2026-09-06T12:40:15.856010Z  INFO applied GEMM plan constraint source_operation=0 matching_plans=1 constraint=GemmPlanConstraint { source_operation: 0, orientation: Normal, row_partitions: 4, column_partitions: 92, inner_partitions: 4, result_row_partitions: 4, result_column_partitions: 1, output_column_block: 48, weight_memory_class: Ipu21Interleaved, reduction_staging: Complete, local_weight_staging: Direct }
2026-09-06T12:40:16.415774Z  INFO applied GEMM plan constraint source_operation=2 matching_plans=1 constraint=GemmPlanConstraint { source_operation: 2, orientation: Normal, row_partitions: 4, column_partitions: 24, inner_partitions: 15, result_row_partitions: 5, result_column_partitions: 3, output_column_block: 48, weight_memory_class: Ipu21Standard, reduction_staging: Complete, local_weight_staging: Direct }
2026-09-06T12:40:17.005326Z  INFO retained operator-plan finalist finalist=0 values=7 operations=4 estimated_cycles=258236 estimated_exchange_cycles=122840 exchange_row_bytes=26984 peak_standard_bytes=169320 peak_interleaved_bytes=60416 peak_total_bytes=229736 maximum_standard_allocation_bytes=114688 active_tile_counts={1440, 1472} padding_group_counts={} conversion_sources=[Some(OperationId(2))]
2026-09-06T12:40:17.012153Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_mid"}: package build phase finished phase="lower_mid" elapsed_ms=1463 success=true
2026-09-06T12:40:20.712417Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="select_finalist"}: selected analytical operator plan estimated_cycles=186526 estimated_exchange_cycles=65184
2026-09-06T12:40:20.844896Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="select_finalist"}: eliminated finite GEMM padding clears using load-time SRAM initialization removed=72
2026-09-06T12:40:20.848144Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="select_finalist"}: package build phase finished phase="select_finalist" elapsed_ms=3835 success=true
2026-09-06T12:40:20.848177Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}: lowered graph for package construction logical_shards=26696 exchange_phases=4
2026-09-06T12:40:20.848412Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="compile_runtime"}: package build phase finished phase="compile_runtime" elapsed_ms=0 success=true
2026-09-06T12:40:20.849761Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="plan_kernels"}: package build phase finished phase="plan_kernels" elapsed_ms=1 success=true
2026-09-06T12:40:20.850030Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="compile_kernels"}: package build phase finished phase="compile_kernels" elapsed_ms=0 success=true
2026-09-06T12:40:20.852501Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="link_runtime"}: package build phase finished phase="link_runtime" elapsed_ms=0 success=true
2026-09-06T12:40:21.300821Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="plan_exchange_storage"}: package build phase finished phase="plan_exchange_storage" elapsed_ms=448 success=true
2026-09-06T12:40:22.237542Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges_provisional"}: prepared large physical exchange phase phase=1 transfers=15064 maximum_identical_destinations=1
2026-09-06T12:40:22.237589Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges_provisional"}: optimized physical exchange schedule phase=1 initial_horizon=4492 selected_horizon=3807 endpoint_lower_bound=3408 lower_bound_gap=399 selected_kind="matching-waves" neighborhood_improvements=0
2026-09-06T12:40:22.251254Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges_provisional"}: finished large physical exchange phase phase=1 tile=1230 row_words=75 horizon=3807
2026-09-06T12:40:26.255888Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges_provisional"}: prepared large physical exchange phase phase=2 transfers=5562 maximum_identical_destinations=1
2026-09-06T12:40:26.255965Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges_provisional"}: optimized physical exchange schedule phase=2 initial_horizon=48919 selected_horizon=48919 endpoint_lower_bound=33408 lower_bound_gap=15511 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:40:26.304602Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges_provisional"}: finished large physical exchange phase phase=2 tile=795 row_words=254 horizon=48919
2026-09-06T12:40:27.188588Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges_provisional"}: prepared large physical exchange phase phase=3 transfers=24760 maximum_identical_destinations=1
