[llvm] 77c6743 - LLT: Add some stub constructors for FP types

[Matt Arsenault via llvm-commits]

Author: Matt Arsenault
Date: 2023-09-03T08:33:19-04:00
New Revision: 77c67436d9e7e63c50752d990a271cf860ba9a0e

URL: https://github.com/llvm/llvm-project/commit/77c67436d9e7e63c50752d990a271cf860ba9a0e
DIFF: https://github.com/llvm/llvm-project/commit/77c67436d9e7e63c50752d990a271cf860ba9a0e.diff

LOG: LLT: Add some stub constructors for FP types

This is to start documenting uses to ease a future migration
to supporting different types with the same size.

https://reviews.llvm.org/D150605

Added: 
    

Modified: 
    llvm/include/llvm/CodeGen/LowLevelType.h
    llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp

Removed: 
    


################################################################################
diff  --git a/llvm/include/llvm/CodeGen/LowLevelType.h b/llvm/include/llvm/CodeGen/LowLevelType.h
index a1e778cd718f6e..b7477834a1ff5e 100644
--- a/llvm/include/llvm/CodeGen/LowLevelType.h
+++ b/llvm/include/llvm/CodeGen/LowLevelType.h
@@ -71,6 +71,22 @@ class LLT {
                ScalarTy.isPointer() ? ScalarTy.getAddressSpace() : 0};
   }
 
+  /// Get a 16-bit IEEE half value.
+  /// TODO: Add IEEE semantics to type - This currently returns a simple `scalar(16)`.
+  static constexpr LLT float16() {
+    return scalar(16);
+  }
+
+  /// Get a 32-bit IEEE float value.
+  static constexpr LLT float32() {
+    return scalar(32);
+  }
+
+  /// Get a 64-bit IEEE double value.
+  static constexpr LLT float64() {
+    return scalar(64);
+  }
+
   /// Get a low-level fixed-width vector of some number of elements and element
   /// width.
   static constexpr LLT fixed_vector(unsigned NumElements,

diff  --git a/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp b/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
index 332ab0e472d5ee..421fc41ad3b62c 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
@@ -2979,10 +2979,10 @@ bool AMDGPULegalizerInfo::legalizeFMad(
 
   // TODO: Always legal with future ftz flag.
   // FIXME: Do we need just output?
-  if (Ty == LLT::scalar(32) &&
+  if (Ty == LLT::float32() &&
       MFI->getMode().FP32Denormals == DenormalMode::getPreserveSign())
     return true;
-  if (Ty == LLT::scalar(16) &&
+  if (Ty == LLT::float16() &&
       MFI->getMode().FP64FP16Denormals == DenormalMode::getPreserveSign())
     return true;
 
@@ -3513,27 +3513,26 @@ bool AMDGPULegalizerInfo::legalizeFPow(MachineInstr &MI,
   Register Src1 = MI.getOperand(2).getReg();
   unsigned Flags = MI.getFlags();
   LLT Ty = B.getMRI()->getType(Dst);
-  const LLT S16 = LLT::scalar(16);
-  const LLT S32 = LLT::scalar(32);
+  const LLT F16 = LLT::float16();
+  const LLT F32 = LLT::float32();
 
