2026-09-06T11:28:00.047426Z  INFO applied GEMM plan constraint source_operation=0 matching_plans=2 constraint=GemmPlanConstraint { source_operation: 0, orientation: Normal, row_partitions: 3, column_partitions: 27, inner_partitions: 18, result_row_partitions: 18, result_column_partitions: 1, output_column_block: 160, weight_memory_class: Ipu21Interleaved, reduction_staging: Complete, local_weight_staging: Direct }
2026-09-06T11:28:00.428715Z  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 }
2026-09-06T11:28:00.977193Z  INFO retained operator-plan finalist finalist=0 values=7 operations=4 estimated_cycles=403663 estimated_exchange_cycles=158840 exchange_row_bytes=35084 peak_standard_bytes=149772 peak_interleaved_bytes=146432 peak_total_bytes=250636 maximum_standard_allocation_bytes=114688 active_tile_counts={1440, 1458} padding_group_counts={} conversion_sources=[Some(OperationId(2))]
2026-09-06T11:28:00.982915Z  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=1230 success=true
2026-09-06T11:28:04.384275Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="select_finalist"}: selected analytical operator plan estimated_cycles=374698 estimated_exchange_cycles=129560
2026-09-06T11:28:04.477559Z  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
2026-09-06T11:28:04.479753Z  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=3496 success=true
2026-09-06T11:28:04.479772Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}: lowered graph for package construction logical_shards=25866 exchange_phases=4
2026-09-06T11:28:04.479969Z  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
2026-09-06T11:28:04.480665Z  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
2026-09-06T11:28:04.481397Z  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
2026-09-06T11:28:04.483137Z  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
2026-09-06T11:28:04.606810Z  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=123 success=true
2026-09-06T11:29:28.577643Z  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=256895 maximum_identical_destinations=1
2026-09-06T11:29:28.577684Z  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=36203 selected_horizon=36203 endpoint_lower_bound=20160 lower_bound_gap=16043 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T11:29:28.804569Z  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=937 row_words=967 horizon=36203
2026-09-06T11:29:46.298037Z  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=16053 maximum_identical_destinations=1
2026-09-06T11:29:46.298069Z  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=47792 selected_horizon=47792 endpoint_lower_bound=33408 lower_bound_gap=14384 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T11:29:46.384285Z  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=1151 row_words=1044 horizon=47792
2026-09-06T11:29:50.222030Z  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
2026-09-06T11:29:50.222062Z  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
2026-09-06T11:29:50.262741Z  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
2026-09-06T11:29:50.277411Z  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=105670 success=true
2026-09-06T11:29:50.500313Z  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
2026-09-06T11:29:50.500350Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}: allocated package support memory linked_end=319176 profile_bytes=132 exchange_table_bytes=8448 host_code_bytes=1236 generated_code_bytes=1564 code_address=320416 standard_ranges=[(409600, 524288)]
2026-09-06T11:29:50.606726Z  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=106 success=true
2026-09-06T11:29:50.615268Z  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
2026-09-06T11:31:05.545925Z  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=256895 maximum_identical_destinations=1
2026-09-06T11:31:05.545963Z  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=36203 selected_horizon=36203 endpoint_lower_bound=20160 lower_bound_gap=16043 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T11:31:05.781625Z  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=937 row_words=967 horizon=36203
2026-09-06T11:31:35.716637Z  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=16053 maximum_identical_destinations=1
2026-09-06T11:31:35.716678Z  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=47792 selected_horizon=47792 endpoint_lower_bound=33408 lower_bound_gap=14384 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T11:31:35.864273Z  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=1151 row_words=1044 horizon=47792
2026-09-06T11:31:42.501904Z  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
2026-09-06T11:31:42.501943Z  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
2026-09-06T11:31:42.568843Z  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
2026-09-06T11:31:42.590339Z  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=111983 success=true
2026-09-06T11:31:44.382585Z  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
2026-09-06T11:33:05.585871Z  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=256895 maximum_identical_destinations=1
2026-09-06T11:33:05.585921Z  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=36203 selected_horizon=36203 endpoint_lower_bound=20160 lower_bound_gap=16043 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T11:33:05.959652Z  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=937 row_words=967 horizon=36203
2026-09-06T11:33:24.718091Z  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=16053 maximum_identical_destinations=1
2026-09-06T11:33:24.718129Z  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=39018 selected_horizon=39018 endpoint_lower_bound=33408 lower_bound_gap=5610 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T11:33:24.805232Z  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=1151 row_words=1042 horizon=39018
2026-09-06T11:33:28.931063Z  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
2026-09-06T11:33:28.931087Z  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
2026-09-06T11:33:28.971724Z  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
2026-09-06T11:33:29.000715Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: evaluated exchange placement finalist offset=4096 baseline_score=446943854592 score=170122346496 baseline_cycles=97251 candidate_cycles=88477 row_bytes=8448 row_capacity=16320 accepted=true
2026-09-06T11:33:29.036999Z  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=106446 success=true
2026-09-06T11:33:29.149854Z  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=7 success=true
2026-09-06T11:33:29.163973Z  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=14 success=true
2026-09-06T11:33:29.271509Z  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=99 success=true
2026-09-06T11:33:29.341179Z  INFO writing application package tiles=1472
2026-09-06T11:33:29.420186Z  INFO application package written
2026-09-06T11:33:29.420244Z  INFO reading application package
2026-09-06T11:33:29.550840Z  INFO application package read tiles=1472 compiler=0.1.0
2026-09-06T11:33:29.554308Z  INFO waiting for hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/device.lock
2026-09-06T11:33:29.554318Z  INFO acquired hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/device.lock
2026-09-06T11:33:29.554323Z  INFO opening IPU device path="/dev/ipu0"
2026-09-06T11:33:29.554352Z  INFO IPU device attached path=/dev/ipu0
2026-09-06T11:33:29.554355Z  INFO initializing IPU device
2026-09-06T11:33:29.562398Z  INFO IPU device initialized
2026-09-06T11:33:29.562405Z  INFO replaying device configuration register_writes=2003
2026-09-06T11:33:29.569065Z  INFO loading application tile_count=1472 final_mark=23
2026-09-06T11:33:29.853442Z  INFO application loaded and initial synchronization completed tile_count=1472
2026-09-06T11:33:31.255499Z  INFO starting host exchange session startup_mark=23
2026-09-06T11:33:31.255532Z  INFO attaching host exchange pages pages=2
2026-09-06T11:33:31.256188Z  INFO host exchange session started
2026-09-06T11:33:31.256322Z  INFO invoking streaming host exchange call call="initialize" command=0 phases=14
2026-09-06T11:33:31.263059Z  INFO invoking streaming host exchange call call="run" command=0 phases=23
profile=artifacts/layout-sweep/up-07/execution.ipuprofile tiles=1472 samples=25608
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=45411840 weightBytes=19869696 cycles=246030 minimumTileCycles=229680 deviceMicroseconds=164.020 effectiveGemmTflops=88.149 peakTflops=282.624 efficiencyPercent=31.19 maximumAbsoluteError=0.009766
package=artifacts/layout-sweep/up-07/model.ipuexe tiles=1472 hardwareTest=PASS