2026-09-06T11:45:11.348322Z INFO applied GEMM plan constraint source_operation=0 matching_plans=1 constraint=GemmPlanConstraint { source_operation: 0, orientation: Normal, row_partitions: 3, column_partitions: 90, inner_partitions: 5, result_row_partitions: 5, result_column_partitions: 1, output_column_block: 48, weight_memory_class: Ipu21Interleaved, reduction_staging: Complete, local_weight_staging: Direct } 2026-09-06T11:45:11.756138Z INFO applied GEMM plan constraint source_operation=2 matching_plans=1 constraint=GemmPlanConstraint { source_operation: 2, orientation: Normal, row_partitions: 3, column_partitions: 36, inner_partitions: 13, result_row_partitions: 13, result_column_partitions: 1, output_column_block: 32, weight_memory_class: Ipu21Interleaved, reduction_staging: Complete, local_weight_staging: Direct } 2026-09-06T11:45:12.413175Z INFO retained operator-plan finalist finalist=0 values=7 operations=4 estimated_cycles=352546 estimated_exchange_cycles=155000 exchange_row_bytes=34220 peak_standard_bytes=214444 peak_interleaved_bytes=77312 peak_total_bytes=268716 maximum_standard_allocation_bytes=180224 active_tile_counts={1350, 1404} padding_group_counts={} conversion_sources=[Some(OperationId(2))] 2026-09-06T11:45:12.419046Z 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=1359 success=true 2026-09-06T11:45:15.699933Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="select_finalist"}: selected analytical operator plan estimated_cycles=262666 estimated_exchange_cycles=77608 2026-09-06T11:45:15.855122Z 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 2026-09-06T11:45:15.859076Z 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=3439 success=true 2026-09-06T11:45:15.859107Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}: lowered graph for package construction logical_shards=25056 exchange_phases=4 2026-09-06T11:45:15.859419Z 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 2026-09-06T11:45:15.861980Z 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=2 success=true 2026-09-06T11:45:15.862364Z 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 2026-09-06T11:45:15.865430Z 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 2026-09-06T11:45:15.992808Z 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=127 success=true 2026-09-06T11:45:16.701295Z 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=18830 maximum_identical_destinations=1 2026-09-06T11:45:16.701346Z 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=6696 selected_horizon=6688 endpoint_lower_bound=4944 lower_bound_gap=1744 selected_kind="critical-neighborhood" neighborhood_improvements=1 2026-09-06T11:45:16.716438Z 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=390 row_words=96 horizon=6688 2026-09-06T11:45:30.944374Z 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=3703 ordinary_horizon=61717 paired_horizon=42428 use_paired=true 2026-09-06T11:45:31.073547Z 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=5509 maximum_identical_destinations=1 2026-09-06T11:45:31.073592Z 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=42428 selected_horizon=42428 endpoint_lower_bound=30408 lower_bound_gap=12020 selected_kind="full-duplex" neighborhood_improvements=0 2026-09-06T11:45:31.136396Z 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=753 row_words=395 horizon=42428 2026-09-06T11:45:34.856565Z 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=35568 maximum_identical_destinations=1 2026-09-06T11:45:34.856634Z 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=6113 selected_horizon=5268 endpoint_lower_bound=4096 lower_bound_gap=1172 selected_kind="critical-neighborhood" neighborhood_improvements=2 2026-09-06T11:45:34.893690Z 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=905 row_words=163 horizon=5268 2026-09-06T11:45:34.911690Z 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=18918 success=true 2026-09-06T11:45:35.553095Z 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=7 success=true 2026-09-06T11:45:35.553170Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}: allocated package support memory linked_end=319176 profile_bytes=144 exchange_table_bytes=2348 host_code_bytes=2516 generated_code_bytes=1612 code_address=321696 standard_ranges=[(409600, 524288)] 2026-09-06T11:45:35.661361Z 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=108 success=true 2026-09-06T11:45:35.670159Z 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 2026-09-06T11:45:35.812053Z 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 2026-09-06T11:45:35.821163Z 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=18830 maximum_identical_destinations=1 2026-09-06T11:45:35.821183Z 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=6688 selected_horizon=6688 endpoint_lower_bound=4944 lower_bound_gap=1744 selected_kind="reused" neighborhood_improvements=0 2026-09-06T11:45:35.836013Z 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=390 row_words=96 horizon=6688 2026-09-06T11:45:48.710971Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: compared ordinary and paired exchange schedules phase=2 candidates=3703 ordinary_horizon=61717 paired_horizon=42428 use_paired=true 2026-09-06T11:45:48.794353Z 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=5509 