2026-09-06T11:45:05.506132Z 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 } 2026-09-06T11:45:06.011628Z INFO applied GEMM plan constraint source_operation=2 matching_plans=2 constraint=GemmPlanConstraint { source_operation: 2, orientation: Normal, row_partitions: 4, column_partitions: 24, inner_partitions: 15, result_row_partitions: 1, result_column_partitions: 1, output_column_block: 48, weight_memory_class: Ipu21Interleaved, reduction_staging: Streamed, local_weight_staging: Direct } 2026-09-06T11:45:06.555766Z INFO retained operator-plan finalist finalist=0 values=7 operations=4 estimated_cycles=705840 estimated_exchange_cycles=274480 exchange_row_bytes=59400 peak_standard_bytes=174088 peak_interleaved_bytes=88064 peak_total_bytes=262152 maximum_standard_allocation_bytes=114688 active_tile_counts={96, 1440, 1472} padding_group_counts={} conversion_sources=[Some(OperationId(2))] 2026-09-06T11:45:06.560906Z 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=1342 success=true 2026-09-06T11:45:10.125519Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="select_finalist"}: selected analytical operator plan estimated_cycles=1089745 estimated_exchange_cycles=187800 2026-09-06T11:45:10.202843Z 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 2026-09-06T11:45:10.204057Z 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=3643 success=true 2026-09-06T11:45:10.204073Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}: lowered graph for package construction logical_shards=20672 exchange_phases=17 2026-09-06T11:45:10.204273Z 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 2026-09-06T11:45:10.204797Z 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 2026-09-06T11:45:10.205049Z 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 2026-09-06T11:45:10.206669Z 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 2026-09-06T11:45:10.300904Z 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=94 success=true 2026-09-06T11:45:10.646716Z 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 2026-09-06T11:45:10.646746Z 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 2026-09-06T11:45:10.657257Z 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 2026-09-06T11:45:18.126531Z 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=51847 paired_horizon=41194 use_paired=true 2026-09-06T11:45:18.193368Z 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 2026-09-06T11:45:18.193394Z 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=41194 selected_horizon=41194 endpoint_lower_bound=23544 lower_bound_gap=17650 selected_kind="full-duplex" neighborhood_improvements=0 2026-09-06T11:45:18.223022Z 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=301 horizon=41194 2026-09-06T11:45:18.320902Z 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=8019 success=true 2026-09-06T11:45:18.934129Z 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 2026-09-06T11:45:18.934177Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}: allocated package support memory linked_end=317272 profile_bytes=172 exchange_table_bytes=1444 host_code_bytes=3116 generated_code_bytes=2140 code_address=320392 standard_ranges=[(409600, 524288)] 2026-09-06T11:45:19.017125Z 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=82 success=true 2026-09-06T11:45:19.025514Z 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 2026-09-06T11:45:19.122696Z 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 2026-09-06T11:45:19.129523Z 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 2026-09-06T11:45:19.129541Z 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 2026-09-06T11:45:19.139961Z 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 2026-09-06T11:45:27.993785Z 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=51847 paired_horizon=41194 use_paired=true 2026-09-06T11:45:28.093252Z 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 2026-09-06T11:45:28.093285Z 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=41194 selected_horizon=41194 endpoint_lower_bound=23544 lower_bound_gap=17650 selected_kind="full-duplex" neighborhood_improvements=0 2026-09-06T11:45:28.140636Z 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=301 horizon=41194 2026-09-06T11:45:28.165774Z 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 2026-09-06T11:45:28.172601Z 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=4 2026-09-06T11:45:28.177949Z 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=5 2026-09-06T11:45:28.182889Z 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=6 2026-09-06T11:45:28.187262Z 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=7 2026-09-06T11:45:28.191002Z 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=8 2026-09-06T11:45:28.194553Z 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=9 2026-09-06T11:45:28.198240Z 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=10 2026-09-06T11:45:28.201723Z 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=11 2026-09-06T11:45:28.205954Z 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=12 