[mlir][vector] Add more tests for ConvertVectorToLLVM (8/n)

Adds tests with scalable vectors for the Vector-To-LLVM conversion pass.
Covers the following Ops:
  * vector.transfer_read
  * vector.transfer_write

In addition:
  * Tests that test both xfer_read and xfer_write have their names
    updated to capture that (e.g. `@transfer_read_1d_mask` ->
    `@transfer_read_write_1d_mask`)
  * `@transfer_write_1d_scalable_mask` and
    `@transfer_read_1d_scalable_mask` are re-written as
    `@transfer_read_write_1d_mask_scalable`. This is to make it clear
    that this case is meant to complement
    `@transfer_read_write_1d_mask`.
  * `@transfer_write_tensor` is updated to also test `xfer_read`.

Author: banach-space

mlir/test/Conversion/VectorToLLVM/vector-to-llvm.mlir

@@ -2377,7 +2377,7 @@ func.func @matrix_ops_index(%A: vector<64xindex>, %B: vector<48xindex>) -> vecto
 
 // -----
 
-func.func @transfer_read_1d(%A : memref<?xf32>, %base: index) -> vector<17xf32> {
+func.func @transfer_read_write_1d(%A : memref<?xf32>, %base: index) -> vector<17xf32> {
   %f7 = arith.constant 7.0: f32
   %f = vector.transfer_read %A[%base], %f7
       {permutation_map = affine_map<(d0) -> (d0)>} :
@@ -2387,7 +2387,7 @@ func.func @transfer_read_1d(%A : memref<?xf32>, %base: index) -> vector<17xf32>
     vector<17xf32>, memref<?xf32>
   return %f: vector<17xf32>
 }
-// CHECK-LABEL: func @transfer_read_1d
+// CHECK-LABEL: func @transfer_read_write_1d
 //  CHECK-SAME: %[[MEM:.*]]: memref<?xf32>,
 //  CHECK-SAME: %[[BASE:.*]]: index) -> vector<17xf32>
 //       CHECK: %[[C7:.*]] = arith.constant 7.0
@@ -2449,9 +2449,77 @@ func.func @transfer_read_1d(%A : memref<?xf32>, %base: index) -> vector<17xf32>
 //  CHECK-SAME: {alignment = 4 : i32} :
 //  CHECK-SAME: vector<17xf32>, vector<17xi1> into !llvm.ptr
 
