2026-09-06T12:37:31.413426Z 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 } 2026-09-06T12:37:32.064144Z 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: 3, result_column_partitions: 1, output_column_block: 48, weight_memory_class: Ipu21Standard, reduction_staging: Complete, local_weight_staging: Direct } 2026-09-06T12:37:32.617635Z INFO retained operator-plan finalist finalist=0 values=7 operations=4 estimated_cycles=311142 estimated_exchange_cycles=164280 exchange_row_bytes=36308 peak_standard_bytes=178644 peak_interleaved_bytes=60416 peak_total_bytes=239060 maximum_standard_allocation_bytes=114688 active_tile_counts={288, 1440, 1472} padding_group_counts={} conversion_sources=[Some(OperationId(2))] 2026-09-06T12:37:32.623012Z 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=1507 success=true 2026-09-06T12:37:36.309367Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="select_finalist"}: selected analytical operator plan estimated_cycles=214110 estimated_exchange_cycles=78672 2026-09-06T12:37:36.441865Z 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 2026-09-06T12:37:36.444311Z 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=3821 success=true 2026-09-06T12:37:36.444343Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}: lowered graph for package construction logical_shards=21656 exchange_phases=4 2026-09-06T12:37:36.444602Z 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 2026-09-06T12:37:36.445906Z 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 2026-09-06T12:37:36.446296Z 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 2026-09-06T12:37:36.449186Z 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 2026-09-06T12:37:36.841604Z 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=392 success=true 2026-09-06T12:37:37.460404Z 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 2026-09-06T12:37:37.460444Z 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=4180 selected_horizon=3779 endpoint_lower_bound=3408 lower_bound_gap=371 selected_kind="matching-waves" neighborhood_improvements=0 2026-09-06T12:37:37.477788Z 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=690 row_words=75 horizon=3779 2026-09-06T12:37:45.668562Z 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=41592 paired_horizon=32939 use_paired=true 2026-09-06T12:37:45.762251Z 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 2026-09-06T12:37:45.762288Z 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=32939 selected_horizon=32939 endpoint_lower_bound=23544 lower_bound_gap=9395 selected_kind="full-duplex" neighborhood_improvements=0 2026-09-06T12:37:45.816175Z 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=1182 row_words=303 horizon=32939 2026-09-06T12:37:46.865568Z 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=15984 maximum_identical_destinations=1 2026-09-06T12:37:46.865617Z 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=23830 selected_horizon=23217 endpoint_lower_bound=22320 lower_bound_gap=897 selected_kind="critical-neighborhood" neighborhood_improvements=1 2026-09-06T12:37:46.874820Z 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=197 row_words=164 horizon=23217 2026-09-06T12:37:46.881519Z 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=10039 success=true 2026-09-06T12:37:47.505747Z 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=8 success=true 2026-09-06T12:37:47.505793Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}: allocated package support memory linked_end=317036 profile_bytes=120 exchange_table_bytes=1656 host_code_bytes=2608 generated_code_bytes=1412 code_address=319648 standard_ranges=[(409600, 524288)] 2026-09-06T12:37:47.601285Z 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=95 success=true 2026-09-06T12:37:47.610272Z 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 2026-09-06T12:37:47.709616Z 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 2026-09-06T12:37:47.717822Z 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 2026-09-06T12:37:47.717849Z 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=3779 selected_horizon=3779 endpoint_lower_bound=3408 lower_bound_gap=371 selected_kind="reused" neighborhood_improvements=0 2026-09-06T12:37:47.728683Z 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=690 row_words=75 horizon=3779 2026-09-06T12:37:57.280512Z 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=41592 paired_horizon=32939 use_paired=true 2026-09-06T12:37:57.376268Z 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 2026-09-06T12:37:57.376310Z 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=32939 selected_horizon=32939 endpoint_lower_bound=23544 lower_bound_gap=9395 selected_kind="full-duplex" neighborhood_improvements=0 2026-09-06T12:37:57.424960Z 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=1182 