2026-09-06T12:37:31.865686Z  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 }
2026-09-06T12:37:32.379151Z  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: Ipu21Standard, reduction_staging: Batched(7), local_weight_staging: Direct }
2026-09-06T12:37:32.927247Z  INFO retained operator-plan finalist finalist=0 values=7 operations=4 estimated_cycles=261396 estimated_exchange_cycles=124560 exchange_row_bytes=27240 peak_standard_bytes=169576 peak_interleaved_bytes=60416 peak_total_bytes=229992 maximum_standard_allocation_bytes=114688 active_tile_counts={1440, 1472} padding_group_counts={} conversion_sources=[Some(OperationId(2))]
2026-09-06T12:37:32.932949Z  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=1433 success=true
2026-09-06T12:37:37.528006Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="select_finalist"}: selected analytical operator plan estimated_cycles=208794 estimated_exchange_cycles=84552
2026-09-06T12:37:37.626332Z  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
2026-09-06T12:37:37.629795Z  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=4696 success=true
2026-09-06T12:37:37.629832Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}: lowered graph for package construction logical_shards=26264 exchange_phases=5
2026-09-06T12:37:37.630114Z  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
2026-09-06T12:37:37.631410Z  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
2026-09-06T12:37:37.631715Z  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
2026-09-06T12:37:37.634141Z  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
2026-09-06T12:37:37.793763Z  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=159 success=true
2026-09-06T12:37:38.227783Z  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
2026-09-06T12:37:38.227836Z  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
2026-09-06T12:37:38.239080Z  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
2026-09-06T12:37:46.493786Z  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
2026-09-06T12:37:46.589108Z  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
2026-09-06T12:37:46.589143Z  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
2026-09-06T12:37:46.637552Z  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
2026-09-06T12:37:49.460020Z  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=31968 maximum_identical_destinations=1
2026-09-06T12:37:49.460080Z  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=5132 selected_horizon=5132 endpoint_lower_bound=4128 lower_bound_gap=1004 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:37:49.494264Z  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=1243 row_words=157 horizon=5132
2026-09-06T12:37:52.300339Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges_provisional"}: prepared large physical exchange phase phase=4 transfers=31752 maximum_identical_destinations=1
2026-09-06T12:37:52.300408Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges_provisional"}: optimized physical exchange schedule phase=4 initial_horizon=4979 selected_horizon=4979 endpoint_lower_bound=4272 lower_bound_gap=707 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:37:52.342885Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges_provisional"}: finished large physical exchange phase phase=4 tile=1061 row_words=187 horizon=4979
2026-09-06T12:37:52.358503Z  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=14564 success=true
2026-09-06T12:37:53.087890Z  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=13 success=true
2026-09-06T12:37:53.087946Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}: allocated package support memory linked_end=317036 profile_bytes=140 exchange_table_bytes=2548 host_code_bytes=2424 generated_code_bytes=1616 code_address=319464 standard_ranges=[(409600, 524288)]
2026-09-06T12:37:53.217448Z  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=129 success=true
2026-09-06T12:37:53.227153Z  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
2026-09-06T12:37:53.334821Z  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
2026-09-06T12:37:53.343424Z  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
2026-09-06T12:37:53.343444Z  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
2026-09-06T12:37:53.354253Z  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
2026-09-06T12:38:04.983254Z  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
2026-09-06T12:38:05.160862Z  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
2026-09-06T12:38:05.160907Z  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
2026-09-06T12:38:05.220958Z  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
2026-09-06T12:38:08.237311Z  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=31968 maximum_identical_destinations=1
2026-09-06T12:38:08.237364Z  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=5132 selected_horizon=5132 endpoint_lower_bound=4128 lower_bound_gap=1004 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:38:08.268740Z  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=1243 row_words=157 horizon=5132