maximum_identical_destinations=1 2026-09-06T11:45:48.794386Z 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=42428 selected_horizon=42428 endpoint_lower_bound=30408 lower_bound_gap=12020 selected_kind="full-duplex" neighborhood_improvements=0 2026-09-06T11:45:48.834939Z 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=753 row_words=395 horizon=42428 2026-09-06T11:45:49.169914Z 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 2026-09-06T11:45:49.188558Z 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=35568 maximum_identical_destinations=1 2026-09-06T11:45:49.188581Z 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=5268 selected_horizon=5268 endpoint_lower_bound=4096 lower_bound_gap=1172 selected_kind="reused" neighborhood_improvements=0 2026-09-06T11:45:49.224949Z 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=905 row_words=163 horizon=5268 2026-09-06T11:45:49.236963Z 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=13575 success=true 2026-09-06T11:45:50.771155Z 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 2026-09-06T11:45:50.905459Z 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 2026-09-06T11:45:50.914490Z 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=18830 maximum_identical_destinations=1 2026-09-06T11:45:50.914511Z 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=6688 selected_horizon=6688 endpoint_lower_bound=4944 lower_bound_gap=1744 selected_kind="reused" neighborhood_improvements=0 2026-09-06T11:45:50.929259Z 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=390 row_words=96 horizon=6688 2026-09-06T11:46:04.895328Z 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=2 candidates=3241 ordinary_horizon=55576 paired_horizon=53980 use_paired=true 2026-09-06T11:46:05.015425Z 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=5509 maximum_identical_destinations=1 2026-09-06T11:46:05.015456Z 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=53980 selected_horizon=53980 endpoint_lower_bound=45864 lower_bound_gap=8116 selected_kind="full-duplex" neighborhood_improvements=0 2026-09-06T11:46:05.075503Z 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=631 row_words=381 horizon=53980 2026-09-06T11:46:05.368517Z 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 2026-09-06T11:46:05.384331Z 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=35568 maximum_identical_destinations=1 2026-09-06T11:46:05.384347Z 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=5268 selected_horizon=5268 endpoint_lower_bound=4096 lower_bound_gap=1172 selected_kind="reused" neighborhood_improvements=0 2026-09-06T11:46:05.418782Z 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=905 row_words=163 horizon=5268 2026-09-06T11:46:05.437557Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: evaluated exchange placement finalist offset=8192 baseline_score=351356092416 score=128732921856 baseline_cycles=60273 candidate_cycles=71825 row_bytes=2284 row_capacity=16320 accepted=false 2026-09-06T11:46:05.448466Z 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=16211 success=true 2026-09-06T11:46:05.771803Z 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=16 success=true 2026-09-06T11:46:05.783318Z 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=11 success=true 2026-09-06T11:46:05.888954Z 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=101 success=true 2026-09-06T11:46:05.959274Z INFO writing application package tiles=1472 2026-09-06T11:46:06.006525Z INFO application package written 2026-09-06T11:46:06.008866Z INFO reading application package 2026-09-06T11:46:06.114382Z INFO application package read tiles=1472 compiler=0.1.0 2026-09-06T11:46:06.117225Z INFO waiting for hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/device.lock 2026-09-06T11:46:06.117236Z INFO acquired hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/device.lock 2026-09-06T11:46:06.117241Z INFO opening IPU device path="/dev/ipu0" 2026-09-06T11:46:06.117270Z INFO IPU device attached path=/dev/ipu0 2026-09-06T11:46:06.117274Z INFO initializing IPU device 2026-09-06T11:46:06.125094Z INFO IPU device initialized 2026-09-06T11:46:06.125099Z INFO replaying device configuration register_writes=2003 2026-09-06T11:46:06.133964Z INFO loading application tile_count=1472 final_mark=23 2026-09-06T11:46:06.335004Z INFO application loaded and initial synchronization completed tile_count=1472 2026-09-06T11:46:08.875246Z INFO starting host exchange session startup_mark=23 2026-09-06T11:46:08.875276Z INFO attaching host exchange pages pages=2 2026-09-06T11:46:08.876042Z INFO host exchange session started 2026-09-06T11:46:08.876085Z INFO invoking streaming host exchange call call="initialize" command=0 phases=12 2026-09-06T11:46:08.881695Z INFO invoking streaming host exchange call call="run" command=0 phases=65 profile=artifacts/layout-sweep/joint-rows-3/execution.ipuprofile tiles=1472 samples=28301 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=1404 executionTiles=1472 inputBytes=157680000 weightBytes=20393472 cycles=215076 minimumTileCycles=199812 deviceMicroseconds=143.384 effectiveGemmTflops=100.835 peakTflops=282.624 efficiencyPercent=35.68 maximumAbsoluteError=0.011719 package=artifacts/layout-sweep/joint-rows-3/model.ipuexe tiles=1472 hardwareTest=PASS