2026-09-06T11:47:15.045261Z  INFO applied GEMM plan constraint source_operation=0 matching_plans=1 constraint=GemmPlanConstraint { source_operation: 0, orientation: Normal, row_partitions: 2, column_partitions: 135, inner_partitions: 5, result_row_partitions: 5, result_column_partitions: 1, output_column_block: 32, weight_memory_class: Ipu21Interleaved, reduction_staging: Complete, local_weight_staging: Direct }
2026-09-06T11:47:15.500226Z  INFO applied GEMM plan constraint source_operation=2 matching_plans=1 constraint=GemmPlanConstraint { source_operation: 2, orientation: Normal, row_partitions: 5, column_partitions: 24, inner_partitions: 12, result_row_partitions: 12, result_column_partitions: 1, output_column_block: 48, weight_memory_class: Ipu21Interleaved, reduction_staging: Complete, local_weight_staging: Direct }
2026-09-06T11:47:15.949108Z  INFO retained operator-plan finalist finalist=0 values=7 operations=4 estimated_cycles=315222 estimated_exchange_cycles=123000 exchange_row_bytes=27020 peak_standard_bytes=207244 peak_interleaved_bytes=83456 peak_total_bytes=290700 maximum_standard_allocation_bytes=180224 active_tile_counts={1350, 1440} padding_group_counts={} conversion_sources=[Some(OperationId(2))]
2026-09-06T11:47:15.955833Z  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=1198 success=true
2026-09-06T11:47:19.350462Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="select_finalist"}: selected analytical operator plan estimated_cycles=250364 estimated_exchange_cycles=66168
2026-09-06T11:47:19.422045Z  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=96
2026-09-06T11:47:19.423629Z  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=3467 success=true
2026-09-06T11:47:19.423655Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}: lowered graph for package construction logical_shards=25326 exchange_phases=4
2026-09-06T11:47:19.423836Z  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
2026-09-06T11:47:19.424461Z  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
2026-09-06T11:47:19.424768Z  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
2026-09-06T11:47:19.426600Z  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
2026-09-06T11:47:19.554343Z  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=127 success=true
2026-09-06T11:47:19.827668Z  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=12105 maximum_identical_destinations=1
2026-09-06T11:47:19.827695Z  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=6541 selected_horizon=5157 endpoint_lower_bound=4800 lower_bound_gap=357 selected_kind="matching-waves" neighborhood_improvements=0
2026-09-06T11:47:19.837966Z  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=599 row_words=66 horizon=5157
2026-09-06T11:47:24.923703Z  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=2453 ordinary_horizon=50906 paired_horizon=38081 use_paired=true
2026-09-06T11:47:24.993497Z  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=4630 maximum_identical_destinations=1
2026-09-06T11:47:24.993522Z  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=38081 selected_horizon=38081 endpoint_lower_bound=29072 lower_bound_gap=9009 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T11:47:25.028455Z  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=873 row_words=213 horizon=38081
2026-09-06T11:47:29.260275Z  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=50976 maximum_identical_destinations=1
2026-09-06T11:47:29.260311Z  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=3696 lower_bound_gap=2569 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T11:47:29.307854Z  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=1132 row_words=232 horizon=6265
2026-09-06T11:47:29.323975Z  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=9769 success=true
2026-09-06T11:47:30.194855Z  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
2026-09-06T11:47:30.194898Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}: allocated package support memory linked_end=318176 profile_bytes=152 exchange_table_bytes=1712 host_code_bytes=3604 generated_code_bytes=1864 code_address=321784 standard_ranges=[(409600, 524288)]
2026-09-06T11:47:30.302642Z  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=107 success=true
2026-09-06T11:47:30.309810Z  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
2026-09-06T11:47:30.425071Z  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
2026-09-06T11:47:30.429925Z  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=12105 maximum_identical_destinations=1
2026-09-06T11:47:30.429937Z  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=5157 selected_horizon=5157 endpoint_lower_bound=4800 lower_bound_gap=357 selected_kind="reused" neighborhood_improvements=0
2026-09-06T11:47:30.440059Z  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=599 row_words=66 horizon=5157
2026-09-06T11:47:36.039766Z  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=2453 ordinary_horizon=50906 paired_horizon=38081 use_paired=true
