llvm/test/TableGen/x86-fold-tables.inc (+492-492) 


``diff
diff --git a/clang/include/clang/Basic/BuiltinsX86.td 
b/clang/include/clang/Basic/BuiltinsX86.td
index 18fc10eb85c027..32d5486f162b38 100644
--- a/clang/include/clang/Basic/BuiltinsX86.td
+++ b/clang/include/clang/Basic/BuiltinsX86.td
@@ -5304,75 +5304,75 @@ let Features = "avx10.2-256", Attributes = [NoThrow, 
RequiredVectorWidth<128>] i
 }
 
 let Features = "avx10.2-256", Attributes = [NoThrow, Const, 
RequiredVectorWidth<128>] in {
-  def vaddnepbf16128 : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, 
_Vector<8, __bf16>)">;
+  def vaddbf16128 : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, 
_Vector<8, __bf16>)">;
 }
 
 let Features = "avx10.2-256", Attributes = [NoThrow, Const, 
RequiredVectorWidth<256>] in {
-  def vaddnepbf16256 : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, 
_Vector<16, __bf16>)">;
+  def vaddbf16256 : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, 
_Vector<16, __bf16>)">;
 }
 
 let Features = "avx10.2-512", Attributes = [NoThrow, Const, 
RequiredVectorWidth<512>] in {
-  def vaddnepbf16512 : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, 
_Vector<32, __bf16>)">;
+  def vaddbf16512 : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, 
_Vector<32, __bf16>)">;
 }
 
 let Features = "avx10.2-256", Attributes = [NoThrow, Const, 
RequiredVectorWidth<128>] in {
-  def vdivnepbf16128 : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, 
_Vector<8, __bf16>)">;
+  def vdivbf16128 : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, 
_Vector<8, __bf16>)">;
 }
 
 let Features = "avx10.2-256", Attributes = [NoThrow, Const, 
RequiredVectorWidth<256>] in {
-  def vdivnepbf16256 : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, 
_Vector<16, __bf16>)">;
+  def vdivbf16256 : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, 
_Vector<16, __bf16>)">;
 }
 
 let Features = "avx10.2-512", Attributes = [NoThrow, Const, 
RequiredVectorWidth<512>] in {
-  def vdivnepbf16512 : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, 
_Vector<32, __bf16>)">;
+  def vdivbf16512 : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, 
_Vector<32, __bf16>)">;
 }
 
 let Features = "avx10.2-256", Attributes = [NoThrow, Const, 
RequiredVectorWidth<128>] in {
-  def vmaxpbf16128 : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, 
_Vector<8, __bf16>)">;
+  def vmaxbf16128 : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, 
_Vector<8, __bf16>)">;
 }
 
 let Features = "avx10.2-256", Attributes = [NoThrow, Const, 
RequiredVectorWidth<256>] in {
-  def vmaxpbf16256 : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, 
_Vector<16, __bf16>)">;
+  def vmaxbf16256 : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, 
_Vector<16, __bf16>)">;
 }
 
 l

[clang] [llvm] [X86][AVX10.2-BF16] Remove [NE]P from intrinsic and instruction name (PR #123335)

2025-01-17 Thread via cfe-commits 

llvmbot wrote:




@llvm/pr-subscribers-clang-codegen

Author: Phoebe Wang (phoebewang)


Changes

Ref.: https://cdrdv2.intel.com/v1/dl/getContent/828965

---

Patch is 1.81 MiB, truncated to 20.00 KiB below, full version: 
https://github.com/llvm/llvm-project/pull/123335.diff


