2026-09-06T12:38:14.525407Z  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 }
2026-09-06T12:38:15.144780Z  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: Complete, local_weight_staging: Direct }
2026-09-06T12:38:16.028722Z  INFO retained operator-plan finalist finalist=0 values=7 operations=4 estimated_cycles=259590 estimated_exchange_cycles=123960 exchange_row_bytes=27236 peak_standard_bytes=169572 peak_interleaved_bytes=60416 peak_total_bytes=229988 maximum_standard_allocation_bytes=114688 active_tile_counts={1440, 1472} padding_group_counts={} conversion_sources=[Some(OperationId(2))]
2026-09-06T12:38:16.037535Z  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=1975 success=true
2026-09-06T12:38:20.133479Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="select_finalist"}: selected analytical operator plan estimated_cycles=192930 estimated_exchange_cycles=70152
2026-09-06T12:38:20.219788Z  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
2026-09-06T12:38:20.221882Z  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=4184 success=true
2026-09-06T12:38:20.221904Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}: lowered graph for package construction logical_shards=26264 exchange_phases=4
2026-09-06T12:38:20.222098Z  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
2026-09-06T12:38:20.222922Z  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
2026-09-06T12:38:20.223168Z  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
2026-09-06T12:38:20.225003Z  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
2026-09-06T12:38:20.411072Z  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=186 success=true
2026-09-06T12:38:20.793133Z  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
2026-09-06T12:38:20.793168Z  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=4544 selected_horizon=3836 endpoint_lower_bound=3408 lower_bound_gap=428 selected_kind="matching-waves" neighborhood_improvements=0
2026-09-06T12:38:20.806122Z  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=1090 row_words=77 horizon=3836
2026-09-06T12:38:25.107277Z  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
2026-09-06T12:38:25.107317Z  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=45136 selected_horizon=45136 endpoint_lower_bound=33408 lower_bound_gap=11728 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:38:25.160641Z  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=1080 row_words=299 horizon=45136
2026-09-06T12:38:28.384842Z  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=63720 maximum_identical_destinations=1
2026-09-06T12:38:28.384878Z  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=8473 selected_horizon=8473 endpoint_lower_bound=4704 lower_bound_gap=3769 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:38:28.446008Z  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=1206 row_words=278 horizon=8473
2026-09-06T12:38:28.467082Z  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=8055 success=true
2026-09-06T12:38:29.166354Z  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=5 success=true
2026-09-06T12:38:29.166383Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}: allocated package support memory linked_end=317036 profile_bytes=132 exchange_table_bytes=2412 host_code_bytes=2416 generated_code_bytes=1544 code_address=319456 standard_ranges=[(409600, 524288)]
2026-09-06T12:38:29.282102Z  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=115 success=true
2026-09-06T12:38:29.294870Z  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
2026-09-06T12:38:29.445945Z  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
2026-09-06T12:38:29.453154Z  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
2026-09-06T12:38:29.453170Z  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=3836 selected_horizon=3836 endpoint_lower_bound=3408 lower_bound_gap=428 selected_kind="reused" neighborhood_improvements=0
2026-09-06T12:38:29.465598Z  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=1090 row_words=77 horizon=3836
2026-09-06T12:38:34.154103Z  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
2026-09-06T12:38:34.154154Z  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=45136 selected_horizon=45136 endpoint_lower_bound=33408 lower_bound_gap=11728 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:38:34.209769Z  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=1080 row_words=299 horizon=45136
2026-09-06T12:38:34.607305Z  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
2026-09-06T12:38:34.627812Z  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=63720 maximum_identical_destinations=1
2026-09-06T12:38:34.627827Z  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=8473 selected_horizon=8473 endpoint_lower_bound=4704 lower_bound_gap=3769 selected_kind="reused" neighborhood_improvements=0
2026-09-06T12:38:34.666543Z  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=1206 row_words=278 horizon=8473
2026-09-06T12:38:34.679640Z  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=5397 success=true
2026-09-06T12:38:35.985297Z  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
2026-09-06T12:38:36.086073Z  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
2026-09-06T12:38:36.092918Z  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
2026-09-06T12:38:36.092934Z  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=3836 selected_horizon=3836 endpoint_lower_bound=3408 lower_bound_gap=428 selected_kind="reused" neighborhood_improvements=0
2026-09-06T12:38:36.105467Z  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=1090 row_words=77 horizon=3836
2026-09-06T12:38:40.778983Z  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
2026-09-06T12:38:40.779017Z  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=40657 selected_horizon=40657 endpoint_lower_bound=33408 lower_bound_gap=7249 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:38:40.830673Z  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=124 row_words=280 horizon=40657
2026-09-06T12:38:41.411045Z  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
2026-09-06T12:38:41.443472Z  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=63720 maximum_identical_destinations=1
2026-09-06T12:38:41.443495Z  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=8473 selected_horizon=8473 endpoint_lower_bound=4704 lower_bound_gap=3769 selected_kind="reused" neighborhood_improvements=0
2026-09-06T12:38:41.506494Z  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=1206 row_words=278 horizon=8473
2026-09-06T12:38:41.536026Z  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=64544 candidate_cycles=60065 row_bytes=2412 row_capacity=16320 accepted=true
2026-09-06T12:38:41.548414Z  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=6868 success=true
2026-09-06T12:38:41.848838Z  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=11 success=true
2026-09-06T12:38:41.859925Z  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
2026-09-06T12:38:41.959022Z  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=94 success=true
2026-09-06T12:38:42.033069Z  INFO writing application package tiles=1472
2026-09-06T12:38:42.071595Z  INFO application package written
2026-09-06T12:38:42.072617Z  INFO reading application package
2026-09-06T12:38:42.177526Z  INFO application package read tiles=1472 compiler=0.1.0
2026-09-06T12:38:42.178123Z  INFO waiting for hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/alternatives-v1/device.lock
2026-09-06T12:38:55.342031Z  INFO acquired hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/alternatives-v1/device.lock
2026-09-06T12:38:55.342098Z  INFO opening IPU device path="/dev/ipu0"
2026-09-06T12:38:55.342170Z  INFO IPU device attached path=/dev/ipu0
2026-09-06T12:38:55.342177Z  INFO initializing IPU device
2026-09-06T12:38:55.350172Z  INFO IPU device initialized
2026-09-06T12:38:55.350256Z  INFO replaying device configuration register_writes=2003
2026-09-06T12:38:55.359255Z  INFO loading application tile_count=1472 final_mark=23
2026-09-06T12:38:55.625706Z  INFO application loaded and initial synchronization completed tile_count=1472
2026-09-06T12:38:58.306301Z  INFO starting host exchange session startup_mark=23
2026-09-06T12:38:58.306323Z  INFO attaching host exchange pages pages=2
2026-09-06T12:38:58.306839Z  INFO host exchange session started
2026-09-06T12:38:58.306882Z  INFO invoking streaming host exchange call call="initialize" command=0 phases=14
2026-09-06T12:38:58.312648Z  INFO invoking streaming host exchange call call="run" command=0 phases=59
profile=artifacts/layout-sweep/alternatives-v1/mapping-transpose-32/execution.ipuprofile tiles=1472 samples=25788
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=194100 minimumTileCycles=180594 deviceMicroseconds=129.400 effectiveGemmTflops=111.732 peakTflops=282.624 efficiencyPercent=39.53 maximumAbsoluteError=0.011719
package=artifacts/layout-sweep/alternatives-v1/mapping-transpose-32/model.ipuexe tiles=1472 hardwareTest=PASS