2026-09-06T12:40:15.881344Z  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 }
2026-09-06T12:40:16.431411Z  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: 5, result_column_partitions: 3, output_column_block: 48, weight_memory_class: Ipu21Standard, reduction_staging: Complete, local_weight_staging: Direct }
2026-09-06T12:40:16.979774Z  INFO retained operator-plan finalist finalist=0 values=7 operations=4 estimated_cycles=258236 estimated_exchange_cycles=122840 exchange_row_bytes=26984 peak_standard_bytes=169320 peak_interleaved_bytes=60416 peak_total_bytes=229736 maximum_standard_allocation_bytes=114688 active_tile_counts={1440, 1472} padding_group_counts={} conversion_sources=[Some(OperationId(2))]
2026-09-06T12:40:16.985379Z  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=1434 success=true
2026-09-06T12:40:20.779658Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="select_finalist"}: selected analytical operator plan estimated_cycles=186526 estimated_exchange_cycles=65184
2026-09-06T12:40:20.950616Z  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
2026-09-06T12:40:20.963742Z  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=3978 success=true
2026-09-06T12:40:20.963780Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}: lowered graph for package construction logical_shards=26696 exchange_phases=4
2026-09-06T12:40:20.964056Z  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
2026-09-06T12:40:20.968625Z  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=4 success=true
2026-09-06T12:40:20.968998Z  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
2026-09-06T12:40:20.984993Z  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
2026-09-06T12:40:21.770049Z  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=785 success=true
2026-09-06T12:40:22.385138Z  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
2026-09-06T12:40:22.385182Z  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=4193 selected_horizon=3811 endpoint_lower_bound=3408 lower_bound_gap=403 selected_kind="matching-waves" neighborhood_improvements=0
2026-09-06T12:40:22.402462Z  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=815 row_words=76 horizon=3811
2026-09-06T12:40:26.488638Z  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
2026-09-06T12:40:26.488720Z  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=44951 selected_horizon=44951 endpoint_lower_bound=33408 lower_bound_gap=11543 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:40:26.540297Z  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=864 row_words=285 horizon=44951
2026-09-06T12:40:27.874817Z  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=24760 maximum_identical_destinations=1
2026-09-06T12:40:27.874859Z  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=5946 selected_horizon=5898 endpoint_lower_bound=4560 lower_bound_gap=1338 selected_kind="critical-neighborhood" neighborhood_improvements=1
2026-09-06T12:40:27.914464Z  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=595 row_words=129 horizon=5898
2026-09-06T12:40:27.929897Z  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=6159 success=true
2026-09-06T12:40:28.681372Z  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=11 success=true
2026-09-06T12:40:28.681428Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}: allocated package support memory linked_end=317036 profile_bytes=132 exchange_table_bytes=1812 host_code_bytes=2400 generated_code_bytes=1504 code_address=319440 standard_ranges=[(409600, 524288)]
2026-09-06T12:40:28.813230Z  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=131 success=true
2026-09-06T12:40:28.822504Z  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
2026-09-06T12:40:28.932053Z  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
2026-09-06T12:40:28.939677Z  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
2026-09-06T12:40:28.939698Z  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=3811 selected_horizon=3811 endpoint_lower_bound=3408 lower_bound_gap=403 selected_kind="reused" neighborhood_improvements=0
2026-09-06T12:40:28.952375Z  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=815 row_words=76 horizon=3811
2026-09-06T12:40:33.709595Z  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
2026-09-06T12:40:33.709665Z  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=44951 selected_horizon=44951 endpoint_lower_bound=33408 lower_bound_gap=11543 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:40:33.768154Z  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=864 row_words=285 horizon=44951
