Add pass to assign tiles to logical objectFifo

nod-ai · Nov 21, 2024 · faf94d8 · faf94d8
1 parent a528a85
commit faf94d8
Show file tree

Hide file tree

Showing 17 changed files with 963 additions and 334 deletions.
diff --git a/...target/AMD-AIE/iree-amd-aie/Test/samples/matmul_elementwise_pack_peel_objectfifo_e2e.mlir b/...target/AMD-AIE/iree-amd-aie/Test/samples/matmul_elementwise_pack_peel_objectfifo_e2e.mlir
@@ -13,7 +13,7 @@
 // CHECK-DAG:   aie.core(%[[TILE_0_3]])
 // CHECK-DAG:   aie.core(%[[TILE_1_3]])
 // CHECK-DAG:   aie.shim_dma_allocation {{.*}}(MM2S, 0, 0)
-// CHECK-DAG:   aie.shim_dma_allocation {{.*}}(MM2S, 1, 0)
+// CHECK-DAG:   aie.shim_dma_allocation {{.*}}(MM2S, 0, 1)
 // CHECK-DAG:   aie.memtile_dma(%[[TILE_0_1]])
 // CHECK-DAG:   aie.mem(%[[TILE_0_2]])
 // CHECK-DAG:   aie.mem(%[[TILE_0_3]])

diff --git a/compiler/plugins/target/AMD-AIE/iree-amd-aie/Test/samples/matmul_pack_peel_objectfifo.mlir b/compiler/plugins/target/AMD-AIE/iree-amd-aie/Test/samples/matmul_pack_peel_objectfifo.mlir
@@ -1,6 +1,6 @@
 // This pipeline is obtained by going into Passes.cpp, and dumping the pass pipeline (at the end of addAMDAIEObjectFifoLoweringPasses) using `passManager.dump()`. This test is included, as it can be useful to have a reference in IR of all the passes that are run.
 
