2026-09-06T11:39:36.533595Z  INFO applied GEMM plan constraint source_operation=0 matching_plans=2 constraint=GemmPlanConstraint { source_operation: 0, orientation: Normal, row_partitions: 4, column_partitions: 92, inner_partitions: 4, result_row_partitions: 1, result_column_partitions: 1, output_column_block: 48, weight_memory_class: Ipu21Interleaved, reduction_staging: Streamed, local_weight_staging: Direct }
2026-09-06T11:39:36.981318Z  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: 15, result_column_partitions: 1, output_column_block: 48, weight_memory_class: Ipu21Interleaved, reduction_staging: Complete, local_weight_staging: Direct }
2026-09-06T11:39:37.518847Z  INFO retained operator-plan finalist finalist=0 values=7 operations=4 estimated_cycles=455631 estimated_exchange_cycles=149960 exchange_row_bytes=32824 peak_standard_bytes=147512 peak_interleaved_bytes=88064 peak_total_bytes=235576 maximum_standard_allocation_bytes=114688 active_tile_counts={368, 1440} padding_group_counts={} conversion_sources=[Some(OperationId(2))]
2026-09-06T11:39:37.524039Z  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=1311 success=true
2026-09-06T11:39:41.173667Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="select_finalist"}: selected analytical operator plan estimated_cycles=474415 estimated_exchange_cycles=91128
2026-09-06T11:39:41.251016Z  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
2026-09-06T11:39:41.252281Z  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=3728 success=true
2026-09-06T11:39:41.252300Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}: lowered graph for package construction logical_shards=20192 exchange_phases=6
2026-09-06T11:39:41.252501Z  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
2026-09-06T11:39:41.252939Z  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
2026-09-06T11:39:41.253190Z  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
2026-09-06T11:39:41.254991Z  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
2026-09-06T11:39:41.346420Z  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=91 success=true
2026-09-06T11:39:41.383006Z  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=1239 maximum_identical_destinations=1
2026-09-06T11:39:41.383031Z  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=8884 selected_horizon=8884 endpoint_lower_bound=8736 lower_bound_gap=148 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T11:39:41.384021Z  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=157 row_words=18 horizon=8884
2026-09-06T11:39:41.849669Z  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=4 candidates=788 ordinary_horizon=41976 paired_horizon=41793 use_paired=true
2026-09-06T11:39:41.861756Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges_provisional"}: prepared large physical exchange phase phase=4 transfers=1520 maximum_identical_destinations=1
2026-09-06T11:39:41.861771Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges_provisional"}: optimized physical exchange schedule phase=4 initial_horizon=41793 selected_horizon=41793 endpoint_lower_bound=33408 lower_bound_gap=8385 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T11:39:41.868193Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges_provisional"}: finished large physical exchange phase phase=4 tile=323 row_words=56 horizon=41793
2026-09-06T11:39:48.012675Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges_provisional"}: prepared large physical exchange phase phase=5 transfers=63720 maximum_identical_destinations=1
2026-09-06T11:39:48.012719Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges_provisional"}: optimized physical exchange schedule phase=5 initial_horizon=7991 selected_horizon=7991 endpoint_lower_bound=4704 lower_bound_gap=3287 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T11:39:48.074255Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges_provisional"}: finished large physical exchange phase phase=5 tile=1058 row_words=294 horizon=7991
2026-09-06T11:39:48.095435Z  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=6748 success=true
2026-09-06T11:39:48.741938Z  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=4 success=true
2026-09-06T11:39:48.741968Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}: allocated package support memory linked_end=317272 profile_bytes=120 exchange_table_bytes=1352 host_code_bytes=2420 generated_code_bytes=1356 code_address=319696 standard_ranges=[(409600, 524288)]
2026-09-06T11:39:48.822362Z  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=80 success=true
2026-09-06T11:39:48.830594Z  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
2026-09-06T11:39:48.839917Z  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
2026-09-06T11:39:48.840452Z  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=1239 maximum_identical_destinations=1
2026-09-06T11:39:48.840463Z  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=8884 selected_horizon=8884 endpoint_lower_bound=8736 lower_bound_gap=148 selected_kind="reused" neighborhood_improvements=0
2026-09-06T11:39:48.841420Z  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=157 row_words=18 horizon=8884
2026-09-06T11:39:48.846778Z  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=2
2026-09-06T11:39:48.853347Z  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
2026-09-06T11:39:48.974361Z  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=4
2026-09-06T11:39:48.978467Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: prepared large physical exchange phase phase=4 transfers=1520 maximum_identical_destinations=1