+func.func @transfer_read_write_1d_scalable(%A : memref<?xf32>, %base: index) -> vector<[17]xf32> {
+  %f7 = arith.constant 7.0: f32
+  %f = vector.transfer_read %A[%base], %f7
+      {permutation_map = affine_map<(d0) -> (d0)>} :
+    memref<?xf32>, vector<[17]xf32>
+  vector.transfer_write %f, %A[%base]
+      {permutation_map = affine_map<(d0) -> (d0)>} :
+    vector<[17]xf32>, memref<?xf32>
+  return %f: vector<[17]xf32>
+}
+// CHECK-LABEL: func @transfer_read_write_1d_scalable
+//  CHECK-SAME: %[[MEM:.*]]: memref<?xf32>,
+//  CHECK-SAME: %[[BASE:.*]]: index) -> vector<[17]xf32>
+//       CHECK: %[[C7:.*]] = arith.constant 7.0
+//
+// 1. Let dim be the memref dimension, compute the in-bound index (dim - offset)
+//       CHECK: %[[C0:.*]] = arith.constant 0 : index
+//       CHECK: %[[DIM:.*]] = memref.dim %[[MEM]], %[[C0]] : memref<?xf32>
+//       CHECK: %[[BOUND:.*]] = arith.subi %[[DIM]],  %[[BASE]] : index
+//
+// 2. Create a vector with linear indices [ 0 .. vector_length - 1 ].
+//       CHECK: %[[linearIndex:.*]] = llvm.intr.stepvector : vector<[17]xi32>
+//
+// 3. Create bound vector to compute in-bound mask:
+//    [ 0 .. vector_length - 1 ] < [ dim - offset .. dim - offset ]
+//       CHECK: %[[btrunc:.*]] = arith.index_cast %[[BOUND]] : index to i32
+//       CHECK: %[[boundVecInsert:.*]] = llvm.insertelement %[[btrunc]]
+//       CHECK: %[[boundVect:.*]] = llvm.shufflevector %[[boundVecInsert]]
+//       CHECK: %[[mask:.*]] = arith.cmpi slt, %[[linearIndex]], %[[boundVect]]
+//  CHECK-SAME: : vector<[17]xi32>
+//
+// 4. Create pass-through vector.
+//       CHECK: %[[PASS_THROUGH:.*]] = arith.constant dense<7.{{.*}}> : vector<[17]xf32>
+//
+// 5. Bitcast to vector form.
+//       CHECK: %[[gep:.*]] = llvm.getelementptr %{{.*}} :
+//  CHECK-SAME: (!llvm.ptr, i64) -> !llvm.ptr, f32
+//
+// 6. Rewrite as a masked read.
+//       CHECK: %[[loaded:.*]] = llvm.intr.masked.load %[[gep]], %[[mask]],
+//  CHECK-SAME: %[[PASS_THROUGH]] {alignment = 4 : i32} :
+//  CHECK-SAME: -> vector<[17]xf32>
+//
+// 1. Let dim be the memref dimension, compute the in-bound index (dim - offset)
+//       CHECK: %[[C0_b:.*]] = arith.constant 0 : index
+//       CHECK: %[[DIM_b:.*]] = memref.dim %[[MEM]], %[[C0_b]] : memref<?xf32>
+//       CHECK: %[[BOUND_b:.*]] = arith.subi %[[DIM_b]], %[[BASE]] : index
+//
+// 2. Create a vector with linear indices [ 0 .. vector_length - 1 ].
+//       CHECK: %[[linearIndex_b:.*]] = llvm.intr.stepvector : vector<[17]xi32>
+//
+// 3. Create bound vector to compute in-bound mask:
+//    [ 0 .. vector_length - 1 ] < [ dim - offset .. dim - offset ]
+//       CHECK: %[[btrunc_b:.*]] = arith.index_cast %[[BOUND_b]] : index to i32
+//       CHECK: %[[boundVecInsert_b:.*]] = llvm.insertelement %[[btrunc_b]]
+//       CHECK: %[[boundVect_b:.*]] = llvm.shufflevector %[[boundVecInsert_b]]
+//       CHECK: %[[mask_b:.*]] = arith.cmpi slt, %[[linearIndex_b]],
+//  CHECK-SAME: %[[boundVect_b]] : vector<[17]xi32>
+//
+// 4. Bitcast to vector form.
+//       CHECK: %[[gep_b:.*]] = llvm.getelementptr {{.*}} :
+//  CHECK-SAME: (!llvm.ptr, i64) -> !llvm.ptr, f32
+//
+// 5. Rewrite as a masked write.
+//       CHECK: llvm.intr.masked.store %[[loaded]], %[[gep_b]], %[[mask_b]]
+//  CHECK-SAME: {alignment = 4 : i32} :
+//  CHECK-SAME: vector<[17]xf32>, vector<[17]xi1> into !llvm.ptr
+
 // -----
 
