2026-09-06T11:44:28.537405Z  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 }
2026-09-06T11:44:28.978717Z  INFO applied GEMM plan constraint source_operation=2 matching_plans=2 constraint=GemmPlanConstraint { source_operation: 2, orientation: Normal, row_partitions: 4, column_partitions: 24, inner_partitions: 15, result_row_partitions: 1, result_column_partitions: 1, output_column_block: 48, weight_memory_class: Ipu21Interleaved, reduction_staging: Complete, local_weight_staging: Direct }
2026-09-06T11:44:29.601770Z  INFO retained operator-plan finalist finalist=0 values=7 operations=4 estimated_cycles=697897 estimated_exchange_cycles=266680 exchange_row_bytes=59348 peak_standard_bytes=341972 peak_interleaved_bytes=88064 peak_total_bytes=392404 maximum_standard_allocation_bytes=282624 active_tile_counts={96, 1440, 1472} padding_group_counts={} conversion_sources=[Some(OperationId(2))]
2026-09-06T11:44:29.607490Z  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=1358 success=true
2026-09-06T11:44:32.977689Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="select_finalist"}: selected analytical operator plan estimated_cycles=564410 estimated_exchange_cycles=121872
2026-09-06T11:44:33.025700Z  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
2026-09-06T11:44:33.026412Z  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=3418 success=true
2026-09-06T11:44:33.026424Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}: lowered graph for package construction logical_shards=20672 exchange_phases=4
2026-09-06T11:44:33.026546Z  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
2026-09-06T11:44:33.026881Z  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
2026-09-06T11:44:33.027027Z  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
2026-09-06T11:44:33.028023Z  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
2026-09-06T11:44:33.104039Z  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=76 success=true
2026-09-06T11:44:33.439300Z  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
2026-09-06T11:44:33.439329Z  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=4180 selected_horizon=3779 endpoint_lower_bound=3408 lower_bound_gap=371 selected_kind="matching-waves" neighborhood_improvements=0
2026-09-06T11:44:33.449842Z  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=690 row_words=75 horizon=3779
2026-09-06T11:44:41.143560Z  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=4028 ordinary_horizon=51847 paired_horizon=41194 use_paired=true
2026-09-06T11:44:41.229858Z  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
2026-09-06T11:44:41.229882Z  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=41194 selected_horizon=41194 endpoint_lower_bound=23544 lower_bound_gap=17650 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T11:44:41.275046Z  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=1182 row_words=301 horizon=41194
2026-09-06T11:44:41.360192Z  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=2832 maximum_identical_destinations=1
2026-09-06T11:44:41.360224Z  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=65649 selected_horizon=65649 endpoint_lower_bound=65520 lower_bound_gap=129 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T11:44:41.362087Z  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=47 row_words=71 horizon=65649
2026-09-06T11:44:41.363105Z  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=8259 success=true
2026-09-06T11:44:42.014453Z  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
2026-09-06T11:44:42.014489Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}: allocated package support memory linked_end=317272 profile_bytes=120 exchange_table_bytes=1444 host_code_bytes=3108 generated_code_bytes=1412 code_address=320384 standard_ranges=[(409600, 524288)]
2026-09-06T11:44:42.090538Z  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=76 success=true
2026-09-06T11:44:42.097994Z  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
2026-09-06T11:44:42.188903Z  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
2026-09-06T11:44:42.194780Z  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
2026-09-06T11:44:42.194793Z  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=3779 selected_horizon=3779 endpoint_lower_bound=3408 lower_bound_gap=371 selected_kind="reused" neighborhood_improvements=0
2026-09-06T11:44:42.204664Z  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=690 row_words=75 horizon=3779
2026-09-06T11:44:50.776326Z  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=4028 ordinary_horizon=51847 paired_horizon=41194 use_paired=true
2026-09-06T11:44:50.865796Z  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
2026-09-06T11:44:50.865818Z  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=41194 selected_horizon=41194 endpoint_lower_bound=23544 lower_bound_gap=17650 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T11:44:50.911177Z  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=1182 row_words=301 horizon=41194
