2026-09-06T11:45:18.355274Z  INFO applied GEMM plan constraint source_operation=0 matching_plans=2 constraint=GemmPlanConstraint { source_operation: 0, orientation: Normal, row_partitions: 6, column_partitions: 54, inner_partitions: 4, result_row_partitions: 4, result_column_partitions: 1, output_column_block: 80, weight_memory_class: Ipu21Interleaved, reduction_staging: Complete, local_weight_staging: Direct }
2026-09-06T11:45:18.754460Z  INFO applied GEMM plan constraint source_operation=2 matching_plans=1 constraint=GemmPlanConstraint { source_operation: 2, orientation: Normal, row_partitions: 6, column_partitions: 24, inner_partitions: 10, result_row_partitions: 10, result_column_partitions: 1, output_column_block: 48, weight_memory_class: Ipu21Interleaved, reduction_staging: Complete, local_weight_staging: Direct }
2026-09-06T11:45:19.175992Z  INFO retained operator-plan finalist finalist=0 values=7 operations=4 estimated_cycles=349678 estimated_exchange_cycles=140920 exchange_row_bytes=31052 peak_standard_bytes=145740 peak_interleaved_bytes=133632 peak_total_bytes=246604 maximum_standard_allocation_bytes=114688 active_tile_counts={1296, 1440} padding_group_counts={} conversion_sources=[Some(OperationId(2))]
2026-09-06T11:45:19.179905Z  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=1118 success=true
2026-09-06T11:45:24.414128Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="select_finalist"}: selected analytical operator plan estimated_cycles=278297 estimated_exchange_cycles=79000
2026-09-06T11:45:24.477887Z  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=120
2026-09-06T11:45:24.479793Z  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=5299 success=true
2026-09-06T11:45:24.479822Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}: lowered graph for package construction logical_shards=24576 exchange_phases=4
2026-09-06T11:45:24.480066Z  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
2026-09-06T11:45:24.480851Z  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
2026-09-06T11:45:24.481285Z  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
2026-09-06T11:45:24.483627Z  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
2026-09-06T11:45:24.647587Z  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=163 success=true
2026-09-06T11:45:25.659966Z  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=23672 maximum_identical_destinations=1
2026-09-06T11:45:25.660019Z  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=4838 selected_horizon=4705 endpoint_lower_bound=4080 lower_bound_gap=625 selected_kind="critical-neighborhood" neighborhood_improvements=1
2026-09-06T11:45:25.679288Z  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=413 row_words=118 horizon=4705
2026-09-06T11:45:42.852450Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges_provisional"}: compared ordinary and paired exchange schedules phase=2 candidates=5967 ordinary_horizon=53206 paired_horizon=43263 use_paired=true
2026-09-06T11:45:42.988438Z  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=8252 maximum_identical_destinations=1
2026-09-06T11:45:42.988472Z  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=43263 selected_horizon=43263 endpoint_lower_bound=27432 lower_bound_gap=15831 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T11:45:43.056540Z  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=830 row_words=389 horizon=43263
2026-09-06T11:45:46.460904Z  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=41760 maximum_identical_destinations=1
2026-09-06T11:45:46.460957Z  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=5019 selected_horizon=4999 endpoint_lower_bound=3024 lower_bound_gap=1975 selected_kind="matching-waves" neighborhood_improvements=0
2026-09-06T11:45:46.499297Z  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=223 row_words=178 horizon=4999
2026-09-06T11:45:46.516923Z  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=21869 success=true
2026-09-06T11:45:46.949075Z  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
2026-09-06T11:45:46.949126Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}: allocated package support memory linked_end=319104 profile_bytes=168 exchange_table_bytes=2440 host_code_bytes=2196 generated_code_bytes=1676 code_address=321304 standard_ranges=[(409600, 524288)]
2026-09-06T11:45:47.057600Z  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=108 success=true
2026-09-06T11:45:47.068355Z  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
2026-09-06T11:45:47.242952Z  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
2026-09-06T11:45:47.253785Z  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=23672 maximum_identical_destinations=1
2026-09-06T11:45:47.253812Z  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=4705 selected_horizon=4705 endpoint_lower_bound=4080 lower_bound_gap=625 selected_kind="reused" neighborhood_improvements=0
2026-09-06T11:45:47.272069Z  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=413 row_words=118 horizon=4705
2026-09-06T11:46:00.142703Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: compared ordinary and paired exchange schedules phase=2 candidates=5967 ordinary_horizon=53206 paired_horizon=43263 use_paired=true
2026-09-06T11:46:00.220556Z  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=8252 maximum_identical_destinations=1