2026-09-06T12:40:27.188641Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges_provisional"}: optimized physical exchange schedule phase=3 initial_horizon=6478 selected_horizon=6478 endpoint_lower_bound=4560 lower_bound_gap=1918 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:40:27.216166Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges_provisional"}: finished large physical exchange phase phase=3 tile=403 row_words=129 horizon=6478
2026-09-06T12:40:27.228975Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges_provisional"}: package build phase finished phase="lower_exchanges_provisional" elapsed_ms=5928 success=true
2026-09-06T12:40:27.873858Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="size_tile_code"}: package build phase finished phase="size_tile_code" elapsed_ms=7 success=true
2026-09-06T12:40:27.873922Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}: allocated package support memory linked_end=317036 profile_bytes=132 exchange_table_bytes=1784 host_code_bytes=2400 generated_code_bytes=1504 code_address=319440 standard_ranges=[(409600, 524288)]
2026-09-06T12:40:28.002927Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="place_storage"}: package build phase finished phase="place_storage" elapsed_ms=128 success=true
2026-09-06T12:40:28.011736Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=0
2026-09-06T12:40:28.126288Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=1
2026-09-06T12:40:28.134053Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: prepared large physical exchange phase phase=1 transfers=15064 maximum_identical_destinations=1
2026-09-06T12:40:28.134097Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: optimized physical exchange schedule phase=1 initial_horizon=3807 selected_horizon=3807 endpoint_lower_bound=3408 lower_bound_gap=399 selected_kind="reused" neighborhood_improvements=0
2026-09-06T12:40:28.153604Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: finished large physical exchange phase phase=1 tile=1230 row_words=75 horizon=3807
2026-09-06T12:40:32.770311Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: prepared large physical exchange phase phase=2 transfers=5562 maximum_identical_destinations=1
2026-09-06T12:40:32.770374Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: optimized physical exchange schedule phase=2 initial_horizon=48919 selected_horizon=48919 endpoint_lower_bound=33408 lower_bound_gap=15511 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:40:32.818640Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: finished large physical exchange phase phase=2 tile=795 row_words=254 horizon=48919
2026-09-06T12:40:33.084352Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=3
2026-09-06T12:40:33.100429Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: prepared large physical exchange phase phase=3 transfers=24760 maximum_identical_destinations=1
2026-09-06T12:40:33.100454Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: optimized physical exchange schedule phase=3 initial_horizon=6478 selected_horizon=6478 endpoint_lower_bound=4560 lower_bound_gap=1918 selected_kind="reused" neighborhood_improvements=0
2026-09-06T12:40:33.133969Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: finished large physical exchange phase phase=3 tile=403 row_words=129 horizon=6478
2026-09-06T12:40:33.144503Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: package build phase finished phase="lower_exchanges" elapsed_ms=5141 success=true
2026-09-06T12:40:35.382764Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: reused exchange optimization after validating relocated rows phase=0
2026-09-06T12:40:35.613241Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: reused exchange optimization after validating relocated rows phase=1
2026-09-06T12:40:35.623588Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: prepared large physical exchange phase phase=1 transfers=15064 maximum_identical_destinations=1
2026-09-06T12:40:35.623611Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: optimized physical exchange schedule phase=1 initial_horizon=3807 selected_horizon=3807 endpoint_lower_bound=3408 lower_bound_gap=399 selected_kind="reused" neighborhood_improvements=0
2026-09-06T12:40:35.646528Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: finished large physical exchange phase phase=1 tile=1230 row_words=75 horizon=3807
