[llvm-exegesis] Adding support for FPR8/16/32 and FPCR for setReg warning in Aarch64.

Current implementation (for Aarch64) in llvm-exegesis only supports
GRP32, GPR64, FPR64/128, PPR16 and ZPR128 register class, thus for
opcodes variants which used llvm-exegesis throws warning "setReg is not
implemented". This code will handle the all rest floating point register
classes and initialize the registers using appropriate base instruction. And appropriate testcases for the four register classes.

Author: lakshayk-nv

llvm/test/tools/llvm-exegesis/AArch64/setReg_init_check.s

@@ -37,3 +37,40 @@ RUN: FileCheck %s --check-prefix=FPR64-ASM < %t.s
 FPR64-ASM:          <foo>:
 FPR64-ASM:          movi d{{[0-9]+}}, #0000000000000000
 FPR64-ASM-NEXT:     addv h{{[0-9]+}}, v{{[0-9]+}}.4h
+
+## FPR32 Register Class Initialization Testcase
+RUN: llvm-exegesis -mcpu=neoverse-v2 -mode=latency --dump-object-to-disk=%d --opcode-name=FABSSr --benchmark-phase=assemble-measured-code 2>&1
+RUN: llvm-objdump -d %d > %t.s
+RUN: FileCheck %s --check-prefix=FPR32-ASM < %t.s
+FPR32-ASM:         <foo>:
+FPR32-ASM:         movi d{{[0-9]+}}, #0000000000000000
+FPR32-ASM-NEXT:    fabs s{{[0-9]+}}, s{{[0-9]+}}
+
+
+## FPR16 Register Class Initialization Testcase
+RUN: llvm-exegesis -mcpu=neoverse-v2 -mode=latency --dump-object-to-disk=%d --opcode-name=FABSHr --benchmark-phase=assemble-measured-code 2>&1
+RUN: llvm-objdump -d %d > %t.s
+RUN: FileCheck %s --check-prefix=FPR16-ASM < %t.s
+FPR16-ASM:         <foo>:
+FPR16-ASM:         movi d{{[0-9]+}}, #0000000000000000
+FPR16-ASM-NEXT:    fabs h{{[0-9]+}}, h{{[0-9]+}}
+
+## FPR8 Register Class Initialization Testcase
+RUN: llvm-exegesis -mcpu=neoverse-v2 -mode=latency --dump-object-to-disk=%d --opcode-name=SQABSv1i8 --benchmark-phase=assemble-measured-code 2>&1
+RUN: llvm-objdump -d %d > %t.s
+RUN: FileCheck %s --check-prefix=FPR8-ASM < %t.s
+FPR8-ASM:         <foo>:
+FPR8-ASM:         mov     w{{[0-9]+}}, #0x0
+FPR8-ASM-NEXT:    fmov    h{{[0-9]+}}, w{{[0-9]+}}
+FPR8-ASM-NEXT:    sqabs   b{{[0-9]+}}, b{{[0-9]+}}
+
+
+## FPCR Register Class Initialization Testcase
+RUN: llvm-exegesis -mcpu=neoverse-v2 -mode=latency --dump-object-to-disk=%d --opcode-name=BFCVT --benchmark-phase=assemble-measured-code 2>&1
+RUN: llvm-objdump -d %d > %t.s
+RUN: FileCheck %s --check-prefix=FPCR-ASM < %t.s
+FPCR-ASM:         <foo>:
+FPCR-ASM:         movi d{{[0-9]+}}, #0000000000000000
+FPCR-ASM-NEXT:    mov     x{{[0-9]+}}, #0x0
+FPCR-ASM-NEXT:    msr     FPCR, x{{[0-9]+}}
+FPCR-ASM-NEXT:    bfcvt   h{{[0-9]+}}, s{{[0-9]+}}

llvm/tools/llvm-exegesis/lib/AArch64/Target.cpp

@@ -28,8 +28,8 @@ static unsigned getLoadImmediateOpcode(unsigned RegBitWidth) {
 // Generates instruction to load an immediate value into a register.
 static MCInst loadImmediate(MCRegister Reg, unsigned RegBitWidth,
                             const APInt &Value) {
-  assert (Value.getBitWidth() <= RegBitWidth &&
-          "Value must fit in the Register");
+  assert(Value.getBitWidth() <= RegBitWidth &&
+         "Value must fit in the Register");
   return MCInstBuilder(getLoadImmediateOpcode(RegBitWidth))
       .addReg(Reg)
       .addImm(Value.getZExtValue());
@@ -53,9 +53,44 @@ static MCInst loadPPRImmediate(MCRegister Reg, unsigned RegBitWidth,
       .addImm(31); // All lanes true for 16 bits
 }
 