2026-09-06T11:46:00.220572Z  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=43263 selected_horizon=43263 endpoint_lower_bound=27432 lower_bound_gap=15831 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T11:46:00.259700Z  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=830 row_words=389 horizon=43263
2026-09-06T11:46:00.462828Z  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
2026-09-06T11:46:00.474225Z  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=41760 maximum_identical_destinations=1
2026-09-06T11:46:00.474236Z  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=4999 selected_horizon=4999 endpoint_lower_bound=3024 lower_bound_gap=1975 selected_kind="reused" neighborhood_improvements=0
2026-09-06T11:46:00.494807Z  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=223 row_words=178 horizon=4999
2026-09-06T11:46:00.501877Z  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=13444 success=true
2026-09-06T11:46:01.716409Z  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
2026-09-06T11:46:01.876869Z  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
2026-09-06T11:46:01.886836Z  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=23672 maximum_identical_destinations=1
2026-09-06T11:46:01.886851Z  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=4705 selected_horizon=4705 endpoint_lower_bound=4080 lower_bound_gap=625 selected_kind="reused" neighborhood_improvements=0
2026-09-06T11:46:01.904990Z  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=413 row_words=118 horizon=4705
2026-09-06T11:46:19.464427Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: compared ordinary and paired exchange schedules phase=2 candidates=5967 ordinary_horizon=41078 paired_horizon=34302 use_paired=true
2026-09-06T11:46:19.588989Z  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=8252 maximum_identical_destinations=1
2026-09-06T11:46:19.589022Z  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=34302 selected_horizon=34302 endpoint_lower_bound=27432 lower_bound_gap=6870 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T11:46:19.654178Z  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=830 row_words=387 horizon=34302
2026-09-06T11:46:19.985101Z  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
2026-09-06T11:46:20.003610Z  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=41760 maximum_identical_destinations=1
2026-09-06T11:46:20.003628Z  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=4999 selected_horizon=4999 endpoint_lower_bound=3024 lower_bound_gap=1975 selected_kind="reused" neighborhood_improvements=0
2026-09-06T11:46:20.039487Z  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=223 row_words=178 horizon=4999
2026-09-06T11:46:20.059988Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: evaluated exchange placement finalist offset=20480 baseline_score=673028849664 score=252092694528 baseline_cycles=64609 candidate_cycles=55648 row_bytes=2432 row_capacity=16320 accepted=true
2026-09-06T11:46:20.070622Z  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=19568 success=true
2026-09-06T11:46:20.288302Z  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=10 success=true
2026-09-06T11:46:20.299338Z  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=11 success=true
2026-09-06T11:46:20.402912Z  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=98 success=true
2026-09-06T11:46:20.453245Z  INFO writing application package tiles=1472
2026-09-06T11:46:20.509423Z  INFO application package written
2026-09-06T11:46:20.511739Z  INFO reading application package
2026-09-06T11:46:20.604586Z  INFO application package read tiles=1472 compiler=0.1.0
2026-09-06T11:46:20.606624Z  INFO waiting for hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/device.lock
2026-09-06T11:46:20.606634Z  INFO acquired hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/device.lock
2026-09-06T11:46:20.606639Z  INFO opening IPU device path="/dev/ipu0"
2026-09-06T11:46:20.606668Z  INFO IPU device attached path=/dev/ipu0
2026-09-06T11:46:20.606671Z  INFO initializing IPU device
2026-09-06T11:46:20.614744Z  INFO IPU device initialized
2026-09-06T11:46:20.614749Z  INFO replaying device configuration register_writes=2003
2026-09-06T11:46:20.621996Z  INFO loading application tile_count=1472 final_mark=23
2026-09-06T11:46:20.904787Z  INFO application loaded and initial synchronization completed tile_count=1472
2026-09-06T11:46:22.899576Z  INFO starting host exchange session startup_mark=23
2026-09-06T11:46:22.899607Z  INFO attaching host exchange pages pages=2
2026-09-06T11:46:22.900332Z  INFO host exchange session started
2026-09-06T11:46:22.900376Z  INFO invoking streaming host exchange call call="initialize" command=0 phases=24
2026-09-06T11:46:22.908268Z  INFO invoking streaming host exchange call call="run" command=0 phases=43
profile=artifacts/layout-sweep/joint-rows-6/execution.ipuprofile tiles=1472 samples=24985
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=90823680 weightBytes=19869696 cycles=209370 minimumTileCycles=199974 deviceMicroseconds=139.580 effectiveGemmTflops=103.583 peakTflops=282.624 efficiencyPercent=36.65 maximumAbsoluteError=0.009766
package=artifacts/layout-sweep/joint-rows-6/model.ipuexe tiles=1472 hardwareTest=PASS