2026-09-06T12:40:34.248697Z  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
2026-09-06T12:40:34.269049Z  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=24760 maximum_identical_destinations=1
2026-09-06T12:40:34.269075Z  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=5898 selected_horizon=5898 endpoint_lower_bound=4560 lower_bound_gap=1338 selected_kind="reused" neighborhood_improvements=0
2026-09-06T12:40:34.312886Z  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=595 row_words=129 horizon=5898
2026-09-06T12:40:34.322450Z  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=5509 success=true
2026-09-06T12:40:37.236054Z  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
2026-09-06T12:40:37.455609Z  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
2026-09-06T12:40:37.465192Z  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
2026-09-06T12:40:37.465253Z  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=3811 selected_horizon=3811 endpoint_lower_bound=3408 lower_bound_gap=403 selected_kind="reused" neighborhood_improvements=0
2026-09-06T12:40:37.478297Z  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=815 row_words=76 horizon=3811
2026-09-06T12:40:41.992476Z  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
2026-09-06T12:40:41.992524Z  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=40635 selected_horizon=40635 endpoint_lower_bound=33408 lower_bound_gap=7227 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:40:42.044192Z  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=864 row_words=283 horizon=40635
2026-09-06T12:40:42.286111Z  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
2026-09-06T12:40:42.302587Z  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=24760 maximum_identical_destinations=1
2026-09-06T12:40:42.302615Z  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=5898 selected_horizon=5898 endpoint_lower_bound=4560 lower_bound_gap=1338 selected_kind="reused" neighborhood_improvements=0
2026-09-06T12:40:42.331010Z  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=595 row_words=129 horizon=5898
2026-09-06T12:40:42.349324Z  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=61694 candidate_cycles=57378 row_bytes=1804 row_capacity=16320 accepted=true
2026-09-06T12:40:42.361303Z  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=8038 success=true
2026-09-06T12:40:42.693030Z  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=15 success=true
2026-09-06T12:40:42.706001Z  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=12 success=true
2026-09-06T12:40:42.809532Z  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=97 success=true
2026-09-06T12:40:42.893933Z  INFO writing application package tiles=1472
2026-09-06T12:40:42.932743Z  INFO application package written
2026-09-06T12:40:42.933592Z  INFO reading application package
2026-09-06T12:40:43.027953Z  INFO application package read tiles=1472 compiler=0.1.0
2026-09-06T12:40:43.028399Z  INFO waiting for hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/alternatives-followup/device.lock
2026-09-06T12:40:45.471454Z  INFO acquired hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/alternatives-followup/device.lock
2026-09-06T12:40:45.471520Z  INFO opening IPU device path="/dev/ipu0"
2026-09-06T12:40:45.471659Z  INFO IPU device attached path=/dev/ipu0
2026-09-06T12:40:45.471667Z  INFO initializing IPU device
2026-09-06T12:40:45.479606Z  INFO IPU device initialized
2026-09-06T12:40:45.479655Z  INFO replaying device configuration register_writes=2003
2026-09-06T12:40:45.489609Z  INFO loading application tile_count=1472 final_mark=23
2026-09-06T12:40:45.810920Z  INFO application loaded and initial synchronization completed tile_count=1472
2026-09-06T12:40:50.273819Z  INFO starting host exchange session startup_mark=23
2026-09-06T12:40:50.273878Z  INFO attaching host exchange pages pages=2
2026-09-06T12:40:50.274292Z  INFO host exchange session started
2026-09-06T12:40:50.274392Z  INFO invoking streaming host exchange call call="initialize" command=0 phases=14
2026-09-06T12:40:50.281928Z  INFO invoking streaming host exchange call call="run" command=0 phases=59
profile=artifacts/layout-sweep/alternatives-followup/mapping-block-360-15-mixed/execution.ipuprofile tiles=1472 samples=24596
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=190650 minimumTileCycles=180444 deviceMicroseconds=127.100 effectiveGemmTflops=113.754 peakTflops=282.624 efficiencyPercent=40.25 maximumAbsoluteError=0.011719
package=artifacts/layout-sweep/alternatives-followup/mapping-block-360-15-mixed/model.ipuexe tiles=1472 hardwareTest=PASS