From a5f7480bd3a2bc90f777516e3153b3733dae1314 Mon Sep 17 00:00:00 2001
From: Andrzej Warzynski <andrzej.warzynski@arm.com>
Date: Thu, 14 Mar 2024 13:37:13 +0000
Subject: [PATCH 1/2] [mlir][SVE] Add e2e for 1D depthwise WC convolution

Follow-up for #81625
---
 .../Linalg/CPU/ArmSVE/1d-depthwise-conv.mlir  | 62 +++++++++++++++++++
 1 file changed, 62 insertions(+)
 create mode 100644 mlir/test/Integration/Dialect/Linalg/CPU/ArmSVE/1d-depthwise-conv.mlir

diff --git a/mlir/test/Integration/Dialect/Linalg/CPU/ArmSVE/1d-depthwise-conv.mlir b/mlir/test/Integration/Dialect/Linalg/CPU/ArmSVE/1d-depthwise-conv.mlir
new file mode 100644
index 0000000000000..97c6d1637c0c1
--- /dev/null
+++ b/mlir/test/Integration/Dialect/Linalg/CPU/ArmSVE/1d-depthwise-conv.mlir
@@ -0,0 +1,62 @@
+// DEFINE: %{compile} =  mlir-opt %s \
+// DEFINE:    -transform-interpreter -test-transform-dialect-erase-schedule \
+// DEFINE:    -one-shot-bufferize="bufferize-function-boundaries" -lower-vector-mask -cse -canonicalize -convert-vector-to-scf -arm-sve-legalize-vector-storage \
+// DEFINE:    -convert-vector-to-llvm="enable-arm-sve" -test-lower-to-llvm -o %t
+// DEFINE: %{entry_point} = conv
+// DEFINE: %{run} = %mcr_aarch64_cmd %t -e %{entry_point} -entry-point-result=void --march=aarch64 --mattr="+sve"\
+// DEFINE:    -shared-libs=%mlir_runner_utils,%mlir_c_runner_utils
+
+// RUN: %{compile} | %{run} | FileCheck %s
+
+func.func @conv() {
+  // Define input/output tensors
+  %input_init = tensor.empty() : tensor<1x8x6xi32>
+  %output_init = tensor.empty() : tensor<1x7x6xi32>
+
+  %five = arith.constant 5 : i32
+  %zero = arith.constant 0 : i32
+  %input = linalg.fill ins(%five : i32) outs(%input_init : tensor<1x8x6xi32>) -> tensor<1x8x6xi32>
+  %output = linalg.fill ins(%zero : i32) outs(%output_init : tensor<1x7x6xi32>) -> tensor<1x7x6xi32>
+
+  // Define the filter tensor
+  %filter = arith.constant dense<[
+    [ 1,  2, 3, 4, 5, 6],
+    [ 11, 12, 13, 14, 15, 16]
+  ]> : tensor<2x6xi32>
+
+  // static sizes -> dynamic sizes
+  %input_dyn = tensor.cast %input_init : tensor<1x8x6xi32> to tensor<1x8x?xi32>
+  %output_dyn = tensor.cast %output : tensor<1x7x6xi32> to tensor<1x7x?xi32>
+  %filter_dyn = tensor.cast %filter : tensor<2x6xi32> to tensor<2x?xi32>
+
+  // Run the convolution
+  %res = linalg.depthwise_conv_1d_nwc_wc
+    {dilations = dense<1> : vector<1xi64>,
+    strides = dense<1> : vector<1xi64>}
+    ins(%input_dyn, %filter_dyn : tensor<1x8x?xi32>, tensor<2x?xi32>)
+    outs(%output_dyn : tensor<1x7x?xi32>) -> tensor<1x7x?xi32>
+
+  // Print the results
+  // CHECK: SVE: START OF TEST OUTPUT
+  vector.print str "SVE: START OF TEST OUTPUT\n"
+
+  // CHECK-NEXT: Unranked Memref base@ = {{.*}} rank = 3 offset = 0 sizes = [1, 7, 6] strides = [42, 6, 1] data =
+  // CHECK-COUNT-7: [60, 70, 80, 90, 100, 110]
+  %xf = tensor.cast %res : tensor<1x7x?xi32> to tensor<*xi32>
+  call @printMemrefI32(%xf) : (tensor<*xi32>) -> ()
+
+  // CHECK-NEXT: SVE: END OF TEST OUTPUT
+  vector.print str "SVE: END OF TEST OUTPUT\n"
+
+  return
+}
+
+module attributes {transform.with_named_sequence} {
+  transform.named_sequence @__transform_main(%arg0: !transform.any_op {transform.readonly}) {
+    %0 = transform.structured.match ops{["linalg.depthwise_conv_1d_nwc_wc"]} in %arg0 : (!transform.any_op) -> !transform.any_op
+    transform.structured.vectorize %0 vector_sizes [1, 7, [8], 2] : !transform.any_op
+    transform.yield
+  }
+}
+
+func.func private @printMemrefI32(%ptr : tensor<*xi32>) attributes { llvm.emit_c_interface }

From 41de1a722ca810c0768d6fab446c3c82edeba228 Mon Sep 17 00:00:00 2001
From: Andrzej Warzynski <andrzej.warzynski@arm.com>
Date: Fri, 22 Mar 2024 14:06:54 +0000
Subject: [PATCH 2/2] fixup! [BOLT] Add BB index to BAT (#86044)

Simplify test
---
 .../Dialect/Linalg/CPU/ArmSVE/1d-depthwise-conv.mlir            | 2 --
 1 file changed, 2 deletions(-)

diff --git a/mlir/test/Integration/Dialect/Linalg/CPU/ArmSVE/1d-depthwise-conv.mlir b/mlir/test/Integration/Dialect/Linalg/CPU/ArmSVE/1d-depthwise-conv.mlir
index 97c6d1637c0c1..57d69383c2de6 100644
--- a/mlir/test/Integration/Dialect/Linalg/CPU/ArmSVE/1d-depthwise-conv.mlir
+++ b/mlir/test/Integration/Dialect/Linalg/CPU/ArmSVE/1d-depthwise-conv.mlir
@@ -31,8 +31,6 @@ func.func @conv() {
 
   // Run the convolution
   %res = linalg.depthwise_conv_1d_nwc_wc
-    {dilations = dense<1> : vector<1xi64>,
-    strides = dense<1> : vector<1xi64>}
     ins(%input_dyn, %filter_dyn : tensor<1x8x?xi32>, tensor<2x?xi32>)
     outs(%output_dyn : tensor<1x7x?xi32>) -> tensor<1x7x?xi32>