[mlir][AVX512] Fix result type of vp2intersect: vector of bits

[springerm]

Summary

The result values of vp2intersect are vectors of bits, i.e.,
vector<8xi1> or vector<16xi8> (instead of i8 or i16).

mlir/include/mlir/Dialect/AVX512/AVX512.td

def MaskScaleFOp : AVX512_Op<"mask.scalef", [NoSideEffect,
   let assemblyFormat =
     "$src `,` $a `,` $b `,` $k `,` $rounding attr-dict `:` type($dst)";
 }
 
 def Vp2IntersectOp : AVX512_Op<"vp2intersect", [NoSideEffect,
   AllTypesMatch<["a", "b"]>,
   TypesMatchWith<"k1 has the same number of bits as elements in a",
                  "a", "k1",
-                 "IntegerType::get($_self.getContext(), "
-                 "($_self.cast<VectorType>().getShape()[0]))">,
+                 "VectorType::get({$_self.cast<VectorType>().getShape()[0]}, "
+                 "IntegerType::get($_self.getContext(), 1))">,
   TypesMatchWith<"k2 has the same number of bits as elements in b",
                  // Should use `b` instead of `a`, but that would require
                  // adding `type($b)` to assemblyFormat.
                  "a", "k2",
-                 "IntegerType::get($_self.getContext(), "
-                 "($_self.cast<VectorType>().getShape()[0]))">]> {
+                 "VectorType::get({$_self.cast<VectorType>().getShape()[0]}, "
+                 "IntegerType::get($_self.getContext(), 1))">]> {
   let summary = "Vp2Intersect op";
   let description = [{
     The `vp2intersect` op is an AVX512 specific op that can lower to the proper
     LLVMAVX512 operation: `llvm.vp2intersect.d.512` or
     `llvm.vp2intersect.q.512` depending on the type of MLIR vectors it is
     applied to.
 
     #### From the Intel Intrinsics Guide:
 
     Compute intersection of packed integer vectors `a` and `b`, and store
     indication of match in the corresponding bit of two mask registers
     specified by `k1` and `k2`. A match in corresponding elements of `a` and
     `b` is indicated by a set bit in the corresponding bit of the mask
     registers.
   }];
   let arguments = (ins VectorOfLengthAndType<[16, 8], [I32, I64]>:$a,
                    VectorOfLengthAndType<[16, 8], [I32, I64]>:$b
                    );
-  let results = (outs AnyTypeOf<[I16, I8]>:$k1,
-                 AnyTypeOf<[I16, I8]>:$k2
+  let results = (outs VectorOfLengthAndType<[16, 8], [I1, I1]>:$k1,
+                 VectorOfLengthAndType<[16, 8], [I1, I1]>:$k2
                  );
   let assemblyFormat =
     "$a `,` $b attr-dict `:` type($a)";
 }
 
 #endif // AVX512_OPS

mlir/test/Conversion/AVX512ToLLVM/convert-to-llvm.mlir

func @avx512_mask_rndscale(%a: vector<16xf32>, %b: vector<8xf64>, %i32: i32, %i16: i16, %i8: i8)
   // CHECK: llvm_avx512.mask.scalef.pd.512
   %3 = avx512.mask.scalef %b, %b, %b, %i8, %i32: vector<8xf64>
 
   // Keep results alive.
   return %0, %1, %2, %3 : vector<16xf32>, vector<8xf64>, vector<16xf32>, vector<8xf64>
 }
 
 func @avx512_vp2intersect(%a: vector<16xi32>, %b: vector<8xi64>)
-  -> (i16, i16, i8, i8)
+  -> (vector<16xi1>, vector<16xi1>, vector<8xi1>, vector<8xi1>)
 {
   // CHECK: llvm_avx512.vp2intersect.d.512
   %0, %1 = avx512.vp2intersect %a, %a : vector<16xi32>
   // CHECK: llvm_avx512.vp2intersect.q.512
   %2, %3 = avx512.vp2intersect %b, %b : vector<8xi64>
-  return %0, %1, %2, %3 : i16, i16, i8, i8
+  return %0, %1, %2, %3 : vector<16xi1>, vector<16xi1>, vector<8xi1>, vector<8xi1>
 }

mlir/test/Dialect/AVX512/roundtrip.mlir

func @avx512_scalef(%a: vector<16xf32>, %b: vector<8xf64>, %i32: i32, %i16: i16, %i8: i8)
   // CHECK: avx512.mask.scalef {{.*}}: vector<16xf32>
   %0 = avx512.mask.scalef %a, %a, %a, %i16, %i32: vector<16xf32>
   // CHECK: avx512.mask.scalef {{.*}}: vector<8xf64>
   %1 = avx512.mask.scalef %b, %b, %b, %i8, %i32 : vector<8xf64>
   return %0, %1: vector<16xf32>, vector<8xf64>
 }
 
 func @avx512_vp2intersect(%a: vector<16xi32>, %b: vector<8xi64>)
-  -> (i16, i16, i8, i8)
+  -> (vector<16xi1>, vector<16xi1>, vector<8xi1>, vector<8xi1>)
 {
   // CHECK: avx512.vp2intersect {{.*}} : vector<16xi32>
   %0, %1 = avx512.vp2intersect %a, %a : vector<16xi32>
   // CHECK: avx512.vp2intersect {{.*}} : vector<8xi64>
   %2, %3 = avx512.vp2intersect %b, %b : vector<8xi64>
-  return %0, %1, %2, %3 : i16, i16, i8, i8
+  return %0, %1, %2, %3 : vector<16xi1>, vector<16xi1>, vector<8xi1>, vector<8xi1>
 }