2026-09-06T12:37:31.413414Z  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: 1, result_column_partitions: 2, output_column_block: 48, weight_memory_class: Ipu21Interleaved, reduction_staging: Complete, local_weight_staging: Direct }
2026-09-06T12:37:32.092583Z  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: Ipu21Standard, reduction_staging: Complete, local_weight_staging: Direct }
2026-09-06T12:37:32.673002Z  INFO retained operator-plan finalist finalist=0 values=7 operations=4 estimated_cycles=295478 estimated_exchange_cycles=137720 exchange_row_bytes=30332 peak_standard_bytes=172668 peak_interleaved_bytes=60416 peak_total_bytes=233084 maximum_standard_allocation_bytes=114688 active_tile_counts={736, 1440} padding_group_counts={} conversion_sources=[Some(OperationId(2))]
2026-09-06T12:37:32.679841Z  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=1564 success=true
2026-09-06T12:37:36.134814Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="select_finalist"}: selected analytical operator plan estimated_cycles=219850 estimated_exchange_cycles=75208
2026-09-06T12:37:36.225488Z  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
2026-09-06T12:37:36.228474Z  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=3548 success=true
2026-09-06T12:37:36.228513Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}: lowered graph for package construction logical_shards=22368 exchange_phases=4
2026-09-06T12:37:36.228803Z  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
2026-09-06T12:37:36.229800Z  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
2026-09-06T12:37:36.230173Z  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
2026-09-06T12:37:36.233187Z  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
2026-09-06T12:37:36.564439Z  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=330 success=true
2026-09-06T12:37:37.269269Z  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=3389 maximum_identical_destinations=1
2026-09-06T12:37:37.269316Z  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=11882 selected_horizon=11882 endpoint_lower_bound=11776 lower_bound_gap=106 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:37:37.274597Z  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=435 row_words=32 horizon=11882
2026-09-06T12:37:37.846357Z  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=812 ordinary_horizon=33533 paired_horizon=33523 use_paired=true
2026-09-06T12:37:37.869448Z  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=1541 maximum_identical_destinations=1
2026-09-06T12:37:37.869488Z  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=33523 selected_horizon=33523 endpoint_lower_bound=33408 lower_bound_gap=115 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:37:37.879927Z  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=682 row_words=64 horizon=33523
2026-09-06T12:37:45.047370Z  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=63720 maximum_identical_destinations=1
2026-09-06T12:37:45.047448Z  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=7991 selected_horizon=7991 endpoint_lower_bound=4704 lower_bound_gap=3287 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:37:45.111099Z  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=1058 row_words=294 horizon=7991
2026-09-06T12:37:45.137329Z  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=8572 success=true
2026-09-06T12:37:45.773247Z  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=8 success=true
2026-09-06T12:37:45.773297Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}: allocated package support memory linked_end=317036 profile_bytes=112 exchange_table_bytes=1400 host_code_bytes=2416 generated_code_bytes=1292 code_address=319456 standard_ranges=[(409600, 524288)]
2026-09-06T12:37:45.887545Z  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=114 success=true
2026-09-06T12:37:45.901696Z  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
2026-09-06T12:37:45.934657Z  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
2026-09-06T12:37:45.936572Z  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=3389 maximum_identical_destinations=1
2026-09-06T12:37:45.936592Z  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=11882 selected_horizon=11882 endpoint_lower_bound=11776 lower_bound_gap=106 selected_kind="reused" neighborhood_improvements=0
2026-09-06T12:37:45.940052Z  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=435 row_words=32 horizon=11882
2026-09-06T12:37:46.095698Z  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
2026-09-06T12:37:46.100621Z  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=1541 maximum_identical_destinations=1
2026-09-06T12:37:46.100646Z  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=33523 selected_horizon=33523 endpoint_lower_bound=33408 lower_bound_gap=115 selected_kind="reused" neighborhood_improvements=0