2026-09-06T11:44:50.945281Z  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
2026-09-06T11:44:50.946669Z  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=2832 maximum_identical_destinations=1
2026-09-06T11:44:50.946682Z  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=65649 selected_horizon=65649 endpoint_lower_bound=65520 lower_bound_gap=129 selected_kind="reused" neighborhood_improvements=0
2026-09-06T11:44:50.948569Z  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=47 row_words=71 horizon=65649
2026-09-06T11:44:50.949384Z  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=8858 success=true
2026-09-06T11:44:52.076798Z  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
2026-09-06T11:44:52.169445Z  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
2026-09-06T11:44:52.175518Z  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
2026-09-06T11:44:52.175529Z  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=3779 selected_horizon=3779 endpoint_lower_bound=3408 lower_bound_gap=371 selected_kind="reused" neighborhood_improvements=0
2026-09-06T11:44:52.185772Z  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=690 row_words=75 horizon=3779
2026-09-06T11:45:00.868055Z  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=4028 ordinary_horizon=41592 paired_horizon=32939 use_paired=true
2026-09-06T11:45:00.951280Z  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
2026-09-06T11:45:00.951309Z  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=32939 selected_horizon=32939 endpoint_lower_bound=23544 lower_bound_gap=9395 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T11:45:00.996916Z  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=1182 row_words=303 horizon=32939
2026-09-06T11:45:01.030735Z  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
2026-09-06T11:45:01.032198Z  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=2832 maximum_identical_destinations=1
2026-09-06T11:45:01.032232Z  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=65649 selected_horizon=65649 endpoint_lower_bound=65520 lower_bound_gap=129 selected_kind="reused" neighborhood_improvements=0
2026-09-06T11:45:01.034129Z  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=47 row_words=71 horizon=65649
2026-09-06T11:45:01.039757Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: evaluated exchange placement finalist offset=4096 baseline_score=445300015104 score=170111729664 baseline_cycles=117670 candidate_cycles=109415 row_bytes=1452 row_capacity=16320 accepted=true
2026-09-06T11:45:01.045679Z  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=10096 success=true
2026-09-06T11:45:01.353932Z  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=13 success=true
2026-09-06T11:45:01.362884Z  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=8 success=true
2026-09-06T11:45:01.448855Z  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=82 success=true
2026-09-06T11:45:01.503651Z  INFO writing application package tiles=1472
2026-09-06T11:45:01.541615Z  INFO application package written
2026-09-06T11:45:01.543596Z  INFO reading application package
2026-09-06T11:45:01.622964Z  INFO application package read tiles=1472 compiler=0.1.0
2026-09-06T11:45:01.624845Z  INFO waiting for hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/device.lock
2026-09-06T11:45:01.624856Z  INFO acquired hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/device.lock
2026-09-06T11:45:01.624861Z  INFO opening IPU device path="/dev/ipu0"
2026-09-06T11:45:01.624890Z  INFO IPU device attached path=/dev/ipu0
2026-09-06T11:45:01.624893Z  INFO initializing IPU device
2026-09-06T11:45:01.632719Z  INFO IPU device initialized
2026-09-06T11:45:01.632727Z  INFO replaying device configuration register_writes=2003
2026-09-06T11:45:01.641091Z  INFO loading application tile_count=1472 final_mark=23
2026-09-06T11:45:01.923007Z  INFO application loaded and initial synchronization completed tile_count=1472
2026-09-06T11:45:04.726569Z  INFO starting host exchange session startup_mark=23
2026-09-06T11:45:04.726597Z  INFO attaching host exchange pages pages=2
2026-09-06T11:45:04.727047Z  INFO host exchange session started
2026-09-06T11:45:04.727087Z  INFO invoking streaming host exchange call call="initialize" command=0 phases=14
2026-09-06T11:45:04.743548Z  INFO invoking streaming host exchange call call="run" command=0 phases=67
profile=artifacts/layout-sweep/down-23/execution.ipuprofile tiles=1472 samples=21636
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=96 executionTiles=1472 inputBytes=154736640 weightBytes=19869696 cycles=345792 minimumTileCycles=178224 deviceMicroseconds=230.528 effectiveGemmTflops=62.717 peakTflops=282.624 efficiencyPercent=22.19 maximumAbsoluteError=0.011719
package=artifacts/layout-sweep/down-23/model.ipuexe tiles=1472 hardwareTest=PASS