2026-09-06T12:40:55.573906Z 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 } 2026-09-06T12:40:56.177743Z 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 } 2026-09-06T12:40:56.711228Z 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))] 2026-09-06T12:40:56.716829Z 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=1530 success=true 2026-09-06T12:41:00.727029Z 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 2026-09-06T12:41:00.844556Z 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 2026-09-06T12:41:00.848435Z 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=4131 success=true 2026-09-06T12:41:00.848473Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}: lowered graph for package construction logical_shards=26696 exchange_phases=4 2026-09-06T12:41:00.848761Z 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 2026-09-06T12:41:00.850233Z 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 2026-09-06T12:41:00.850579Z 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 2026-09-06T12:41:00.854057Z 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 2026-09-06T12:41:00.995585Z 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=141 success=true 2026-09-06T12:41:01.482893Z 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 2026-09-06T12:41:01.482928Z 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=4166 selected_horizon=4149 endpoint_lower_bound=3408 lower_bound_gap=741 selected_kind="critical-neighborhood" neighborhood_improvements=1 2026-09-06T12:41:01.495408Z 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=1364 row_words=79 horizon=4149 2026-09-06T12:41:11.695715Z 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=4028 ordinary_horizon=41096 paired_horizon=42084 use_paired=false 2026-09-06T12:41:11.762625Z 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 2026-09-06T12:41:11.762649Z 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=41096 selected_horizon=41096 endpoint_lower_bound=33408 lower_bound_gap=7688 selected_kind="full-duplex" neighborhood_improvements=0 2026-09-06T12:41:11.793395Z 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=992 row_words=266 horizon=41096 2026-09-06T12:41:12.417112Z 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 2026-09-06T12:41:12.417137Z 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=5966 selected_horizon=5909 endpoint_lower_bound=4560 lower_bound_gap=1349 selected_kind="critical-neighborhood" neighborhood_improvements=1 2026-09-06T12:41:12.434078Z 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=532 row_words=130 horizon=5909 2026-09-06T12:41:12.440382Z 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=11444 success=true 2026-09-06T12:41:12.817364Z 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=4 success=true 2026-09-06T12:41:12.817391Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}: allocated package support memory linked_end=317036 profile_bytes=132 exchange_table_bytes=1872 host_code_bytes=2400 generated_code_bytes=1504 code_address=319440 standard_ranges=[(409600, 524288)] 2026-09-06T12:41:12.941133Z 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=123 success=true 2026-09-06T12:41:12.955298Z 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 2026-09-06T12:41:13.310572Z 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 2026-09-06T12:41:13.310599Z 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=4166 selected_horizon=4149 endpoint_lower_bound=3408 lower_bound_gap=741 selected_kind="critical-neighborhood" neighborhood_improvements=1 2026-09-06T12:41:13.318121Z 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=1364 row_words=79 horizon=4149 2026-09-06T12:41:23.979501Z 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=4028 ordinary_horizon=41096 paired_horizon=42084 use_paired=false 2026-09-06T12:41:24.075352Z 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 2026-09-06T12:41:24.075379Z 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=41096 selected_horizon=41096 endpoint_lower_bound=33408 lower_bound_gap=7688 selected_kind="full-duplex" neighborhood_improvements=0 2026-09-06T12:41:24.123961Z 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=992 row_words=266 horizon=41096 2026-09-06T12:41:24.337234Z 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 2026-09-06T12:41:24.348683Z 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 2026-09-06T12:41:24.348699Z 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=5909 selected_horizon=5909 endpoint_lower_bound=4560 lower_bound_gap=1349 selected_kind="reused" neighborhood_improvements=0 2026-09-06T12:41:24.375587Z 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=532 row_words=130 horizon=5909 2026-09-06T12:41:24.382463Z 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=11441 success=true 2026-09-06T12:41:26.259662Z 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 2026-09-06T12:41:26.323011Z 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 2026-09-06T12:41:26.327294Z 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 2026-09-06T12:41:26.327304Z 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=4149 selected_horizon=4149 endpoint_lower_bound=3408 lower_bound_gap=741 selected_kind="reused" neighborhood_improvements=0 2026-09-06T12:41:26.334666Z 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=1364 row_words=79 horizon=4149 2026-09-06T12:41:32.919694Z 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=4028 ordinary_horizon=41111 paired_horizon=32990 use_paired=true 2026-09-06T12:41:32.991236Z 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 2026-09-06T12:41:32.991262Z 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=32990 selected_horizon=32990 endpoint_lower_bound=23544 lower_bound_gap=9446 selected_kind="full-duplex" neighborhood_improvements=0 2026-09-06T12:41:33.038563Z 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=874 row_words=425 horizon=32990 2026-09-06T12:41:33.179697Z 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 2026-09-06T12:41:33.186801Z 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 2026-09-06T12:41:33.186811Z 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=5909 selected_horizon=5909 endpoint_lower_bound=4560 lower_bound_gap=1349 selected_kind="reused" neighborhood_improvements=0 2026-09-06T12:41:33.203028Z 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=532 row_words=130 horizon=5909 2026-09-06T12:41:33.213323Z 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=58186 candidate_cycles=50080 row_bytes=2444 row_capacity=16320 accepted=true 2026-09-06T12:41:33.222101Z 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=8839 success=true 2026-09-06T12:41:33.414978Z 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 2026-09-06T12:41:33.422248Z 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=7 success=true 2026-09-06T12:41:33.479855Z 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=54 success=true 2026-09-06T12:41:33.527139Z INFO writing application package tiles=1472 2026-09-06T12:41:33.550510Z INFO application package written 2026-09-06T12:41:33.551088Z INFO reading application package 2026-09-06T12:41:33.602663Z INFO application package read tiles=1472 compiler=0.1.0 2026-09-06T12:41:33.602971Z INFO waiting for hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/alternatives-followup/device.lock 2026-09-06T12:41:40.139672Z INFO acquired hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/alternatives-followup/device.lock 2026-09-06T12:41:40.139692Z INFO opening IPU device path="/dev/ipu0" 2026-09-06T12:41:40.139723Z INFO IPU device attached path=/dev/ipu0 2026-09-06T12:41:40.139726Z INFO initializing IPU device 2026-09-06T12:41:40.147675Z INFO IPU device initialized 2026-09-06T12:41:40.147689Z INFO replaying device configuration register_writes=2003 2026-09-06T12:41:40.157338Z INFO loading application tile_count=1472 final_mark=23 2026-09-06T12:41:40.404954Z INFO application loaded and initial synchronization completed tile_count=1472 2026-09-06T12:41:42.838806Z INFO starting host exchange session startup_mark=23 2026-09-06T12:41:42.838846Z INFO attaching host exchange pages pages=2 2026-09-06T12:41:42.839260Z INFO host exchange session started 2026-09-06T12:41:42.839372Z INFO invoking streaming host exchange call call="initialize" command=0 phases=14 2026-09-06T12:41:42.845912Z INFO invoking streaming host exchange call call="run" command=0 phases=59 profile=artifacts/layout-sweep/alternatives-followup/mapping-transpose-4-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=182616 minimumTileCycles=172404 deviceMicroseconds=121.744 effectiveGemmTflops=118.758 peakTflops=282.624 efficiencyPercent=42.02 maximumAbsoluteError=0.011719 package=artifacts/layout-sweep/alternatives-followup/mapping-transpose-4-mixed/model.ipuexe tiles=1472 hardwareTest=PASS