-func.func @transfer_read_index_1d(%A : memref<?xindex>, %base: index) -> vector<17xindex> {
+func.func @transfer_read_write_index_1d(%A : memref<?xindex>, %base: index) -> vector<17xindex> {
   %f7 = arith.constant 7: index
   %f = vector.transfer_read %A[%base], %f7
       {permutation_map = affine_map<(d0) -> (d0)>} :
@@ -2461,7 +2529,7 @@ func.func @transfer_read_index_1d(%A : memref<?xindex>, %base: index) -> vector<
     vector<17xindex>, memref<?xindex>
   return %f: vector<17xindex>
 }
-// CHECK-LABEL: func @transfer_read_index_1d
+// CHECK-LABEL: func @transfer_read_write_index_1d
 //  CHECK-SAME: %[[BASE:[a-zA-Z0-9]*]]: index) -> vector<17xindex>
 //       CHECK: %[[SPLAT:.*]] = arith.constant dense<7> : vector<17xindex>
 //       CHECK: %{{.*}} = builtin.unrealized_conversion_cast %[[SPLAT]] : vector<17xindex> to vector<17xi64>
@@ -2472,6 +2540,27 @@ func.func @transfer_read_index_1d(%A : memref<?xindex>, %base: index) -> vector<
 //       CHECK: llvm.intr.masked.store %[[loaded]], %{{.*}}, %{{.*}} {alignment = 8 : i32} :
 //  CHECK-SAME: vector<17xi64>, vector<17xi1> into !llvm.ptr
 
+func.func @transfer_read_write_index_1d_scalable(%A : memref<?xindex>, %base: index) -> vector<[17]xindex> {
+  %f7 = arith.constant 7: index
+  %f = vector.transfer_read %A[%base], %f7
+      {permutation_map = affine_map<(d0) -> (d0)>} :
+    memref<?xindex>, vector<[17]xindex>
+  vector.transfer_write %f, %A[%base]
+      {permutation_map = affine_map<(d0) -> (d0)>} :
+    vector<[17]xindex>, memref<?xindex>
+  return %f: vector<[17]xindex>
+}
+// CHECK-LABEL: func @transfer_read_write_index_1d
+//  CHECK-SAME: %[[BASE:[a-zA-Z0-9]*]]: index) -> vector<[17]xindex>
+//       CHECK: %[[SPLAT:.*]] = arith.constant dense<7> : vector<[17]xindex>
+//       CHECK: %{{.*}} = builtin.unrealized_conversion_cast %[[SPLAT]] : vector<[17]xindex> to vector<[17]xi64>
+
+//       CHECK: %[[loaded:.*]] = llvm.intr.masked.load %{{.*}}, %{{.*}}, %{{.*}} {alignment = 8 : i32} :
+//  CHECK-SAME: (!llvm.ptr, vector<[17]xi1>, vector<[17]xi64>) -> vector<[17]xi64>
+
+//       CHECK: llvm.intr.masked.store %[[loaded]], %{{.*}}, %{{.*}} {alignment = 8 : i32} :
+//  CHECK-SAME: vector<[17]xi64>, vector<[17]xi1> into !llvm.ptr
+
 // -----
 
 func.func @transfer_read_2d_to_1d(%A : memref<?x?xf32>, %base0: index, %base1: index) -> vector<17xf32> {
@@ -2501,9 +2590,34 @@ func.func @transfer_read_2d_to_1d(%A : memref<?x?xf32>, %base0: index, %base1: i
 //       CHECK: %[[boundVect:.*]] = llvm.shufflevector %[[boundVecInsert]]
 //       CHECK: %[[mask:.*]] = arith.cmpi slt, %[[linearIndex]], %[[boundVect]]
 