-// RUN: iree-opt --pass-pipeline="builtin.module(fold-memref-alias-ops,iree-amdaie-distribute-l1-allocations,iree-amdaie-convert-to-dma,iree-amdaie-normalize-loop-bounds,iree-amdaie-insert-cores,iree-amdaie-localize-logicalobjectfifo,cse,iree-amdaie-distribute-cores-and-objectfifos,cse,canonicalize{  max-iterations=10 max-num-rewrites=-1 region-simplify=normal test-convergence=false top-down=true},iree-amdaie-split-logical-objectfifos-for-connection-reuse,cse,canonicalize{  max-iterations=10 max-num-rewrites=-1 region-simplify=normal test-convergence=false top-down=true},iree-amdaie-dma-to-circular-dma,func.func(iree-amdaie-create-aie-workgroup),cse,iree-amdaie-dma-cse,iree-amdaie-hoist-logical-objectfifo,iree-amdaie-canonicalize-doubly-strided-op{fold-single-dims=false},iree-amdaie-flatten-logicalobjectfifo,iree-amdaie-assign-logical-objectfifo-depth{l1-buffer-depth=2 l2-buffer-depth=2 l3-buffer-depth=1},iree-amdaie-access-to-acquire-release,iree-amdaie-none-access-to-temporary-buffer,iree-amdaie-assign-connection-types,cse,canonicalize{  max-iterations=10 max-num-rewrites=-1 region-simplify=normal test-convergence=false top-down=true},iree-amdaie-dma-composition{only-zero-stride-on-outer-dim=true},cse,canonicalize{  max-iterations=10 max-num-rewrites=-1 region-simplify=normal test-convergence=false top-down=true},iree-amdaie-dma-cse,iree-amdaie-assign-npu-dma-bd-ids,cse,canonicalize{  max-iterations=10 max-num-rewrites=-1 region-simplify=normal test-convergence=false top-down=true},iree-amdaie-controlcode-loop-unroll,cse,canonicalize{  max-iterations=10 max-num-rewrites=-1 region-simplify=normal test-convergence=false top-down=true},iree-amdaie-dma-cse,iree-amdaie-canonicalize-doubly-strided-op{fold-single-dims=false},canonicalize{  max-iterations=10 max-num-rewrites=-1 region-simplify=normal test-convergence=false top-down=true},iree-amdaie-convert-core-forall-to-for,canonicalize{  max-iterations=10 max-num-rewrites=-1 region-simplify=normal test-convergence=false top-down=true},iree-amdaie-assign-channels,cse,canonicalize{  max-iterations=10 max-num-rewrites=-1 region-simplify=normal test-convergence=false top-down=true},iree-amdaie-objfifo-bufferization,iree-amdaie-connection-to-flow,iree-amdaie-assign-packet-ids,iree-amdaie-controlcode-lowering,iree-amdaie-controlcode-to-transaction,iree-amdaie-acquire-release-to-use-lock,iree-amdaie-canonicalize-npu-dma-cpy-nd{nb-dimensions=4},canonicalize{  max-iterations=10 max-num-rewrites=-1 region-simplify=normal test-convergence=false top-down=true},iree-amdaie-sink-into-core,canonicalize{  max-iterations=10 max-num-rewrites=-1 region-simplify=normal test-convergence=false top-down=true},iree-amdaie-lower-to-aie,iree-amdaie-remove-memoryspace)" --split-input-file %s | FileCheck %s
+// RUN: iree-opt --pass-pipeline="builtin.module(fold-memref-alias-ops,iree-amdaie-distribute-l1-allocations,iree-amdaie-convert-to-dma,iree-amdaie-normalize-loop-bounds,iree-amdaie-insert-cores,iree-amdaie-localize-logicalobjectfifo,cse,iree-amdaie-distribute-cores-and-objectfifos,cse,canonicalize{  max-iterations=10 max-num-rewrites=-1 region-simplify=normal test-convergence=false top-down=true},iree-amdaie-split-logical-objectfifos-for-connection-reuse,cse,canonicalize{  max-iterations=10 max-num-rewrites=-1 region-simplify=normal test-convergence=false top-down=true},iree-amdaie-assign-tiles,cse,canonicalize{  max-iterations=10 max-num-rewrites=-1 region-simplify=normal test-convergence=false top-down=true},iree-amdaie-dma-to-circular-dma,func.func(iree-amdaie-create-aie-workgroup),cse,iree-amdaie-dma-cse,iree-amdaie-hoist-logical-objectfifo,iree-amdaie-canonicalize-doubly-strided-op{fold-single-dims=false},iree-amdaie-flatten-logicalobjectfifo,iree-amdaie-assign-logical-objectfifo-depth{l1-buffer-depth=2 l2-buffer-depth=2 l3-buffer-depth=1},iree-amdaie-access-to-acquire-release,iree-amdaie-none-access-to-temporary-buffer,iree-amdaie-assign-connection-types,cse,canonicalize{  max-iterations=10 max-num-rewrites=-1 region-simplify=normal test-convergence=false top-down=true},iree-amdaie-dma-composition{only-zero-stride-on-outer-dim=true},cse,canonicalize{  max-iterations=10 max-num-rewrites=-1 region-simplify=normal test-convergence=false top-down=true},iree-amdaie-dma-cse,iree-amdaie-assign-npu-dma-bd-ids,cse,canonicalize{  max-iterations=10 max-num-rewrites=-1 region-simplify=normal test-convergence=false top-down=true},iree-amdaie-controlcode-loop-unroll,cse,canonicalize{  max-iterations=10 max-num-rewrites=-1 region-simplify=normal test-convergence=false top-down=true},iree-amdaie-dma-cse,iree-amdaie-canonicalize-doubly-strided-op{fold-single-dims=false},canonicalize{  max-iterations=10 max-num-rewrites=-1 region-simplify=normal test-convergence=false top-down=true},iree-amdaie-convert-core-forall-to-for,canonicalize{  max-iterations=10 max-num-rewrites=-1 region-simplify=normal test-convergence=false top-down=true},iree-amdaie-assign-channels,cse,canonicalize{  max-iterations=10 max-num-rewrites=-1 region-simplify=normal test-convergence=false top-down=true},iree-amdaie-objfifo-bufferization,iree-amdaie-connection-to-flow,iree-amdaie-assign-packet-ids,iree-amdaie-controlcode-lowering,iree-amdaie-controlcode-to-transaction,iree-amdaie-acquire-release-to-use-lock,iree-amdaie-canonicalize-npu-dma-cpy-nd{nb-dimensions=4},canonicalize{  max-iterations=10 max-num-rewrites=-1 region-simplify=normal test-convergence=false top-down=true},iree-amdaie-sink-into-core,canonicalize{  max-iterations=10 max-num-rewrites=-1 region-simplify=normal test-convergence=false top-down=true},iree-amdaie-lower-to-aie,iree-amdaie-remove-memoryspace)" --split-input-file %s | FileCheck %s
 