29 Files Affected:

- (modified) clang/include/clang/Basic/BuiltinsX86.td (+48-48) 
- (modified) clang/lib/CodeGen/CGBuiltin.cpp (+15-15) 
- (modified) clang/lib/Headers/avx10_2_512bf16intrin.h (+103-107) 
- (modified) clang/lib/Headers/avx10_2bf16intrin.h (+210-216) 
- (modified) clang/lib/Sema/SemaX86.cpp (+9-9) 
- (modified) clang/test/CodeGen/X86/avx10_2_512bf16-builtins.c (+150-150) 
- (modified) clang/test/CodeGen/X86/avx10_2bf16-builtins.c (+273-273) 
- (modified) llvm/include/llvm/IR/IntrinsicsX86.td (+78-78) 
- (modified) llvm/lib/Target/X86/AsmParser/X86AsmParser.cpp (+4-4) 
- (modified) llvm/lib/Target/X86/MCTargetDesc/X86ATTInstPrinter.cpp (+9-9) 
- (modified) llvm/lib/Target/X86/MCTargetDesc/X86InstComments.cpp (+2-2) 
- (modified) llvm/lib/Target/X86/MCTargetDesc/X86InstPrinterCommon.cpp (+10-10) 
- (modified) llvm/lib/Target/X86/MCTargetDesc/X86IntelInstPrinter.cpp (+9-9) 
- (modified) llvm/lib/Target/X86/X86InstrAVX10.td (+70-70) 
- (modified) llvm/lib/Target/X86/X86InstrFMA3Info.cpp (+2-2) 
- (modified) llvm/lib/Target/X86/X86InstrUtils.td (+3-3) 
- (modified) llvm/lib/Target/X86/X86IntrinsicsInfo.h (+27-27) 
- (modified) llvm/test/CodeGen/X86/avx10.2-fma-commute.ll (+108-108) 
- (modified) llvm/test/CodeGen/X86/avx10_2_512bf16-arith.ll (+110-110) 
- (modified) llvm/test/CodeGen/X86/avx10_2_512bf16-intrinsics.ll (+97-97) 
- (modified) llvm/test/CodeGen/X86/avx10_2bf16-arith.ll (+222-222) 
- (modified) llvm/test/CodeGen/X86/avx10_2bf16-intrinsics.ll (+222-222) 
- (modified) llvm/test/MC/Disassembler/X86/avx10.2-bf16-32.txt (+1492-1492) 
- (modified) llvm/test/MC/Disassembler/X86/avx10.2-bf16-64.txt (+1492-1492) 
- (modified) llvm/test/MC/X86/avx10.2-bf16-32-att.s (+1492-1492) 
- (modified) llvm/test/MC/X86/avx10.2-bf16-32-intel.s (+1492-1492) 
- (modified) llvm/test/MC/X86/avx10.2-bf16-64-att.s (+1492-1492) 
- (modified) llvm/test/MC/X86/avx10.2-bf16-64-intel.s (+1492-1492) 
- (modified) llvm/test/TableGen/x86-fold-tables.inc (+492-492) 


``diff
diff --git a/clang/include/clang/Basic/BuiltinsX86.td 
b/clang/include/clang/Basic/BuiltinsX86.td
index 18fc10eb85c027..32d5486f162b38 100644
--- a/clang/include/clang/Basic/BuiltinsX86.td
+++ b/clang/include/clang/Basic/BuiltinsX86.td
@@ -5304,75 +5304,75 @@ let Features = "avx10.2-256", Attributes = [NoThrow, 
RequiredVectorWidth<128>] i
 }
 
 let Features = "avx10.2-256", Attributes = [NoThrow, Const, 
RequiredVectorWidth<128>] in {
-  def vaddnepbf16128 : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, 
_Vector<8, __bf16>)">;
+  def vaddbf16128 : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, 
_Vector<8, __bf16>)">;
 }
 
 let Features = "avx10.2-256", Attributes = [NoThrow, Const, 
RequiredVectorWidth<256>] in {
-  def vaddnepbf16256 : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, 
_Vector<16, __bf16>)">;
+  def vaddbf16256 : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, 
_Vector<16, __bf16>)">;
 }
 
 let Features = "avx10.2-512", Attributes = [NoThrow, Const, 
RequiredVectorWidth<512>] in {
-  def vaddnepbf16512 : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, 
_Vector<32, __bf16>)">;
+  def vaddbf16512 : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, 
_Vector<32, __bf16>)">;
 }
 
 let Features = "avx10.2-256", Attributes = [NoThrow, Const, 
RequiredVectorWidth<128>] in {
-  def vdivnepbf16128 : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, 
_Vector<8, __bf16>)">;
+  def vdivbf16128 : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, 
_Vector<8, __bf16>)">;
 }
 
 let Features = "avx10.2-256", Attributes = [NoThrow, Const, 
RequiredVectorWidth<256>] in {
-  def vdivnepbf16256 : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, 
_Vector<16, __bf16>)">;
+  def vdivbf16256 : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, 
_Vector<16, __bf16>)">;
 }
 
 let Features = "avx10.2-512", Attributes = [NoThrow, Const, 
RequiredVectorWidth<512>] in {
-  def vdivnepbf16512 : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, 
_Vector<32, __bf16>)">;
+  def vdivbf16512 : X86Builtin<"_Vector<32, __bf16>(_Vector<32, __bf16>, 
_Vector<32, __bf16>)">;
 }
 
 let Features = "avx10.2-256", Attributes = [NoThrow, Const, 
RequiredVectorWidth<128>] in {
-  def vmaxpbf16128 : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, 
_Vector<8, __bf16>)">;
+  def vmaxbf16128 : X86Builtin<"_Vector<8, __bf16>(_Vector<8, __bf16>, 
_Vector<8, __bf16>)">;
 }
 
 let Features = "avx10.2-256", Attributes = [NoThrow, Const, 
RequiredVectorWidth<256>] in {
-  def vmaxpbf16256 : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, 
_Vector<16, __bf16>)">;
+  def vmaxbf16256 : X86Builtin<"_Vector<16, __bf16>(_Vector<16, __bf16>, 
_Vector<16, __bf16>)">;