+func.func @transfer_read_2d_to_1d_scalable(%A : memref<?x?xf32>, %base0: index, %base1: index) -> vector<[17]xf32> {
+  %f7 = arith.constant 7.0: f32
+  %f = vector.transfer_read %A[%base0, %base1], %f7
+      {permutation_map = affine_map<(d0, d1) -> (d1)>} :
+    memref<?x?xf32>, vector<[17]xf32>
+  return %f: vector<[17]xf32>
+}
+// CHECK-LABEL: func @transfer_read_2d_to_1d
+//  CHECK-SAME: %[[BASE_0:[a-zA-Z0-9]*]]: index, %[[BASE_1:[a-zA-Z0-9]*]]: index) -> vector<[17]xf32>
+//       CHECK: %[[c1:.*]] = arith.constant 1 : index
+//       CHECK: %[[DIM:.*]] = memref.dim %{{.*}}, %[[c1]] : memref<?x?xf32>
+//
+// Compute the in-bound index (dim - offset)
+//       CHECK: %[[BOUND:.*]] = arith.subi %[[DIM]], %[[BASE_1]] : index
+//
+// Create a vector with linear indices [ 0 .. vector_length - 1 ].
+//       CHECK: %[[linearIndex:.*]] = llvm.intr.stepvector : vector<[17]xi32>
+//
+// Create bound vector to compute in-bound mask:
+//    [ 0 .. vector_length - 1 ] < [ dim - offset .. dim - offset ]
+//       CHECK: %[[btrunc:.*]] = arith.index_cast %[[BOUND]] : index to i32
+//       CHECK: %[[boundVecInsert:.*]] = llvm.insertelement %[[btrunc]]
+//       CHECK: %[[boundVect:.*]] = llvm.shufflevector %[[boundVecInsert]]
+//       CHECK: %[[mask:.*]] = arith.cmpi slt, %[[linearIndex]], %[[boundVect]]
+
 // -----
 
-func.func @transfer_read_1d_non_zero_addrspace(%A : memref<?xf32, 3>, %base: index) -> vector<17xf32> {
+func.func @transfer_read_write_1d_non_zero_addrspace(%A : memref<?xf32, 3>, %base: index) -> vector<17xf32> {
   %f7 = arith.constant 7.0: f32
   %f = vector.transfer_read %A[%base], %f7
       {permutation_map = affine_map<(d0) -> (d0)>} :
@@ -2513,7 +2627,7 @@ func.func @transfer_read_1d_non_zero_addrspace(%A : memref<?xf32, 3>, %base: ind
     vector<17xf32>, memref<?xf32, 3>
   return %f: vector<17xf32>
 }
-// CHECK-LABEL: func @transfer_read_1d_non_zero_addrspace
+// CHECK-LABEL: func @transfer_read_write_1d_non_zero_addrspace
 //  CHECK-SAME: %[[BASE:[a-zA-Z0-9]*]]: index) -> vector<17xf32>
 //
 // 1. Check address space for GEP is correct.
@@ -2528,6 +2642,31 @@ func.func @transfer_read_1d_non_zero_addrspace(%A : memref<?xf32, 3>, %base: ind
 //       CHECK: %[[gep_b:.*]] = llvm.getelementptr {{.*}} :
 //  CHECK-SAME: (!llvm.ptr<3>, i64) -> !llvm.ptr<3>, f32
 
+func.func @transfer_read_write_1d_non_zero_addrspace_scalable(%A : memref<?xf32, 3>, %base: index) -> vector<[17]xf32> {
+  %f7 = arith.constant 7.0: f32
+  %f = vector.transfer_read %A[%base], %f7
+      {permutation_map = affine_map<(d0) -> (d0)>} :
+    memref<?xf32, 3>, vector<[17]xf32>
+  vector.transfer_write %f, %A[%base]
+      {permutation_map = affine_map<(d0) -> (d0)>} :
+    vector<[17]xf32>, memref<?xf32, 3>
+  return %f: vector<[17]xf32>
+}
+// CHECK-LABEL: func @transfer_read_write_1d_non_zero_addrspace_scalable
+//  CHECK-SAME: %[[BASE:[a-zA-Z0-9]*]]: index) -> vector<[17]xf32>
+//
+// 1. Check address space for GEP is correct.
+//       CHECK: %[[gep:.*]] = llvm.getelementptr {{.*}} :
+//  CHECK-SAME: (!llvm.ptr<3>, i64) -> !llvm.ptr<3>, f32
+//
+// 2. Check address space of the memref is correct.
+//       CHECK: %[[c0:.*]] = arith.constant 0 : index
+//       CHECK: %[[DIM:.*]] = memref.dim %{{.*}}, %[[c0]] : memref<?xf32, 3>
+//
+// 3. Check address space for GEP is correct.
+//       CHECK: %[[gep_b:.*]] = llvm.getelementptr {{.*}} :
+//  CHECK-SAME: (!llvm.ptr<3>, i64) -> !llvm.ptr<3>, f32
+
 // -----
 