2026-09-06T11:39:48.978478Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: optimized physical exchange schedule phase=4 initial_horizon=41793 selected_horizon=41793 endpoint_lower_bound=33408 lower_bound_gap=8385 selected_kind="reused" neighborhood_improvements=0
2026-09-06T11:39:48.984470Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: finished large physical exchange phase phase=4 tile=323 row_words=56 horizon=41793
2026-09-06T11:39:55.533092Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: prepared large physical exchange phase phase=5 transfers=63720 maximum_identical_destinations=1
2026-09-06T11:39:55.533142Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: optimized physical exchange schedule phase=5 initial_horizon=7991 selected_horizon=7991 endpoint_lower_bound=4704 lower_bound_gap=3287 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T11:39:55.594235Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: finished large physical exchange phase phase=5 tile=1058 row_words=294 horizon=7991
2026-09-06T11:39:55.618515Z  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=6796 success=true
2026-09-06T11:39:56.545964Z  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
2026-09-06T11:39:56.555589Z  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
2026-09-06T11:39:56.556083Z  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=1239 maximum_identical_destinations=1
2026-09-06T11:39:56.556091Z  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=8884 selected_horizon=8884 endpoint_lower_bound=8736 lower_bound_gap=148 selected_kind="reused" neighborhood_improvements=0
2026-09-06T11:39:56.557125Z  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=157 row_words=18 horizon=8884
2026-09-06T11:39:56.562421Z  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=2
2026-09-06T11:39:56.568631Z  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
2026-09-06T11:39:57.119517Z  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=4 candidates=788 ordinary_horizon=47191 paired_horizon=44522 use_paired=true
2026-09-06T11:39:57.132245Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: prepared large physical exchange phase phase=4 transfers=1520 maximum_identical_destinations=1
2026-09-06T11:39:57.132258Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: optimized physical exchange schedule phase=4 initial_horizon=44522 selected_horizon=44522 endpoint_lower_bound=33408 lower_bound_gap=11114 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T11:39:57.139138Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: finished large physical exchange phase phase=4 tile=323 row_words=56 horizon=44522
2026-09-06T11:40:03.759605Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: prepared large physical exchange phase phase=5 transfers=63720 maximum_identical_destinations=1
2026-09-06T11:40:03.759641Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: optimized physical exchange schedule phase=5 initial_horizon=7991 selected_horizon=7991 endpoint_lower_bound=4704 lower_bound_gap=3287 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T11:40:03.820265Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: finished large physical exchange phase phase=5 tile=1058 row_words=294 horizon=7991
2026-09-06T11:40:03.847759Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: evaluated exchange placement finalist offset=16384 baseline_score=448685899776 score=421462573056 baseline_cycles=74757 candidate_cycles=77486 row_bytes=1352 row_capacity=16320 accepted=false
2026-09-06T11:40:03.856465Z  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=8237 success=true
2026-09-06T11:40:04.163448Z  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=8 success=true
2026-09-06T11:40:04.172812Z  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=9 success=true
2026-09-06T11:40:04.257770Z  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=81 success=true
2026-09-06T11:40:04.314703Z  INFO writing application package tiles=1472
2026-09-06T11:40:04.365132Z  INFO application package written
2026-09-06T11:40:04.367271Z  INFO reading application package
2026-09-06T11:40:04.452371Z  INFO application package read tiles=1472 compiler=0.1.0
2026-09-06T11:40:04.454316Z  INFO waiting for hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/device.lock
2026-09-06T11:40:04.454328Z  INFO acquired hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/device.lock
2026-09-06T11:40:04.454333Z  INFO opening IPU device path="/dev/ipu0"
2026-09-06T11:40:04.454360Z  INFO IPU device attached path=/dev/ipu0
2026-09-06T11:40:04.454370Z  INFO initializing IPU device
2026-09-06T11:40:04.462498Z  INFO IPU device initialized
2026-09-06T11:40:04.462537Z  INFO replaying device configuration register_writes=2003
2026-09-06T11:40:04.471435Z  INFO loading application tile_count=1472 final_mark=23
2026-09-06T11:40:04.752845Z  INFO application loaded and initial synchronization completed tile_count=1472
2026-09-06T11:40:07.369502Z  INFO starting host exchange session startup_mark=23
2026-09-06T11:40:07.369529Z  INFO attaching host exchange pages pages=2
2026-09-06T11:40:07.370016Z  INFO host exchange session started
2026-09-06T11:40:07.370077Z  INFO invoking streaming host exchange call call="initialize" command=0 phases=14
2026-09-06T11:40:07.381330Z  INFO invoking streaming host exchange call call="run" command=0 phases=59
profile=artifacts/layout-sweep/up-22/execution.ipuprofile tiles=1472 samples=24506
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=300408 minimumTileCycles=284064 deviceMicroseconds=200.272 effectiveGemmTflops=72.192 peakTflops=282.624 efficiencyPercent=25.54 maximumAbsoluteError=0.011719
package=artifacts/layout-sweep/up-22/model.ipuexe tiles=1472 hardwareTest=PASS