2026-09-06T12:40:58.765033Z  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 }
2026-09-06T12:40:59.376988Z  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 }
2026-09-06T12:41:00.041133Z  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))]
2026-09-06T12:41:00.048129Z  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=1587 success=true
2026-09-06T12:41:03.950407Z  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
2026-09-06T12:41:04.039168Z  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
2026-09-06T12:41:04.041307Z  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=3993 success=true
2026-09-06T12:41:04.041329Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}: lowered graph for package construction logical_shards=26696 exchange_phases=4
2026-09-06T12:41:04.041533Z  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
2026-09-06T12:41:04.042274Z  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=0 success=true
2026-09-06T12:41:04.042526Z  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
2026-09-06T12:41:04.044305Z  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
2026-09-06T12:41:04.192586Z  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=148 success=true
2026-09-06T12:41:04.543612Z  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
2026-09-06T12:41:04.543643Z  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=4149 selected_horizon=3777 endpoint_lower_bound=3408 lower_bound_gap=369 selected_kind="matching-waves" neighborhood_improvements=0
2026-09-06T12:41:04.556971Z  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=1243 row_words=76 horizon=3777
2026-09-06T12:41:08.001066Z  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
2026-09-06T12:41:08.001118Z  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=41529 selected_horizon=41529 endpoint_lower_bound=33408 lower_bound_gap=8121 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:41:08.042165Z  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=1335 row_words=262 horizon=41529
2026-09-06T12:41:08.795741Z  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
2026-09-06T12:41:08.795780Z  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=6265 selected_horizon=6265 endpoint_lower_bound=4560 lower_bound_gap=1705 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:41:08.824047Z  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=231 row_words=138 horizon=6265
2026-09-06T12:41:08.832713Z  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=4640 success=true
2026-09-06T12:41:09.448403Z  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=5 success=true
2026-09-06T12:41:09.448438Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}: allocated package support memory linked_end=317036 profile_bytes=132 exchange_table_bytes=1740 host_code_bytes=2400 generated_code_bytes=1544 code_address=319440 standard_ranges=[(409600, 524288)]
2026-09-06T12:41:09.553241Z  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=104 success=true
2026-09-06T12:41:09.567743Z  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
2026-09-06T12:41:09.723813Z  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
2026-09-06T12:41:09.729602Z  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
2026-09-06T12:41:09.729614Z  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=3777 selected_horizon=3777 endpoint_lower_bound=3408 lower_bound_gap=369 selected_kind="reused" neighborhood_improvements=0
2026-09-06T12:41:09.740864Z  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=1243 row_words=76 horizon=3777
2026-09-06T12:41:13.476289Z  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
2026-09-06T12:41:13.476334Z  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=41529 selected_horizon=41529 endpoint_lower_bound=33408 lower_bound_gap=8121 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:41:13.518315Z  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=1335 row_words=262 horizon=41529
2026-09-06T12:41:13.734946Z  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
2026-09-06T12:41:13.747395Z  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
2026-09-06T12:41:13.747413Z  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=6265 selected_horizon=6265 endpoint_lower_bound=4560 lower_bound_gap=1705 selected_kind="reused" neighborhood_improvements=0
2026-09-06T12:41:13.775231Z  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=231 row_words=138 horizon=6265
2026-09-06T12:41:13.782491Z  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=4229 success=true
2026-09-06T12:41:15.147449Z  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
2026-09-06T12:41:15.243748Z  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
2026-09-06T12:41:15.249927Z  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
2026-09-06T12:41:15.249940Z  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=3777 selected_horizon=3777 endpoint_lower_bound=3408 lower_bound_gap=369 selected_kind="reused" neighborhood_improvements=0
2026-09-06T12:41:15.261230Z  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=1243 row_words=76 horizon=3777
2026-09-06T12:41:19.158924Z  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
2026-09-06T12:41:19.158971Z  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=39504 selected_horizon=39504 endpoint_lower_bound=33408 lower_bound_gap=6096 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:41:19.202378Z  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=1335 row_words=262 horizon=39504
2026-09-06T12:41:19.414296Z  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
2026-09-06T12:41:19.427637Z  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
2026-09-06T12:41:19.427658Z  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=6265 selected_horizon=6265 endpoint_lower_bound=4560 lower_bound_gap=1705 selected_kind="reused" neighborhood_improvements=0
2026-09-06T12:41:19.455564Z  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=231 row_words=138 horizon=6265
2026-09-06T12:41:19.470156Z  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=58589 candidate_cycles=56564 row_bytes=1740 row_capacity=16320 accepted=true
2026-09-06T12:41:19.484002Z  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=5701 success=true
2026-09-06T12:41:19.815089Z  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=12 success=true
2026-09-06T12:41:19.825128Z  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=10 success=true
2026-09-06T12:41:19.915818Z  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=86 success=true
2026-09-06T12:41:19.983929Z  INFO writing application package tiles=1472
2026-09-06T12:41:20.012009Z  INFO application package written
2026-09-06T12:41:20.012805Z  INFO reading application package
2026-09-06T12:41:20.097404Z  INFO application package read tiles=1472 compiler=0.1.0
2026-09-06T12:41:20.097822Z  INFO waiting for hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/alternatives-followup/device.lock
2026-09-06T12:41:34.500277Z  INFO acquired hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/alternatives-followup/device.lock
2026-09-06T12:41:34.500332Z  INFO opening IPU device path="/dev/ipu0"
2026-09-06T12:41:34.500426Z  INFO IPU device attached path=/dev/ipu0
2026-09-06T12:41:34.500433Z  INFO initializing IPU device
2026-09-06T12:41:34.508564Z  INFO IPU device initialized
2026-09-06T12:41:34.508603Z  INFO replaying device configuration register_writes=2003
2026-09-06T12:41:34.518166Z  INFO loading application tile_count=1472 final_mark=23
2026-09-06T12:41:34.786081Z  INFO application loaded and initial synchronization completed tile_count=1472
2026-09-06T12:41:37.155492Z  INFO starting host exchange session startup_mark=23
2026-09-06T12:41:37.155523Z  INFO attaching host exchange pages pages=2
2026-09-06T12:41:37.156033Z  INFO host exchange session started
2026-09-06T12:41:37.156085Z  INFO invoking streaming host exchange call call="initialize" command=0 phases=14
2026-09-06T12:41:37.161460Z  INFO invoking streaming host exchange call call="run" command=0 phases=59
profile=artifacts/layout-sweep/alternatives-followup/mapping-transpose-92-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=188346 minimumTileCycles=177768 deviceMicroseconds=125.564 effectiveGemmTflops=115.146 peakTflops=282.624 efficiencyPercent=40.74 maximumAbsoluteError=0.011719
package=artifacts/layout-sweep/alternatives-followup/mapping-transpose-92-mixed/model.ipuexe tiles=1472 hardwareTest=PASS