-  if (Ty == S32) {
-    auto Log = B.buildFLog2(S32, Src0, Flags);
-    auto Mul = B.buildIntrinsic(Intrinsic::amdgcn_fmul_legacy, {S32})
+  if (Ty == F32) {
+    auto Log = B.buildFLog2(F32, Src0, Flags);
+    auto Mul = B.buildIntrinsic(Intrinsic::amdgcn_fmul_legacy, {F32})
                    .addUse(Log.getReg(0))
                    .addUse(Src1)
                    .setMIFlags(Flags);
     B.buildFExp2(Dst, Mul, Flags);
-  } else if (Ty == S16) {
+  } else if (Ty == F16) {
     // There's no f16 fmul_legacy, so we need to convert for it.
-    auto Log = B.buildFLog2(S16, Src0, Flags);
-    auto Ext0 = B.buildFPExt(S32, Log, Flags);
-    auto Ext1 = B.buildFPExt(S32, Src1, Flags);
-    auto Mul = B.buildIntrinsic(Intrinsic::amdgcn_fmul_legacy, {S32})
+    auto Log = B.buildFLog2(F16, Src0, Flags);
+    auto Ext0 = B.buildFPExt(F32, Log, Flags);
+    auto Ext1 = B.buildFPExt(F32, Src1, Flags);
+    auto Mul = B.buildIntrinsic(Intrinsic::amdgcn_fmul_legacy, {F32})
                    .addUse(Ext0.getReg(0))
                    .addUse(Ext1.getReg(0))
                    .setMIFlags(Flags);
-
-    B.buildFExp2(Dst, B.buildFPTrunc(S16, Mul), Flags);
+    B.buildFExp2(Dst, B.buildFPTrunc(F16, Mul), Flags);
   } else
     return false;
 
@@ -3558,11 +3557,11 @@ bool AMDGPULegalizerInfo::legalizeFFloor(MachineInstr &MI,
                                          MachineIRBuilder &B) const {
 
   const LLT S1 = LLT::scalar(1);
-  const LLT S64 = LLT::scalar(64);
+  const LLT F64 = LLT::float64();
   Register Dst = MI.getOperand(0).getReg();
   Register OrigSrc = MI.getOperand(1).getReg();
   unsigned Flags = MI.getFlags();
-  assert(ST.hasFractBug() && MRI.getType(Dst) == S64 &&
+  assert(ST.hasFractBug() && MRI.getType(Dst) == F64 &&
          "this should not have been custom lowered");
 
   // V_FRACT is buggy on SI, so the F32 version is never used and (x-floor(x))
@@ -3573,7 +3572,7 @@ bool AMDGPULegalizerInfo::legalizeFFloor(MachineInstr &MI,
   //
   // Convert floor(x) to (x - fract(x))
 
-  auto Fract = B.buildIntrinsic(Intrinsic::amdgcn_fract, {S64})
+  auto Fract = B.buildIntrinsic(Intrinsic::amdgcn_fract, {F64})
                    .addUse(OrigSrc)
                    .setMIFlags(Flags);
 
@@ -3585,9 +3584,9 @@ bool AMDGPULegalizerInfo::legalizeFFloor(MachineInstr &MI,
   Register ModSrc = stripAnySourceMods(OrigSrc, MRI);
 
   auto Const =
-      B.buildFConstant(S64, llvm::bit_cast<double>(0x3fefffffffffffff));
+      B.buildFConstant(F64, llvm::bit_cast<double>(0x3fefffffffffffff));
 
-  Register Min = MRI.createGenericVirtualRegister(S64);
+  Register Min = MRI.createGenericVirtualRegister(F64);
 
   // We don't need to concern ourselves with the snan handling 
diff erence, so
   // use the one which will directly select.
@@ -3600,10 +3599,10 @@ bool AMDGPULegalizerInfo::legalizeFFloor(MachineInstr &MI,
   Register CorrectedFract = Min;
   if (!MI.getFlag(MachineInstr::FmNoNans)) {
     auto IsNan = B.buildFCmp(CmpInst::FCMP_ORD, S1, ModSrc, ModSrc, Flags);
-    CorrectedFract = B.buildSelect(S64, IsNan, ModSrc, Min, Flags).getReg(0);
+    CorrectedFract = B.buildSelect(F64, IsNan, ModSrc, Min, Flags).getReg(0);
   }
 
-  auto NegFract = B.buildFNeg(S64, CorrectedFract, Flags);
+  auto NegFract = B.buildFNeg(F64, CorrectedFract, Flags);
   B.buildFAdd(Dst, OrigSrc, NegFract, Flags);
 
   MI.eraseFromParent();