[MLIR][Affine] Switch default option for affine data copy generate pass

The more common use of this pass for testing and other purposes is the
pointwise copy generation as opposed to DMA generation. Switch the
default pass option to pointwise copy generation for easier testing. NFC
otherwise.

Users who were relying on `generate-dma` to be on by default will have
to pass it explicitly: `-affine-data-copy-generate='generate-dma=1'`.

Author: bondhugula

mlir/include/mlir/Dialect/Affine/Passes.td

@@ -27,7 +27,7 @@ def AffineDataCopyGeneration : Pass<"affine-data-copy-generate", "func::FuncOp">
            /*default=*/"1",
            "Fast memory space identifier for copy generation (default: 1)">,
     Option<"generateDma", "generate-dma", "bool",
-           /*default=*/"true", "Generate DMA instead of point-wise copy">,
+           /*default=*/"false", "Generate DMA instead of point-wise copy">,
     Option<"minDmaTransferSize", "min-dma-transfer", "int",
            /*default=*/"1024",
            "Minimum DMA transfer size supported by the target in bytes">,

mlir/lib/Dialect/Affine/Transforms/AffineDataCopyGeneration.cpp

@@ -86,7 +86,7 @@ struct AffineDataCopyGeneration
 
 /// Generates copies for memref's living in 'slowMemorySpace' into newly created
 /// buffers in 'fastMemorySpace', and replaces memory operations to the former
-/// by the latter. Only load op's handled for now.
+/// by the latter.
 std::unique_ptr<OperationPass<func::FuncOp>>
 mlir::affine::createAffineDataCopyGenerationPass(
     unsigned slowMemorySpace, unsigned fastMemorySpace, unsigned tagMemorySpace,

mlir/test/Dialect/Affine/affine-data-copy.mlir

@@ -1,6 +1,6 @@
-// RUN: mlir-opt %s -split-input-file -affine-data-copy-generate="generate-dma=false fast-mem-space=0 skip-non-unit-stride-loops" | FileCheck %s
+// RUN: mlir-opt %s -split-input-file -affine-data-copy-generate="fast-mem-space=0 skip-non-unit-stride-loops" | FileCheck %s
 // Small buffer size to trigger fine copies.
-// RUN: mlir-opt %s -split-input-file -affine-data-copy-generate="generate-dma=false fast-mem-space=0 fast-mem-capacity=1" | FileCheck --check-prefix=CHECK-SMALL %s
+// RUN: mlir-opt %s -split-input-file -affine-data-copy-generate="fast-mem-space=0 fast-mem-capacity=1" | FileCheck --check-prefix=CHECK-SMALL %s
 
 // Test affine data copy with a memref filter. We use a test pass that invokes
 // affine data copy utility on the input loop nest.

mlir/test/Dialect/Affine/dma-generate.mlir

@@ -1,5 +1,5 @@
-// RUN: mlir-opt -allow-unregistered-dialect %s -split-input-file -affine-data-copy-generate="generate-dma fast-mem-space=2 skip-non-unit-stride-loops" -verify-diagnostics | FileCheck %s
-// RUN: mlir-opt -allow-unregistered-dialect %s -split-input-file -affine-data-copy-generate="generate-dma fast-mem-capacity=16 fast-mem-space=2" | FileCheck %s --check-prefix FAST-MEM-16KB
+// RUN: mlir-opt -allow-unregistered-dialect %s -split-input-file -affine-data-copy-generate="generate-dma=1 fast-mem-space=2 skip-non-unit-stride-loops" -verify-diagnostics | FileCheck %s
+// RUN: mlir-opt -allow-unregistered-dialect %s -split-input-file -affine-data-copy-generate="generate-dma=1 fast-mem-capacity=16 fast-mem-space=2" | FileCheck %s --check-prefix FAST-MEM-16KB
 
 // We run most test cases with -copy-skip-non-unit-stride-loops to allow testing
 // DMA generation at inner levels easily - since the DMA generation would