[7/11][POC][Clang][RISCV] Define tuple type variant of vssseg2e32

[eopXD]

Summary

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

Depends on D147912.

This is the 7th 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 strided segment store is
not removed, and only signed integer strided segment store of NF=2,
EEW=32 is defined here.

[craig.topper]

clang/include/clang/Basic/riscv_vector.td

1721

Same comment as last review

[eopXD]

Address comment from Craig.

[eopXD]

Rebase.

[eopXD]

Reduce variable declared but only used once.

[eopXD]

Removed another variable that is too verbose.

[craig.topper]

LGTM

[eopXD]

Rebase.

clang/include/clang/Basic/riscv_vector.td

foreach type = ["i"] in {
     }] in {
           defvar T = "(Tuple:" # nf # ")";
           def : RVVBuiltin<"v", T # "vPCet", type>;
       }
     }
   }
 }
 
+multiclass RVVStridedSegStoreTuple<string op> {
+  foreach type = ["i"] in {
+    defvar eew = !cond(!eq(type, "i") : "32");
+      foreach nf = [2] in {
+        let Name = op # nf # "e" # eew # "_v_tuple",
+            OverloadedName = op # nf # "e" # eew # "_tuple",
+            IRName = op # nf,
+            MaskedIRName = op # nf # "_mask",
+            NF = nf,
+            HasMaskedOffOperand = false,
+            MaskedPolicyScheme = NonePolicy,
+            ManualCodegen = [{
+    {
+      // Masked
+      // Builtin: (mask, ptr, stride, v_tuple, vl)
+      // Intrinsic: (val0, val1, ..., ptr, stride, mask, vl)
+      // Unmasked
+      // Builtin: (ptr, stride, v_tuple, vl)
+      // Intrinsic: (val0, val1, ..., ptr, stride, vl)
+      unsigned Offset = IsMasked ? 1 : 0;
+      llvm::Value *VTupleOperand = Ops[Offset + 2];
+
+      SmallVector<llvm::Value*, 12> Operands;
+      for (unsigned I = 0; I < NF; ++I) {
+        llvm::Value *V = Builder.CreateExtractValue(VTupleOperand, {I});
+        Operands.push_back(V);
+      }
+      Operands.push_back(Ops[Offset]); // Ptr
+      Operands.push_back(Ops[Offset + 1]); // Stride
+      if (IsMasked)
+        Operands.push_back(Ops[0]);
+      Operands.push_back(Ops[Offset + 3]); // VL
+
+      IntrinsicTypes = {Operands[0]->getType(), Operands.back()->getType()};
+      llvm::Function *F = CGM.getIntrinsic(ID, IntrinsicTypes);
+      return Builder.CreateCall(F, Operands, "");
+    }
+            }] in {
+          defvar T = "(Tuple:" # nf # ")";
+          def : RVVBuiltin<"v", "0Pet" # T # "v", type>;
+      }
+    }
+  }
+}
+
 // TODO: Extend for policy
 let UnMaskedPolicyScheme = NonePolicy,
     MaskedPolicyScheme = NonePolicy,
     IsTuple = true in {
 defm : RVVUnitStridedSegLoadTuple<"vlseg">;
 defm : RVVUnitStridedSegLoadFFTuple<"vlseg">;
 defm : RVVStridedSegLoadTuple<"vlsseg">;
 }
 
 let UnMaskedPolicyScheme = NonePolicy,
     MaskedPolicyScheme = NonePolicy,
     IsTuple = true in {
 defm : RVVUnitStridedSegStoreTuple<"vsseg">;
+defm : RVVStridedSegStoreTuple<"vssseg">;
 }
 
 
 let UnMaskedPolicyScheme = NonePolicy,
     MaskedPolicyScheme = NonePolicy in {
 defm : RVVUnitStridedSegStore<"vsseg">;
 defm : RVVStridedSegStore<"vssseg">;
 defm : RVVIndexedSegStore<"vsuxseg">;

clang/test/CodeGen/RISCV/rvv-intrinsics-autogenerated/non-policy/non-overloaded/vssseg2e32_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 void @test_vssseg2e32_v_tuple_i32m1
+// CHECK-RV64-SAME: (ptr noundef [[BASE:%.*]], i64 noundef [[BSTRIDE:%.*]], <vscale x 2 x i32> [[V_TUPLE_COERCE0:%.*]], <vscale x 2 x i32> [[V_TUPLE_COERCE1:%.*]], i64 noundef [[VL:%.*]]) #[[ATTR0:[0-9]+]] {
+// CHECK-RV64-NEXT:  entry:
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32> } poison, <vscale x 2 x i32> [[V_TUPLE_COERCE0]], 0
+// CHECK-RV64-NEXT:    [[TMP1:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP0]], <vscale x 2 x i32> [[V_TUPLE_COERCE1]], 1
+// CHECK-RV64-NEXT:    [[TMP2:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP1]], 0
+// CHECK-RV64-NEXT:    [[TMP3:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP1]], 1
+// CHECK-RV64-NEXT:    call void @llvm.riscv.vssseg2.nxv2i32.i64(<vscale x 2 x i32> [[TMP2]], <vscale x 2 x i32> [[TMP3]], ptr [[BASE]], i64 [[BSTRIDE]], i64 [[VL]])
+// CHECK-RV64-NEXT:    ret void
+//
+void test_vssseg2e32_v_tuple_i32m1(int32_t *base, ptrdiff_t bstride, vint32m1x2_t v_tuple, size_t vl) {
+  return __riscv_vssseg2e32_v_tuple_i32m1(base, bstride, v_tuple, vl);
+}
+
+// CHECK-RV64-LABEL: define dso_local void @test_vssseg2e32_v_tuple_i32m1_m
+// CHECK-RV64-SAME: (<vscale x 2 x i1> [[MASK:%.*]], ptr noundef [[BASE:%.*]], i64 noundef [[BSTRIDE:%.*]], <vscale x 2 x i32> [[V_TUPLE_COERCE0:%.*]], <vscale x 2 x i32> [[V_TUPLE_COERCE1:%.*]], i64 noundef [[VL:%.*]]) #[[ATTR0]] {
+// CHECK-RV64-NEXT:  entry:
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32> } poison, <vscale x 2 x i32> [[V_TUPLE_COERCE0]], 0
+// CHECK-RV64-NEXT:    [[TMP1:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP0]], <vscale x 2 x i32> [[V_TUPLE_COERCE1]], 1
+// CHECK-RV64-NEXT:    [[TMP2:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP1]], 0
+// CHECK-RV64-NEXT:    [[TMP3:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP1]], 1
+// CHECK-RV64-NEXT:    call void @llvm.riscv.vssseg2.mask.nxv2i32.i64(<vscale x 2 x i32> [[TMP2]], <vscale x 2 x i32> [[TMP3]], ptr [[BASE]], i64 [[BSTRIDE]], <vscale x 2 x i1> [[MASK]], i64 [[VL]])
+// CHECK-RV64-NEXT:    ret void
+//
+void test_vssseg2e32_v_tuple_i32m1_m(vbool32_t mask, int32_t *base, ptrdiff_t bstride, vint32m1x2_t v_tuple, size_t vl) {
+  return __riscv_vssseg2e32_v_tuple_i32m1_m(mask, base, bstride, v_tuple, vl);
+}