+// Generates instructions to load an immediate value into an FPCR register.
+static std::vector<MCInst>
+loadFPCRImmediate(MCRegister Reg, unsigned RegBitWidth, const APInt &Value) {
+  MCRegister TempReg = AArch64::X8;
+  MCInst LoadImm = MCInstBuilder(AArch64::MOVi64imm).addReg(TempReg).addImm(0);
+  MCInst MoveToFPCR =
+      MCInstBuilder(AArch64::MSR).addImm(AArch64SysReg::FPCR).addReg(TempReg);
+  return {LoadImm, MoveToFPCR};
+}
+
+// Generates instructions to load an immediate value into an FPR8 register.
+static std::vector<MCInst>
+loadFP8Immediate(MCRegister Reg, unsigned RegBitWidth, const APInt &Value) {
+  assert(Value.getBitWidth() <= 8 && "Value must fit in 8 bits");
+
+  // Use a temporary general-purpose register (W8) to hold the 8-bit value
+  MCRegister TempReg = AArch64::W8;
+
+  // Load the 8-bit value into a general-purpose register (W8)
+  MCInst LoadImm = MCInstBuilder(AArch64::MOVi32imm)
+                       .addReg(TempReg)
+                       .addImm(Value.getZExtValue());
+
+  // Move the value from the general-purpose register to the FPR16 register
+  // Convert the FPR8 register to an FPR16 register
+  MCRegister FPR16Reg = Reg + (AArch64::H0 - AArch64::B0);
+  MCInst MoveToFPR =
+      MCInstBuilder(AArch64::FMOVWHr).addReg(FPR16Reg).addReg(TempReg);
+  return {LoadImm, MoveToFPR};
+}
+
 // Fetch base-instruction to load an FP immediate value into a register.
 static unsigned getLoadFPImmediateOpcode(unsigned RegBitWidth) {
   switch (RegBitWidth) {
+  case 16:
+    return AArch64::FMOVH0; //FMOVHi;
+  case 32:
+    return AArch64::FMOVS0; //FMOVSi;
   case 64:
     return AArch64::MOVID; //FMOVDi;
   case 128:
@@ -67,11 +102,12 @@ static unsigned getLoadFPImmediateOpcode(unsigned RegBitWidth) {
 // Generates instruction to load an FP immediate value into a register.
 static MCInst loadFPImmediate(MCRegister Reg, unsigned RegBitWidth,
                               const APInt &Value) {
-  assert(Value.getZExtValue() == 0 &&
-         "Expected initialisation value 0");
-  return MCInstBuilder(getLoadFPImmediateOpcode(RegBitWidth))
-      .addReg(Reg)
-      .addImm(Value.getZExtValue());
+  assert(Value.getZExtValue() == 0 && "Expected initialisation value 0");
+  MCInst Instructions =
+      MCInstBuilder(getLoadFPImmediateOpcode(RegBitWidth)).addReg(Reg);
+  if (RegBitWidth >= 64)
+    Instructions.addOperand(MCOperand::createImm(Value.getZExtValue()));
+  return Instructions;
 }
 
 #include "AArch64GenExegesis.inc"
@@ -92,12 +128,20 @@ class ExegesisAArch64Target : public ExegesisTarget {
       return {loadImmediate(Reg, 64, Value)};
     if (AArch64::PPRRegClass.contains(Reg))
       return {loadPPRImmediate(Reg, 16, Value)};
+    if (AArch64::FPR8RegClass.contains(Reg))
+      return loadFP8Immediate(Reg, 8, Value);
+    if (AArch64::FPR16RegClass.contains(Reg))
+      return {loadFPImmediate(Reg, 16, Value)};
+    if (AArch64::FPR32RegClass.contains(Reg))
+      return {loadFPImmediate(Reg, 32, Value)};
     if (AArch64::FPR64RegClass.contains(Reg))
       return {loadFPImmediate(Reg, 64, Value)};
     if (AArch64::FPR128RegClass.contains(Reg))
       return {loadFPImmediate(Reg, 128, Value)};
     if (AArch64::ZPRRegClass.contains(Reg))
       return {loadZPRImmediate(Reg, 128, Value)};
+    if (Reg == AArch64::FPCR)
+      return {loadFPCRImmediate(Reg, 32, Value)};
 
     errs() << "setRegTo is not implemented, results will be unreliable\n";
     return {};