2026-09-06T12:40:40.738482Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: prepared large physical exchange phase phase=2 transfers=5562 maximum_identical_destinations=1
2026-09-06T12:40:40.738540Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: optimized physical exchange schedule phase=2 initial_horizon=40549 selected_horizon=40549 endpoint_lower_bound=33408 lower_bound_gap=7141 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:40:40.790384Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: finished large physical exchange phase phase=2 tile=795 row_words=265 horizon=40549
2026-09-06T12:40:41.034339Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: reused exchange optimization after validating relocated rows phase=3
2026-09-06T12:40:41.050821Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: prepared large physical exchange phase phase=3 transfers=24760 maximum_identical_destinations=1
2026-09-06T12:40:41.050849Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: optimized physical exchange schedule phase=3 initial_horizon=6478 selected_horizon=6478 endpoint_lower_bound=4560 lower_bound_gap=1918 selected_kind="reused" neighborhood_improvements=0
2026-09-06T12:40:41.078247Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: finished large physical exchange phase phase=3 tile=403 row_words=129 horizon=6478
2026-09-06T12:40:41.096712Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: evaluated exchange placement finalist offset=28672 baseline_score=170111729664 score=151709220864 baseline_cycles=66239 candidate_cycles=57869 row_bytes=1780 row_capacity=16320 accepted=true
2026-09-06T12:40:41.112034Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: package build phase finished phase="optimize_exchange_placement" elapsed_ms=7967 success=true
2026-09-06T12:40:41.443239Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="prepare_tile_code"}: package build phase finished phase="prepare_tile_code" elapsed_ms=20 success=true
2026-09-06T12:40:41.456493Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="emit_tile_code"}: package build phase finished phase="emit_tile_code" elapsed_ms=13 success=true
2026-09-06T12:40:41.558480Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="build_tile_images"}: package build phase finished phase="build_tile_images" elapsed_ms=95 success=true
2026-09-06T12:40:41.648927Z  INFO writing application package tiles=1472
2026-09-06T12:40:41.694079Z  INFO application package written
2026-09-06T12:40:41.694878Z  INFO reading application package
2026-09-06T12:40:41.790970Z  INFO application package read tiles=1472 compiler=0.1.0
2026-09-06T12:40:41.791674Z  INFO waiting for hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/alternatives-followup/device.lock
2026-09-06T12:40:41.791687Z  INFO acquired hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/alternatives-followup/device.lock
2026-09-06T12:40:41.791693Z  INFO opening IPU device path="/dev/ipu0"
2026-09-06T12:40:41.791753Z  INFO IPU device attached path=/dev/ipu0
2026-09-06T12:40:41.791756Z  INFO initializing IPU device
2026-09-06T12:40:41.799871Z  INFO IPU device initialized
2026-09-06T12:40:41.799877Z  INFO replaying device configuration register_writes=2003
2026-09-06T12:40:41.809683Z  INFO loading application tile_count=1472 final_mark=23
2026-09-06T12:40:42.105799Z  INFO application loaded and initial synchronization completed tile_count=1472
2026-09-06T12:40:45.308060Z  INFO starting host exchange session startup_mark=23
2026-09-06T12:40:45.308101Z  INFO attaching host exchange pages pages=2
2026-09-06T12:40:45.308502Z  INFO host exchange session started
2026-09-06T12:40:45.308567Z  INFO invoking streaming host exchange call call="initialize" command=0 phases=14
2026-09-06T12:40:45.315888Z  INFO invoking streaming host exchange call call="run" command=0 phases=59
profile=artifacts/layout-sweep/alternatives-followup/mapping-block-360-24-mixed/execution.ipuprofile tiles=1472 samples=24596
workload=siglip-mlp-f16-b1-t729-d1152-h4304-n1 benchmark=siglip-mlp-f16 batch=1 tokens=729 rows=729 dimension=1152 hiddenDimension=4304 blocks=1 biases=false activeTiles=1440 executionTiles=1472 inputBytes=154736640 weightBytes=19869696 cycles=191004 minimumTileCycles=180216 deviceMicroseconds=127.336 effectiveGemmTflops=113.543 peakTflops=282.624 efficiencyPercent=40.17 maximumAbsoluteError=0.011719
package=artifacts/layout-sweep/alternatives-followup/mapping-block-360-24-mixed/model.ipuexe tiles=1472 hardwareTest=PASS