2026-09-06T12:38:11.294645Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: prepared large physical exchange phase phase=4 transfers=31752 maximum_identical_destinations=1
2026-09-06T12:38:11.294697Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: optimized physical exchange schedule phase=4 initial_horizon=4979 selected_horizon=4979 endpoint_lower_bound=4272 lower_bound_gap=707 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:38:11.326225Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: finished large physical exchange phase phase=4 tile=1061 row_words=187 horizon=4979
2026-09-06T12:38:11.340601Z  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=18123 success=true
2026-09-06T12:38:12.887121Z  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
2026-09-06T12:38:13.002681Z  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
2026-09-06T12:38:13.010953Z  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
2026-09-06T12:38:13.010977Z  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
2026-09-06T12:38:13.022000Z  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
2026-09-06T12:38:23.050523Z  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
2026-09-06T12:38:23.139896Z  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
2026-09-06T12:38:23.139922Z  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
2026-09-06T12:38:23.182548Z  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
2026-09-06T12:38:25.704120Z  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=31968 maximum_identical_destinations=1
2026-09-06T12:38:25.704155Z  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=5132 selected_horizon=5132 endpoint_lower_bound=4128 lower_bound_gap=1004 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:38:25.738004Z  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=1243 row_words=157 horizon=5132
2026-09-06T12:38:28.650266Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: prepared large physical exchange phase phase=4 transfers=31752 maximum_identical_destinations=1
2026-09-06T12:38:28.650299Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: optimized physical exchange schedule phase=4 initial_horizon=4979 selected_horizon=4979 endpoint_lower_bound=4272 lower_bound_gap=707 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:38:28.681648Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: finished large physical exchange phase phase=4 tile=1061 row_words=187 horizon=4979
2026-09-06T12:38:28.703060Z  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=53877 candidate_cycles=52320 row_bytes=2548 row_capacity=16320 accepted=true
2026-09-06T12:38:28.722173Z  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=17381 success=true
2026-09-06T12:38:29.075118Z  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=15 success=true
2026-09-06T12:38:29.087135Z  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
2026-09-06T12:38:29.180758Z  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=88 success=true
2026-09-06T12:38:29.285691Z  INFO writing application package tiles=1472
2026-09-06T12:38:29.332448Z  INFO application package written
2026-09-06T12:38:29.333425Z  INFO reading application package
2026-09-06T12:38:29.437079Z  INFO application package read tiles=1472 compiler=0.1.0
2026-09-06T12:38:29.437415Z  INFO waiting for hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/alternatives-v1/device.lock
2026-09-06T12:38:42.361643Z  INFO acquired hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/alternatives-v1/device.lock
2026-09-06T12:38:42.361698Z  INFO opening IPU device path="/dev/ipu0"
2026-09-06T12:38:42.361782Z  INFO IPU device attached path=/dev/ipu0
2026-09-06T12:38:42.361789Z  INFO initializing IPU device
2026-09-06T12:38:42.369739Z  INFO IPU device initialized
2026-09-06T12:38:42.369757Z  INFO replaying device configuration register_writes=2003
2026-09-06T12:38:42.378791Z  INFO loading application tile_count=1472 final_mark=23
2026-09-06T12:38:42.651943Z  INFO application loaded and initial synchronization completed tile_count=1472
2026-09-06T12:38:45.188692Z  INFO starting host exchange session startup_mark=23
2026-09-06T12:38:45.188724Z  INFO attaching host exchange pages pages=2
2026-09-06T12:38:45.189220Z  INFO host exchange session started
2026-09-06T12:38:45.189307Z  INFO invoking streaming host exchange call call="initialize" command=0 phases=14
2026-09-06T12:38:45.196774Z  INFO invoking streaming host exchange call call="run" command=0 phases=59
profile=artifacts/layout-sweep/alternatives-v1/down-batch-7/execution.ipuprofile tiles=1472 samples=28700
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=186168 minimumTileCycles=177594 deviceMicroseconds=124.112 effectiveGemmTflops=116.493 peakTflops=282.624 efficiencyPercent=41.22 maximumAbsoluteError=0.011719
package=artifacts/layout-sweep/alternatives-v1/down-batch-7/model.ipuexe tiles=1472 hardwareTest=PASS