row_words=303 horizon=32939 2026-09-06T12:37:57.562909Z 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 2026-09-06T12:37:57.571776Z 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=15984 maximum_identical_destinations=1 2026-09-06T12:37:57.571801Z 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=23217 selected_horizon=23217 endpoint_lower_bound=22320 lower_bound_gap=897 selected_kind="reused" neighborhood_improvements=0 2026-09-06T12:37:57.580839Z 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=197 row_words=164 horizon=23217 2026-09-06T12:37:57.586424Z 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=9985 success=true 2026-09-06T12:37:59.350855Z 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 2026-09-06T12:37:59.455088Z 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 2026-09-06T12:37:59.463245Z 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 2026-09-06T12:37:59.463265Z 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=3779 selected_horizon=3779 endpoint_lower_bound=3408 lower_bound_gap=371 selected_kind="reused" neighborhood_improvements=0 2026-09-06T12:37:59.474092Z 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=690 row_words=75 horizon=3779 2026-09-06T12:38:09.951757Z 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=41592 paired_horizon=31382 use_paired=true 2026-09-06T12:38:10.049907Z 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 2026-09-06T12:38:10.049964Z 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=31382 selected_horizon=31382 endpoint_lower_bound=23544 lower_bound_gap=7838 selected_kind="full-duplex" neighborhood_improvements=0 2026-09-06T12:38:10.100890Z 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=1182 row_words=295 horizon=31382 2026-09-06T12:38:10.245328Z 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 2026-09-06T12:38:10.254613Z 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=15984 maximum_identical_destinations=1 2026-09-06T12:38:10.254643Z 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=23217 selected_horizon=23217 endpoint_lower_bound=22320 lower_bound_gap=897 selected_kind="reused" neighborhood_improvements=0 2026-09-06T12:38:10.263872Z 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=197 row_words=164 horizon=23217 2026-09-06T12:38:10.276814Z 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=66983 candidate_cycles=65426 row_bytes=1656 row_capacity=16320 accepted=true 2026-09-06T12:38:10.291511Z 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=12705 success=true 2026-09-06T12:38:10.649300Z 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=28 success=true 2026-09-06T12:38:10.661932Z 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 2026-09-06T12:38:10.762794Z 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=95 success=true 2026-09-06T12:38:10.839879Z INFO writing application package tiles=1472 2026-09-06T12:38:10.884715Z INFO application package written 2026-09-06T12:38:10.885484Z INFO reading application package 2026-09-06T12:38:10.977504Z INFO application package read tiles=1472 compiler=0.1.0 2026-09-06T12:38:10.978034Z INFO waiting for hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/alternatives-v1/device.lock 2026-09-06T12:38:10.978051Z INFO acquired hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/alternatives-v1/device.lock 2026-09-06T12:38:10.978061Z INFO opening IPU device path="/dev/ipu0" 2026-09-06T12:38:10.978135Z INFO IPU device attached path=/dev/ipu0 2026-09-06T12:38:10.978148Z INFO initializing IPU device 2026-09-06T12:38:10.986233Z INFO IPU device initialized 2026-09-06T12:38:10.986247Z INFO replaying device configuration register_writes=2003 2026-09-06T12:38:10.996307Z INFO loading application tile_count=1472 final_mark=23 2026-09-06T12:38:11.281828Z INFO application loaded and initial synchronization completed tile_count=1472 2026-09-06T12:38:13.426814Z INFO starting host exchange session startup_mark=23 2026-09-06T12:38:13.426849Z INFO attaching host exchange pages pages=2 2026-09-06T12:38:13.427347Z INFO host exchange session started 2026-09-06T12:38:13.427394Z INFO invoking streaming host exchange call call="initialize" command=0 phases=14 2026-09-06T12:38:13.434390Z INFO invoking streaming host exchange call call="run" command=0 phases=61 profile=artifacts/layout-sweep/alternatives-v1/down-result-3x1/execution.ipuprofile tiles=1472 samples=22140 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=288 executionTiles=1472 inputBytes=154736640 weightBytes=19869696 cycles=205680 minimumTileCycles=169482 deviceMicroseconds=137.120 effectiveGemmTflops=105.441 peakTflops=282.624 efficiencyPercent=37.31 maximumAbsoluteError=0.011719 package=artifacts/layout-sweep/alternatives-v1/down-result-3x1/model.ipuexe tiles=1472 hardwareTest=PASS