 
 
@@ -20,7 +20,7 @@
 // CHECK:         aie.use_lock
 // Check a bit of the aiex.runtime_sequence:
 // CHECK:       aiex.runtime_sequence @matmul_i32()
-// CHECK:       } {npu_instructions = dense_resource<npu_instructions> : tensor<174xui32>, runtime_sequence_name = "matmul_i32"}
+// CHECK:       } {npu_instructions = dense_resource<npu_instructions> : tensor<208xui32>, runtime_sequence_name = "matmul_i32"}
 
 #pipeline_layout = #hal.pipeline.layout<bindings= [
     #hal.pipeline.binding<storage_buffer, ReadOnly>,

diff --git a/...ler/plugins/target/AMD-AIE/iree-amd-aie/Test/samples/matmul_pack_peel_objectfifo_e2e.mlir b/...ler/plugins/target/AMD-AIE/iree-amd-aie/Test/samples/matmul_pack_peel_objectfifo_e2e.mlir
@@ -14,7 +14,7 @@
 // CHECK-DAG:   aie.core(%[[TILE_0_3]])
 // CHECK-DAG:   aie.core(%[[TILE_1_3]])
 // CHECK-DAG:   aie.shim_dma_allocation {{.*}}(MM2S, 0, 0)
-// CHECK-DAG:   aie.shim_dma_allocation {{.*}}(MM2S, 1, 0)
+// CHECK-DAG:   aie.shim_dma_allocation {{.*}}(MM2S, 0, 1)
 // CHECK-DAG:   aie.memtile_dma(%[[TILE_0_1]])
 // CHECK-DAG:   aie.mem(%[[TILE_0_2]])
 // CHECK-DAG:   aie.mem(%[[TILE_0_3]])

diff --git a/...ins/target/AMD-AIE/iree-amd-aie/Test/samples/matmul_pack_peel_objectfifo_ukernel_e2e.mlir b/...ins/target/AMD-AIE/iree-amd-aie/Test/samples/matmul_pack_peel_objectfifo_ukernel_e2e.mlir
@@ -15,7 +15,7 @@
 // PHOENIX-DAG:   aie.core(%[[TILE_0_3]])
 // PHOENIX-DAG:   aie.core(%[[TILE_1_3]])
 // PHOENIX-DAG:   aie.shim_dma_allocation {{.*}}(MM2S, 0, 0)
-// PHOENIX-DAG:   aie.shim_dma_allocation {{.*}}(MM2S, 1, 0)
+// PHOENIX-DAG:   aie.shim_dma_allocation {{.*}}(MM2S, 0, 1)
 // PHOENIX-DAG:   aie.memtile_dma(%[[TILE_0_1]])
 // PHOENIX-DAG:   aie.mem(%[[TILE_0_2]])
 // PHOENIX-DAG:   aie.mem(%[[TILE_0_3]])
@@ -39,7 +39,7 @@
 // STRIX-DAG:   aie.core(%[[TILE_0_3]])
 // STRIX-DAG:   aie.core(%[[TILE_1_3]])
 // STRIX-DAG:   aie.shim_dma_allocation {{.*}}(MM2S, 0, 0)
-// STRIX-DAG:   aie.shim_dma_allocation {{.*}}(MM2S, 1, 0)
+// STRIX-DAG:   aie.shim_dma_allocation {{.*}}(MM2S, 0, 1)
 // STRIX-DAG:   aie.memtile_dma(%[[TILE_0_1]])
 // STRIX-DAG:   aie.mem(%[[TILE_0_2]])
 // STRIX-DAG:   aie.mem(%[[TILE_0_3]])