[RISCV] Implement RISCVTTIImpl::getPreferredAddressingMode for HasVendorXCVmem

llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp

@@ -2329,6 +2329,15 @@ unsigned RISCVTTIImpl::getMaximumVF(unsigned ElemWidth, unsigned Opcode) const {
   return std::max<unsigned>(1U, RegWidth.getFixedValue() / ElemWidth);
 }
 
+TTI::AddressingModeKind
+RISCVTTIImpl::getPreferredAddressingMode(const Loop *L,
+                                         ScalarEvolution *SE) const {
+  if (ST->hasVendorXCVmem() && !ST->is64Bit())
+    return TTI::AMK_PostIndexed;
+
+  return BasicTTIImplBase::getPreferredAddressingMode(L, SE);
+}
+
 bool RISCVTTIImpl::isLSRCostLess(const TargetTransformInfo::LSRCost &C1,
                                  const TargetTransformInfo::LSRCost &C2) {
   // RISC-V specific here are "instruction number 1st priority".

llvm/lib/Target/RISCV/RISCVTargetTransformInfo.h

@@ -388,6 +388,9 @@ class RISCVTTIImpl : public BasicTTIImplBase<RISCVTTIImpl> {
     llvm_unreachable("unknown register class");
   }
 
+  TTI::AddressingModeKind getPreferredAddressingMode(const Loop *L,
+                                                     ScalarEvolution *SE) const;
+
   unsigned getRegisterClassForType(bool Vector, Type *Ty = nullptr) const {
     if (Vector)
       return RISCVRegisterClass::VRRC;

llvm/test/CodeGen/RISCV/xcvmem-heuristic.ll

@@ -0,0 +1,34 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -O3 -mtriple=riscv32 -mattr=+m,+xcvmem -verify-machineinstrs < %s \
+; RUN:   | FileCheck %s --check-prefixes=CHECK
+
+define i32 @test_heuristic(ptr %b, i32 %e, i1 %0) {
+; CHECK-LABEL: test_heuristic:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    add a3, a0, a1
+; CHECK-NEXT:    andi a2, a2, 1
+; CHECK-NEXT:  .LBB0_1: # %loop
+; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    cv.lbu a1, (a3), 1
+; CHECK-NEXT:    addi a0, a0, 1
+; CHECK-NEXT:    beqz a2, .LBB0_1
+; CHECK-NEXT:  # %bb.2: # %exit
+; CHECK-NEXT:    mv a0, a1
+; CHECK-NEXT:    ret
+entry:
+  %1 = getelementptr i8, ptr %b, i32 %e
+  br label %loop
+
+loop:                                             ; preds = %loop, %entry
+  %2 = phi ptr [ %b, %entry ], [ %7, %loop ]
+  %3 = phi ptr [ %1, %entry ], [ %8, %loop ]
+  %4 = load i8, ptr %2, align 1
+  %5 = load i8, ptr %3, align 1
+  %6 = zext i8 %5 to i32
+  %7 = getelementptr i8, ptr %2, i32 1
+  %8 = getelementptr i8, ptr %3, i32 1
+  br i1 %0, label %exit, label %loop
+
+exit:                                             ; preds = %loop
+  ret i32 %6
+}