2026-09-06T12:37:46.106837Z  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=682 row_words=64 horizon=33523
2026-09-06T12:37:54.436139Z  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=63720 maximum_identical_destinations=1
2026-09-06T12:37:54.436244Z  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=7991 selected_horizon=7991 endpoint_lower_bound=4704 lower_bound_gap=3287 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:37:54.514042Z  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=1058 row_words=294 horizon=7991
2026-09-06T12:37:54.541400Z  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=8653 success=true
2026-09-06T12:37:55.752469Z  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
2026-09-06T12:37:55.781692Z  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
2026-09-06T12:37:55.783504Z  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=3389 maximum_identical_destinations=1
2026-09-06T12:37:55.783522Z  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=11882 selected_horizon=11882 endpoint_lower_bound=11776 lower_bound_gap=106 selected_kind="reused" neighborhood_improvements=0
2026-09-06T12:37:55.786939Z  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=435 row_words=32 horizon=11882
2026-09-06T12:37:55.934260Z  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
2026-09-06T12:37:55.939527Z  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=1541 maximum_identical_destinations=1
2026-09-06T12:37:55.939551Z  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=33523 selected_horizon=33523 endpoint_lower_bound=33408 lower_bound_gap=115 selected_kind="reused" neighborhood_improvements=0
2026-09-06T12:37:55.946144Z  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=682 row_words=64 horizon=33523
2026-09-06T12:38:06.133933Z  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=63720 maximum_identical_destinations=1
2026-09-06T12:38:06.134002Z  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=7991 selected_horizon=7991 endpoint_lower_bound=4704 lower_bound_gap=3287 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:38:06.204302Z  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=1058 row_words=294 horizon=7991
2026-09-06T12:38:06.244745Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: evaluated exchange placement finalist offset=24576 baseline_score=173497614336 score=159885950976 baseline_cycles=60444 candidate_cycles=60444 row_bytes=1400 row_capacity=16320 accepted=false
2026-09-06T12:38:06.258891Z  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=11717 success=true
2026-09-06T12:38:06.622405Z  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=21 success=true
2026-09-06T12:38:06.639169Z  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=16 success=true
2026-09-06T12:38:06.784495Z  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=137 success=true
2026-09-06T12:38:06.866067Z  INFO writing application package tiles=1472
2026-09-06T12:38:06.901509Z  INFO application package written
2026-09-06T12:38:06.902163Z  INFO reading application package
2026-09-06T12:38:06.984633Z  INFO application package read tiles=1472 compiler=0.1.0
2026-09-06T12:38:06.984998Z  INFO waiting for hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/alternatives-v1/device.lock
2026-09-06T12:38:06.985010Z  INFO acquired hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/alternatives-v1/device.lock
2026-09-06T12:38:06.985016Z  INFO opening IPU device path="/dev/ipu0"
2026-09-06T12:38:06.985058Z  INFO IPU device attached path=/dev/ipu0
2026-09-06T12:38:06.985061Z  INFO initializing IPU device
2026-09-06T12:38:06.993030Z  INFO IPU device initialized
2026-09-06T12:38:06.993036Z  INFO replaying device configuration register_writes=2003
2026-09-06T12:38:07.003301Z  INFO loading application tile_count=1472 final_mark=23
2026-09-06T12:38:07.297593Z  INFO application loaded and initial synchronization completed tile_count=1472
2026-09-06T12:38:09.893749Z  INFO starting host exchange session startup_mark=23
2026-09-06T12:38:09.893809Z  INFO attaching host exchange pages pages=2
2026-09-06T12:38:09.894396Z  INFO host exchange session started
2026-09-06T12:38:09.894563Z  INFO invoking streaming host exchange call call="initialize" command=0 phases=14
2026-09-06T12:38:09.907545Z  INFO invoking streaming host exchange call call="run" command=0 phases=59
profile=artifacts/layout-sweep/alternatives-v1/up-result-1x2/execution.ipuprofile tiles=1472 samples=21844
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=214212 minimumTileCycles=201750 deviceMicroseconds=142.808 effectiveGemmTflops=101.242 peakTflops=282.624 efficiencyPercent=35.82 maximumAbsoluteError=0.011719
package=artifacts/layout-sweep/alternatives-v1/up-result-1x2/model.ipuexe tiles=1472 hardwareTest=PASS