[Mlir-commits] [mlir] [mlir][tensor] Add e2e test for tensor.pack with dynamic tile sizes (PR #115698)

[Andrzej Warzyński]

================
@@ -0,0 +1,97 @@
+// DEFINE: %{compile} =  mlir-opt %s \
+// DEFINE: -transform-interpreter -test-transform-dialect-erase-schedule |\
+// DEFINE:  mlir-opt --test-linalg-transform-patterns="test-generalize-tensor-pack"\
+// DEFINE:    --test-transform-dialect-erase-schedule \
+// DEFINE:    -one-shot-bufferize="bufferize-function-boundaries" \
+// DEFINE:    -buffer-deallocation-pipeline="private-function-dynamic-ownership" \
+// DEFINE:    -cse -canonicalize -test-lower-to-llvm -o %t
+// DEFINE: %{entry_point} = main
+// DEFINE: %{run} = mlir-cpu-runner %t -e %{entry_point} -entry-point-result=void \
+// DEFINE:    -shared-libs=%mlir_runner_utils,%mlir_c_runner_utils
+
+// RUN: rm -f %t && %{compile} && %{run} | FileCheck %s
+
+/// End-to-end test for tensor.pack where one of the inner tile sizes is
+/// dynamic.
+///
+/// Note, ATM this is a relatively simple example, with no vectorization and
+/// the dynamic tile size being a compile-time constant. The intention is to
+/// incrementally expand the config to something much more complex.
+
+func.func @main() {
+  // Allocate and initialise the inputs
+  %A_alloc = tensor.empty() : tensor<7x16xi32>
+
+  %A = arith.constant dense<[
+    [ 1,  8, 15, 22, 29, 36, 43, 50, 57, 64, 71, 78, 85, 92, 99 , 106],
+    [ 2,  9, 16, 23, 30, 37, 44, 51, 58, 65, 72, 79, 86, 93, 100, 107],
+    [ 3, 10, 17, 24, 31, 38, 45, 52, 59, 66, 73, 80, 87, 94, 101, 108],
+    [ 4, 11, 18, 25, 32, 39, 46, 53, 60, 67, 74, 81, 88, 95, 102, 109],
+    [ 5, 12, 19, 26, 33, 40, 47, 54, 61, 68, 75, 82, 89, 96, 103, 110],
+    [ 6, 13, 20, 27, 34, 41, 48, 55, 62, 69, 76, 83, 90, 97, 104, 111],
+    [ 7, 14, 21, 28, 35, 42, 49, 56, 63, 70, 77, 84, 91, 98, 105, 112]
+  ]> : tensor<7x16xi32>
+
+  func.call @pack(%A) : (tensor<7x16xi32>) -> ()
+
+  return
+}
+
+func.func private @pack(%A: tensor<7x16xi32>) {
+  %c1 = arith.constant 1 : index
+  %pad_val = arith.constant 123 : i32
+
+  // Dynamic tile size
+  %tile_size = arith.constant 8 : index
----------------
banach-space wrote:

That's the next step ;-) 

The PRs that I am listing in the summary where specifically for the case when the tile size is an SSA value that's a known compile-time constant. See e.g. this: https://github.com/llvm/llvm-project/pull/114315

So yes, you are right, this is not truly dynamic. But it's enough of a complication to have revealed numerous issues. 

https://github.com/llvm/llvm-project/pull/115698