[5/11][POC][Clang][RISCV] Define tuple type variant of vlseg2e32ff

[eopXD]

Summary

For the cover letter of this patch-set, please checkout D146872.

Depends on D147774.

This is the 5th patch of the patch-set.

This patch is a proof-of-concept and will be extended to full coverage
in the future. Currently, the old non-tuple unit-stride fault-first
segment load is not removed, and only signed integer unit-stride
fault-first segment load of NF=2, EEW=32 is defined here.

[craig.topper]

clang/include/clang/Basic/riscv_vector.td

1619

unsigned Offset = IsMasked ? 1 : 0;
llvm::Value *MaskOperand = IsMasked ? Ops[0] : nullptr;
llvm::Value *PtrOperand = Ops[Offset];
unsigned NewVLOperandIdx = Offset + 1;
llvm::Value *NewVLOperand = Ops[Offset + 1];
...

[eopXD]

Address comments from Craig.

[eopXD]

Rebase.

[craig.topper]

clang/include/clang/Basic/riscv_vector.td

1626

Same comment as previous patch

[eopXD]

Address comment from Craig.

[eopXD]

Removed another variable that is too verbose.

[craig.topper]

LGTM

[eopXD]

Rebase.

clang/include/clang/Basic/riscv_vector.td

multiclass RVVUnitStridedSegStoreTuple<string op> {
    }
       }] in {
           defvar T = "(Tuple:" # nf # ")";
           def : RVVBuiltin<"v", "0Pe" # T # "v", type>;
       }
     }
   }
 }
+
+multiclass RVVUnitStridedSegLoadFFTuple<string op> {
+  foreach type = ["i"] in {
+    defvar eew = !cond(!eq(type, "i") : "32");
+      foreach nf = [2] in {
+        let Name = op # nf # "e" # eew # "ff_v_tuple",
+            OverloadedName = op # nf # "e" # eew # "ff_tuple",
+            IRName = op # nf # "ff",
+            MaskedIRName = op # nf # "ff_mask",
+            NF = nf,
+            ManualCodegen = [{
+    {
+      assert(((IsMasked && (PolicyAttrs & RVV_VTA) && (PolicyAttrs & RVV_VMA)) ||
+             (!IsMasked && (PolicyAttrs & RVV_VTA))) &&
+             "FIXME: Only handling default policy (TAMA) for now");
+
+      llvm::Type *ElementVectorType = cast<StructType>(ResultType)->elements()[0];
+
+      IntrinsicTypes = {ElementVectorType, Ops.back()->getType()};
+      SmallVector<llvm::Value*, 12> Operands;
+
+      Operands.append(NF, llvm::PoisonValue::get(ElementVectorType));
+
+      unsigned Offset = IsMasked ? 1 : 0;
+      Operands.push_back(Ops[Offset]); // Ptr
+      if (IsMasked)
+        Operands.push_back(Ops[0]);
+      Operands.push_back(Ops[Offset + 2]); // vl
+      if (IsMasked)
+        Operands.push_back(ConstantInt::get(Ops.back()->getType(), PolicyAttrs));
+
+      llvm::Function *F = CGM.getIntrinsic(ID, IntrinsicTypes);
+
+      llvm::Value *LoadValue = Builder.CreateCall(F, Operands, "");
+      // Get alignment from the new vl operand
+      clang::CharUnits Align =
+          CGM.getNaturalPointeeTypeAlignment(E->getArg(Offset + 1)->getType());
+
+      llvm::Value *ReturnTuple = llvm::PoisonValue::get(ResultType);
+      for (unsigned I = 0; I < NF; ++I) {
+        llvm::Value *V = Builder.CreateExtractValue(LoadValue, {I});
+        ReturnTuple = Builder.CreateInsertValue(ReturnTuple, V, {I});
+      }
+
+      // Store new_vl
+      llvm::Value *V = Builder.CreateExtractValue(LoadValue, {NF});
+      Builder.CreateStore(V, Address(Ops[Offset + 1], V->getType(), Align));
+
+      if (ReturnValue.isNull())
+        return ReturnTuple;
+      else
+        return Builder.CreateStore(ReturnTuple, ReturnValue.getValue());
+    }
+    }] in {
+          defvar T = "(Tuple:" # nf # ")";
+          def : RVVBuiltin<"v", T # "vPCePz", type>;
+      }
+    }
+  }
+}
+
 // TODO: Extend for policy
 let UnMaskedPolicyScheme = NonePolicy,
     MaskedPolicyScheme = NonePolicy,
     IsTuple = true in {
 defm : RVVUnitStridedSegLoadTuple<"vlseg">;
+defm : RVVUnitStridedSegLoadFFTuple<"vlseg">;
 }
 
 let UnMaskedPolicyScheme = NonePolicy,
     MaskedPolicyScheme = NonePolicy,
     IsTuple = true in {
 defm : RVVUnitStridedSegStoreTuple<"vsseg">;
 }
 

clang/test/CodeGen/RISCV/rvv-intrinsics-autogenerated/non-policy/non-overloaded/vlseg2e32ff_tuple.c

+// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --version 2
+// REQUIRES: riscv-registered-target
+// RUN: %clang_cc1 -triple riscv64 -target-feature +v -target-feature +zfh \
+// RUN:   -target-feature +experimental-zvfh -disable-O0-optnone  \
+// RUN:   -emit-llvm %s -o - | opt -S -passes=mem2reg | \
+// RUN:   FileCheck --check-prefix=CHECK-RV64 %s
+#include <riscv_vector.h>
+
+// CHECK-RV64-LABEL: define dso_local { <vscale x 2 x i32>, <vscale x 2 x i32> } @test_vlseg2e32ff_v_tuple_i32m1
+// CHECK-RV64-SAME: (ptr noundef [[BASE:%.*]], ptr noundef [[NEW_VL:%.*]], i64 noundef [[VL:%.*]]) #[[ATTR0:[0-9]+]] {
+// CHECK-RV64-NEXT:  entry:
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call { <vscale x 2 x i32>, <vscale x 2 x i32>, i64 } @llvm.riscv.vlseg2ff.nxv2i32.i64(<vscale x 2 x i32> poison, <vscale x 2 x i32> poison, ptr [[BASE]], i64 [[VL]])
+// CHECK-RV64-NEXT:    [[TMP1:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, i64 } [[TMP0]], 0
+// CHECK-RV64-NEXT:    [[TMP2:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32> } poison, <vscale x 2 x i32> [[TMP1]], 0
+// CHECK-RV64-NEXT:    [[TMP3:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, i64 } [[TMP0]], 1
+// CHECK-RV64-NEXT:    [[TMP4:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP2]], <vscale x 2 x i32> [[TMP3]], 1
+// CHECK-RV64-NEXT:    [[TMP5:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, i64 } [[TMP0]], 2
+// CHECK-RV64-NEXT:    store i64 [[TMP5]], ptr [[NEW_VL]], align 8
+// CHECK-RV64-NEXT:    ret { <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP4]]
+//
+vint32m1x2_t test_vlseg2e32ff_v_tuple_i32m1(const int32_t *base, size_t *new_vl, size_t vl) {
+  return __riscv_vlseg2e32ff_v_tuple_i32m1(base, new_vl, vl);
+}
+
+// CHECK-RV64-LABEL: define dso_local { <vscale x 2 x i32>, <vscale x 2 x i32> } @test_vlseg2e32ff_v_tuple_i32m1_m
+// CHECK-RV64-SAME: (<vscale x 2 x i1> [[MASK:%.*]], ptr noundef [[BASE:%.*]], ptr noundef [[NEW_VL:%.*]], i64 noundef [[VL:%.*]]) #[[ATTR0]] {
+// CHECK-RV64-NEXT:  entry:
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call { <vscale x 2 x i32>, <vscale x 2 x i32>, i64 } @llvm.riscv.vlseg2ff.mask.nxv2i32.i64(<vscale x 2 x i32> poison, <vscale x 2 x i32> poison, ptr [[BASE]], <vscale x 2 x i1> [[MASK]], i64 [[VL]], i64 3)
+// CHECK-RV64-NEXT:    [[TMP1:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, i64 } [[TMP0]], 0
+// CHECK-RV64-NEXT:    [[TMP2:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32> } poison, <vscale x 2 x i32> [[TMP1]], 0
+// CHECK-RV64-NEXT:    [[TMP3:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, i64 } [[TMP0]], 1
+// CHECK-RV64-NEXT:    [[TMP4:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP2]], <vscale x 2 x i32> [[TMP3]], 1
+// CHECK-RV64-NEXT:    [[TMP5:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, i64 } [[TMP0]], 2
+// CHECK-RV64-NEXT:    store i64 [[TMP5]], ptr [[NEW_VL]], align 8
+// CHECK-RV64-NEXT:    ret { <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP4]]
+//
+vint32m1x2_t test_vlseg2e32ff_v_tuple_i32m1_m(vbool32_t mask, const int32_t *base, size_t *new_vl, size_t vl) {
+  return __riscv_vlseg2e32ff_v_tuple_i32m1_m(mask, base, new_vl, vl);
+}