2026-09-06T11:45:28.209631Z 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=13 2026-09-06T11:45:28.213408Z 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=14 2026-09-06T11:45:28.217096Z 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=15 2026-09-06T11:45:28.220711Z 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=16 2026-09-06T11:45:28.221250Z 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=9204 success=true 2026-09-06T11:45:29.293137Z 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 2026-09-06T11:45:29.470055Z 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 2026-09-06T11:45:29.479030Z 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 2026-09-06T11:45:29.479068Z 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 2026-09-06T11:45:29.494324Z 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 2026-09-06T11:45:38.403719Z 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=32939 use_paired=true 2026-09-06T11:45:38.497436Z 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 2026-09-06T11:45:38.497470Z 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=32939 selected_horizon=32939 endpoint_lower_bound=23544 lower_bound_gap=9395 selected_kind="full-duplex" neighborhood_improvements=0 2026-09-06T11:45:38.545105Z 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=303 horizon=32939 2026-09-06T11:45:38.570868Z 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 2026-09-06T11:45:38.574964Z 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=4 2026-09-06T11:45:38.578880Z 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=5 2026-09-06T11:45:38.582314Z 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=6 2026-09-06T11:45:38.586882Z 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=7 2026-09-06T11:45:38.590630Z 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=8 2026-09-06T11:45:38.594335Z 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=9 2026-09-06T11:45:38.597805Z 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=10 2026-09-06T11:45:38.601434Z 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=11 2026-09-06T11:45:38.604928Z 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=12 2026-09-06T11:45:38.608560Z 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=13 2026-09-06T11:45:38.612273Z 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=14 2026-09-06T11:45:38.616176Z 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=15 2026-09-06T11:45:38.619484Z 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=16 2026-09-06T11:45:38.632771Z 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=445300015104 score=170111729664 baseline_cycles=119550 candidate_cycles=111295 row_bytes=1452 row_capacity=16320 accepted=true 2026-09-06T11:45:38.647017Z 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=10425 success=true 2026-09-06T11:45:38.987267Z 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=33 success=true 2026-09-06T11:45:39.002478Z 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=15 success=true 2026-09-06T11:45:39.094560Z 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=86 success=true 2026-09-06T11:45:39.169586Z INFO writing application package tiles=1472 2026-09-06T11:45:39.254990Z INFO application package written 2026-09-06T11:45:39.257163Z INFO reading application package 2026-09-06T11:45:39.359786Z INFO application package read tiles=1472 compiler=0.1.0 2026-09-06T11:45:39.360562Z INFO waiting for hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/device.lock 2026-09-06T11:45:39.360578Z INFO acquired hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/device.lock 2026-09-06T11:45:39.360584Z INFO opening IPU device path="/dev/ipu0" 2026-09-06T11:45:39.360625Z INFO IPU device attached path=/dev/ipu0 2026-09-06T11:45:39.360628Z INFO initializing IPU device 2026-09-06T11:45:39.368716Z INFO IPU device initialized 2026-09-06T11:45:39.368721Z INFO replaying device configuration register_writes=2003 2026-09-06T11:45:39.378531Z INFO loading application tile_count=1472 final_mark=23 2026-09-06T11:45:39.693001Z INFO application loaded and initial synchronization completed tile_count=1472 2026-09-06T11:45:42.343599Z INFO starting host exchange session startup_mark=23 2026-09-06T11:45:42.343650Z INFO attaching host exchange pages pages=2 2026-09-06T11:45:42.344188Z INFO host exchange session started 2026-09-06T11:45:42.344275Z INFO invoking streaming host exchange call call="initialize" command=0 phases=14 2026-09-06T11:45:42.352435Z INFO invoking streaming host exchange call call="run" command=0 phases=67 profile=artifacts/layout-sweep/down-25/execution.ipuprofile tiles=1472 samples=42020 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=96 executionTiles=1472 inputBytes=154736640 weightBytes=19869696 cycles=482640 minimumTileCycles=456618 deviceMicroseconds=321.760 effectiveGemmTflops=44.935 peakTflops=282.624 efficiencyPercent=15.90 maximumAbsoluteError=0.011719 package=artifacts/layout-sweep/down-25/model.ipuexe tiles=1472 hardwareTest=PASS