2026-09-06T11:47:36.114522Z  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=4630 maximum_identical_destinations=1
2026-09-06T11:47:36.114546Z  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=38081 selected_horizon=38081 endpoint_lower_bound=29072 lower_bound_gap=9009 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T11:47:36.148035Z  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=873 row_words=213 horizon=38081
2026-09-06T11:47:40.588618Z  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=50976 maximum_identical_destinations=1
2026-09-06T11:47:40.588658Z  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=3696 lower_bound_gap=2569 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T11:47:40.655898Z  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=1132 row_words=232 horizon=6265
2026-09-06T11:47:40.673308Z  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=10370 success=true
2026-09-06T11:47:42.385606Z  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
2026-09-06T11:47:42.464535Z  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
2026-09-06T11:47:42.469618Z  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=12105 maximum_identical_destinations=1
2026-09-06T11:47:42.469631Z  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=5157 selected_horizon=5157 endpoint_lower_bound=4800 lower_bound_gap=357 selected_kind="reused" neighborhood_improvements=0
2026-09-06T11:47:42.479983Z  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=599 row_words=66 horizon=5157
2026-09-06T11:47:48.213775Z  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=2453 ordinary_horizon=48837 paired_horizon=36263 use_paired=true
2026-09-06T11:47:48.280063Z  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=4630 maximum_identical_destinations=1
2026-09-06T11:47:48.280086Z  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=36263 selected_horizon=36263 endpoint_lower_bound=29072 lower_bound_gap=7191 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T11:47:48.307497Z  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=873 row_words=221 horizon=36263
2026-09-06T11:47:51.224089Z  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=50976 maximum_identical_destinations=1
2026-09-06T11:47:51.224120Z  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=3696 lower_bound_gap=2569 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T11:47:51.272516Z  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=1132 row_words=232 horizon=6265
2026-09-06T11:47:51.298279Z  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=581134860288 score=177079762944 baseline_cycles=53557 candidate_cycles=51739 row_bytes=1744 row_capacity=16320 accepted=true
2026-09-06T11:47:51.309307Z  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=10635 success=true
2026-09-06T11:47:51.734319Z  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
2026-09-06T11:47:51.745754Z  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
2026-09-06T11:47:51.847959Z  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
2026-09-06T11:47:51.923458Z  INFO writing application package tiles=1472
2026-09-06T11:47:51.981151Z  INFO application package written
2026-09-06T11:47:51.983539Z  INFO reading application package
2026-09-06T11:47:52.089383Z  INFO application package read tiles=1472 compiler=0.1.0
2026-09-06T11:47:52.091700Z  INFO waiting for hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/device.lock
2026-09-06T11:47:55.425658Z  INFO acquired hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/device.lock
2026-09-06T11:47:55.425710Z  INFO opening IPU device path="/dev/ipu0"
2026-09-06T11:47:55.425781Z  INFO IPU device attached path=/dev/ipu0
2026-09-06T11:47:55.425788Z  INFO initializing IPU device
2026-09-06T11:47:55.433899Z  INFO IPU device initialized
2026-09-06T11:47:55.433939Z  INFO replaying device configuration register_writes=2003
2026-09-06T11:47:55.444837Z  INFO loading application tile_count=1472 final_mark=23
2026-09-06T11:47:55.794950Z  INFO application loaded and initial synchronization completed tile_count=1472
2026-09-06T11:47:59.102853Z  INFO starting host exchange session startup_mark=23
2026-09-06T11:47:59.102889Z  INFO attaching host exchange pages pages=2
2026-09-06T11:47:59.104018Z  INFO host exchange session started
2026-09-06T11:47:59.104086Z  INFO invoking streaming host exchange call call="initialize" command=0 phases=18
2026-09-06T11:47:59.111117Z  INFO invoking streaming host exchange call call="run" command=0 phases=93
profile=artifacts/layout-sweep/cross-cropped-2-2/execution.ipuprofile tiles=1472 samples=25185
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=236520000 weightBytes=20504064 cycles=212574 minimumTileCycles=189936 deviceMicroseconds=141.716 effectiveGemmTflops=102.022 peakTflops=282.624 efficiencyPercent=36.10 maximumAbsoluteError=0.009766
package=artifacts/layout-sweep/cross-cropped-2-2/model.ipuexe tiles=1472 hardwareTest=PASS