 func.func @transfer_read_1d_inbounds(%A : memref<?xf32>, %base: index) -> vector<17xf32> {
@@ -2546,51 +2685,71 @@ func.func @transfer_read_1d_inbounds(%A : memref<?xf32>, %base: index) -> vector
 // 2. Rewrite as a load.
 //       CHECK: %[[loaded:.*]] = llvm.load %[[gep]] {alignment = 4 : i64} : !llvm.ptr -> vector<17xf32>
 
+func.func @transfer_read_1d_inbounds_scalable(%A : memref<?xf32>, %base: index) -> vector<[17]xf32> {
+  %f7 = arith.constant 7.0: f32
+  %f = vector.transfer_read %A[%base], %f7 {in_bounds = [true]} :
+    memref<?xf32>, vector<[17]xf32>
+  return %f: vector<[17]xf32>
+}
+// CHECK-LABEL: func @transfer_read_1d_inbounds_scalable
+//  CHECK-SAME: %[[BASE:[a-zA-Z0-9]*]]: index) -> vector<[17]xf32>
+//
+// 1. Bitcast to vector form.
+//       CHECK: %[[gep:.*]] = llvm.getelementptr {{.*}} :
+//  CHECK-SAME: (!llvm.ptr, i64) -> !llvm.ptr, f32
+//
+// 2. Rewrite as a load.
+//       CHECK: %[[loaded:.*]] = llvm.load %[[gep]] {alignment = 4 : i64} : !llvm.ptr -> vector<[17]xf32>
+
 // -----
 
-// CHECK-LABEL: func @transfer_read_1d_mask
+// CHECK-LABEL: func @transfer_read_write_1d_mask
 // CHECK: %[[mask1:.*]] = arith.constant dense<[false, false, true, false, true]>
 // CHECK: %[[cmpi:.*]] = arith.cmpi slt
 // CHECK: %[[mask2:.*]] = arith.andi %[[cmpi]], %[[mask1]]
 // CHECK: %[[r:.*]] = llvm.intr.masked.load %{{.*}}, %[[mask2]]
+// CHECK: %[[cmpi_1:.*]] = arith.cmpi slt
+// CHECK: %[[mask3:.*]] = arith.andi %[[cmpi_1]], %[[mask1]]
+// CHECK: llvm.intr.masked.store %[[r]], %{{.*}}, %[[mask3]]
 // CHECK: return %[[r]]
-func.func @transfer_read_1d_mask(%A : memref<?xf32>, %base : index) -> vector<5xf32> {
+func.func @transfer_read_write_1d_mask(%A : memref<?xf32>, %base : index) -> vector<5xf32> {
   %m = arith.constant dense<[0, 0, 1, 0, 1]> : vector<5xi1>
   %f7 = arith.constant 7.0: f32
   %f = vector.transfer_read %A[%base], %f7, %m : memref<?xf32>, vector<5xf32>
+  vector.transfer_write %f, %A[%base], %m : vector<5xf32>, memref<?xf32>
   return %f: vector<5xf32>
 }
 
