2026-09-06T12:38:10.994410Z  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 }
2026-09-06T12:38:11.522228Z  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 }
2026-09-06T12:38:12.195708Z  INFO retained operator-plan finalist finalist=0 values=7 operations=4 estimated_cycles=259590 estimated_exchange_cycles=123960 exchange_row_bytes=27236 peak_standard_bytes=169572 peak_interleaved_bytes=60416 peak_total_bytes=229988 maximum_standard_allocation_bytes=114688 active_tile_counts={1440, 1472} padding_group_counts={} conversion_sources=[Some(OperationId(2))]
2026-09-06T12:38:12.199517Z  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=1511 success=true
2026-09-06T12:38:16.971056Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="select_finalist"}: selected analytical operator plan estimated_cycles=192930 estimated_exchange_cycles=70152
2026-09-06T12:38:17.098868Z  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
2026-09-06T12:38:17.102171Z  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=4902 success=true
2026-09-06T12:38:17.102230Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}: lowered graph for package construction logical_shards=26264 exchange_phases=4
2026-09-06T12:38:17.102524Z  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
2026-09-06T12:38:17.103920Z  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=1 success=true
2026-09-06T12:38:17.104285Z  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
2026-09-06T12:38:17.106460Z  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
2026-09-06T12:38:17.336170Z  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=229 success=true
2026-09-06T12:38:17.748608Z  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
2026-09-06T12:38:17.748642Z  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=4517 selected_horizon=3829 endpoint_lower_bound=3408 lower_bound_gap=421 selected_kind="matching-waves" neighborhood_improvements=0
2026-09-06T12:38:17.760881Z  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=709 row_words=76 horizon=3829
2026-09-06T12:38:22.527141Z  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
2026-09-06T12:38:22.527191Z  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=46270 selected_horizon=46270 endpoint_lower_bound=33408 lower_bound_gap=12862 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:38:22.597447Z  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=597 row_words=307 horizon=46270
2026-09-06T12:38:29.147179Z  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
2026-09-06T12:38:29.147242Z  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=8488 selected_horizon=8488 endpoint_lower_bound=4704 lower_bound_gap=3784 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:38:29.228056Z  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=1332 row_words=282 horizon=8488
2026-09-06T12:38:29.263036Z  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=11926 success=true
2026-09-06T12:38:29.952197Z  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=6 success=true
2026-09-06T12:38:29.952254Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}: allocated package support memory linked_end=317036 profile_bytes=132 exchange_table_bytes=2488 host_code_bytes=2416 generated_code_bytes=1544 code_address=319456 standard_ranges=[(409600, 524288)]
2026-09-06T12:38:30.077753Z  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=125 success=true
2026-09-06T12:38:30.086684Z  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
2026-09-06T12:38:30.190123Z  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
2026-09-06T12:38:30.197302Z  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
2026-09-06T12:38:30.197319Z  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=3829 selected_horizon=3829 endpoint_lower_bound=3408 lower_bound_gap=421 selected_kind="reused" neighborhood_improvements=0
2026-09-06T12:38:30.209398Z  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=709 row_words=76 horizon=3829
2026-09-06T12:38:33.537253Z  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
2026-09-06T12:38:33.537283Z  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=46270 selected_horizon=46270 endpoint_lower_bound=33408 lower_bound_gap=12862 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:38:33.573929Z  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=597 row_words=307 horizon=46270
2026-09-06T12:38:38.815868Z  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
2026-09-06T12:38:38.815910Z  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=8488 selected_horizon=8488 endpoint_lower_bound=4704 lower_bound_gap=3784 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:38:38.878603Z  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=1332 row_words=282 horizon=8488
2026-09-06T12:38:38.901509Z  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=8823 success=true
2026-09-06T12:38:40.336803Z  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
2026-09-06T12:38:40.471072Z  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
2026-09-06T12:38:40.478553Z  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
2026-09-06T12:38:40.478576Z  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=3829 selected_horizon=3829 endpoint_lower_bound=3408 lower_bound_gap=421 selected_kind="reused" neighborhood_improvements=0
2026-09-06T12:38:40.491469Z  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=709 row_words=76 horizon=3829
2026-09-06T12:38:45.305191Z  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
2026-09-06T12:38:45.305243Z  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=44116 selected_horizon=44116 endpoint_lower_bound=33408 lower_bound_gap=10708 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:38:45.362209Z  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=597 row_words=304 horizon=44116
2026-09-06T12:38:51.883968Z  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
2026-09-06T12:38:51.883998Z  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=8488 selected_horizon=8488 endpoint_lower_bound=4704 lower_bound_gap=3784 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:38:51.927042Z  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=1332 row_words=282 horizon=8488
2026-09-06T12:38:51.949959Z  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=170111729664 score=151709220864 baseline_cycles=65605 candidate_cycles=63451 row_bytes=2488 row_capacity=16320 accepted=true
2026-09-06T12:38:51.960243Z  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=13058 success=true
2026-09-06T12:38:52.194299Z  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
2026-09-06T12:38:52.203446Z  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
2026-09-06T12:38:52.271543Z  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=63 success=true
2026-09-06T12:38:52.326899Z  INFO writing application package tiles=1472
2026-09-06T12:38:52.352766Z  INFO application package written
2026-09-06T12:38:52.353240Z  INFO reading application package
2026-09-06T12:38:52.418387Z  INFO application package read tiles=1472 compiler=0.1.0
2026-09-06T12:38:52.418719Z  INFO waiting for hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/alternatives-v1/device.lock
2026-09-06T12:39:01.711474Z  INFO acquired hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/alternatives-v1/device.lock
2026-09-06T12:39:01.711502Z  INFO opening IPU device path="/dev/ipu0"
2026-09-06T12:39:01.711542Z  INFO IPU device attached path=/dev/ipu0
2026-09-06T12:39:01.711545Z  INFO initializing IPU device
2026-09-06T12:39:01.719325Z  INFO IPU device initialized
2026-09-06T12:39:01.719345Z  INFO replaying device configuration register_writes=2003
2026-09-06T12:39:01.726245Z  INFO loading application tile_count=1472 final_mark=23
2026-09-06T12:39:01.990002Z  INFO application loaded and initial synchronization completed tile_count=1472
2026-09-06T12:39:04.400393Z  INFO starting host exchange session startup_mark=23
2026-09-06T12:39:04.400421Z  INFO attaching host exchange pages pages=2
2026-09-06T12:39:04.400886Z  INFO host exchange session started
2026-09-06T12:39:04.400947Z  INFO invoking streaming host exchange call call="initialize" command=0 phases=14
2026-09-06T12:39:04.408277Z  INFO invoking streaming host exchange call call="run" command=0 phases=59
profile=artifacts/layout-sweep/alternatives-v1/mapping-transpose-16/execution.ipuprofile tiles=1472 samples=25788
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=196644 minimumTileCycles=182418 deviceMicroseconds=131.096 effectiveGemmTflops=110.287 peakTflops=282.624 efficiencyPercent=39.02 maximumAbsoluteError=0.011719
package=artifacts/layout-sweep/alternatives-v1/mapping-transpose-16/model.ipuexe tiles=1472 hardwareTest=PASS