-// -----
-
-// CHECK-LABEL: func @transfer_read_1d_scalable_mask
-// CHECK: %[[passtru:.*]] = arith.constant dense<0.000000e+00> : vector<[4]xf32>
-// CHECK: %[[r:.*]] = llvm.intr.masked.load %{{.*}}, %{{.*}}, %[[passtru]] {alignment = 4 : i32} : (!llvm.ptr, vector<[4]xi1>, vector<[4]xf32>) -> vector<[4]xf32>
-// CHECK: return %[[r]] : vector<[4]xf32>
-func.func @transfer_read_1d_scalable_mask(%arg0: memref<1x?xf32>, %mask: vector<[4]xi1>) -> vector<[4]xf32> {
-  %c0 = arith.constant 0 : index
-  %pad = arith.constant 0.0 : f32
-  %vec = vector.transfer_read %arg0[%c0, %c0], %pad, %mask {in_bounds = [true]} : memref<1x?xf32>, vector<[4]xf32>
-  return %vec : vector<[4]xf32>
+// CHECK-LABEL: func @transfer_read_write_1d_mask_scalable
+// CHECK-SAME: %[[mask:[a-zA-Z0-9]*]]: vector<[5]xi1>
+// CHECK: %[[cmpi:.*]] = arith.cmpi slt
+// CHECK: %[[mask1:.*]] = arith.andi %[[cmpi]], %[[mask]]
+// CHECK: %[[r:.*]] = llvm.intr.masked.load %{{.*}}, %[[mask1]]
+// CHECK: %[[cmpi_1:.*]] = arith.cmpi slt
+// CHECK: %[[mask2:.*]] = arith.andi %[[cmpi_1]], %[[mask]]
+// CHECK: llvm.intr.masked.store %[[r]], %{{.*}}, %[[mask2]]
+// CHECK: return %[[r]]
+func.func @transfer_read_write_1d_mask_scalable(%A : memref<?xf32>, %base : index, %m : vector<[5]xi1>) -> vector<[5]xf32> {
+  %f7 = arith.constant 7.0: f32
+  %f = vector.transfer_read %A[%base], %f7, %m : memref<?xf32>, vector<[5]xf32>
+  vector.transfer_write %f, %A[%base], %m : vector<[5]xf32>, memref<?xf32>
+  return %f: vector<[5]xf32>
 }
 
 // -----
-// CHECK-LABEL: func @transfer_write_1d_scalable_mask
-// CHECK: llvm.intr.masked.store %{{.*}}, %{{.*}}, %{{.*}} {alignment = 4 : i32} : vector<[4]xf32>, vector<[4]xi1> into !llvm.ptr
-func.func @transfer_write_1d_scalable_mask(%arg0: memref<1x?xf32>, %vec: vector<[4]xf32>, %mask: vector<[4]xi1>) {
-  %c0 = arith.constant 0 : index
-  vector.transfer_write %vec, %arg0[%c0, %c0], %mask {in_bounds = [true]} : vector<[4]xf32>, memref<1x?xf32>
-  return
-}
 
-// -----
+// Can't lower xfer_read/xfer_write on tensors, but this shouldn't crash
 
-// CHECK-LABEL: func @transfer_write_tensor
+// CHECK-LABEL: func @transfer_read_write_tensor
+//       CHECK:   vector.transfer_read
 //       CHECK:   vector.transfer_write
-func.func @transfer_write_tensor(%arg0: vector<4xf32>,%arg1: tensor<?xf32>) -> tensor<?xf32> {
-  %c0 = arith.constant 0 : index
-  %0 = vector.transfer_write %arg0, %arg1[%c0] : vector<4xf32>, tensor<?xf32>
-  return %0 : tensor<?xf32>
+func.func @transfer_read_write_tensor(%A: tensor<?xf32>, %base : index) -> vector<4xf32> {
+  %f7 = arith.constant 7.0: f32
+  %c0 = arith.constant 0: index
+  %f = vector.transfer_read %A[%base], %f7 : tensor<?xf32>, vector<4xf32>
+  %w = vector.transfer_write %f, %A[%c0] : vector<4xf32>, tensor<?xf32>
+  "test.some_use"(%w) : (tensor<?xf32>) -> ()
+  return %f : vector<4xf32>
 }
 
 // -----