2026-09-06T12:37:32.398526Z  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 }
2026-09-06T12:37:32.867946Z  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 }
2026-09-06T12:37:33.410499Z  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))]
2026-09-06T12:37:33.415729Z  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=1316 success=true
2026-09-06T12:37:37.666865Z  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
2026-09-06T12:37:37.802444Z  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
2026-09-06T12:37:37.805281Z  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=4389 success=true
2026-09-06T12:37:37.805319Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}: lowered graph for package construction logical_shards=26264 exchange_phases=4
2026-09-06T12:37:37.805585Z  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
2026-09-06T12:37:37.806759Z  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
2026-09-06T12:37:37.807050Z  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
2026-09-06T12:37:37.809410Z  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
2026-09-06T12:37:37.962631Z  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=153 success=true
2026-09-06T12:37:38.486716Z  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
2026-09-06T12:37:38.486768Z  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
2026-09-06T12:37:38.499795Z  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
2026-09-06T12:37:50.127260Z  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
2026-09-06T12:37:50.236282Z  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
2026-09-06T12:37:50.236329Z  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
2026-09-06T12:37:50.287960Z  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
2026-09-06T12:37:57.680242Z  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
2026-09-06T12:37:57.680318Z  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=8048 selected_horizon=8048 endpoint_lower_bound=4704 lower_bound_gap=3344 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:37:57.751508Z  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=1189 row_words=269 horizon=8048
2026-09-06T12:37:57.787405Z  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=19824 success=true
2026-09-06T12:37:58.917737Z  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=96 success=true
2026-09-06T12:37:58.917785Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}: allocated package support memory linked_end=317036 profile_bytes=132 exchange_table_bytes=2220 host_code_bytes=2416 generated_code_bytes=1544 code_address=319456 standard_ranges=[(409600, 524288)]
2026-09-06T12:37:59.190146Z  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=272 success=true
2026-09-06T12:37:59.200357Z  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
2026-09-06T12:37:59.866681Z  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
2026-09-06T12:37:59.866731Z  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
2026-09-06T12:37:59.880724Z  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
2026-09-06T12:38:13.779550Z  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
2026-09-06T12:38:13.876371Z  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
2026-09-06T12:38:13.876397Z  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
2026-09-06T12:38:13.928057Z  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
2026-09-06T12:38:21.143448Z  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
2026-09-06T12:38:21.143483Z  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=8048 selected_horizon=8048 endpoint_lower_bound=4704 lower_bound_gap=3344 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:38:21.206446Z  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=1189 row_words=269 horizon=8048
2026-09-06T12:38:21.238303Z  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=22048 success=true
2026-09-06T12:38:22.816713Z  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
2026-09-06T12:38:22.975809Z  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
2026-09-06T12:38:22.987745Z  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
2026-09-06T12:38:22.987800Z  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
2026-09-06T12:38:23.000538Z  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
2026-09-06T12:38:34.681837Z  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
2026-09-06T12:38:34.801070Z  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
2026-09-06T12:38:34.801096Z  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
2026-09-06T12:38:34.877550Z  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
2026-09-06T12:38:41.782696Z  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
2026-09-06T12:38:41.782736Z  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=8048 selected_horizon=8048 endpoint_lower_bound=4704 lower_bound_gap=3344 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:38:41.858685Z  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=1189 row_words=269 horizon=8048
2026-09-06T12:38:41.905030Z  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=60325 candidate_cycles=52219 row_bytes=2704 row_capacity=16320 accepted=true
2026-09-06T12:38:41.924326Z  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=20685 success=true
2026-09-06T12:38:42.271339Z  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=9 success=true
2026-09-06T12:38:42.282490Z  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
2026-09-06T12:38:42.376097Z  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
2026-09-06T12:38:42.450838Z  INFO writing application package tiles=1472
2026-09-06T12:38:42.483872Z  INFO application package written
2026-09-06T12:38:42.484587Z  INFO reading application package
2026-09-06T12:38:42.581160Z  INFO application package read tiles=1472 compiler=0.1.0
2026-09-06T12:38:42.581689Z  INFO waiting for hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/alternatives-v1/device.lock
2026-09-06T12:38:58.476904Z  INFO acquired hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/alternatives-v1/device.lock
2026-09-06T12:38:58.476966Z  INFO opening IPU device path="/dev/ipu0"
2026-09-06T12:38:58.477036Z  INFO IPU device attached path=/dev/ipu0
2026-09-06T12:38:58.477043Z  INFO initializing IPU device
2026-09-06T12:38:58.487580Z  INFO IPU device initialized
2026-09-06T12:38:58.487605Z  INFO replaying device configuration register_writes=2003
2026-09-06T12:38:58.513540Z  INFO loading application tile_count=1472 final_mark=23
2026-09-06T12:38:58.833841Z  INFO application loaded and initial synchronization completed tile_count=1472
2026-09-06T12:39:01.399676Z  INFO starting host exchange session startup_mark=23
2026-09-06T12:39:01.399705Z  INFO attaching host exchange pages pages=2
2026-09-06T12:39:01.400143Z  INFO host exchange session started
2026-09-06T12:39:01.400184Z  INFO invoking streaming host exchange call call="initialize" command=0 phases=14
2026-09-06T12:39:01.407032Z  INFO invoking streaming host exchange call call="run" command=0 phases=59
profile=artifacts/layout-sweep/alternatives-v1/mapping-transpose-4/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=184404 minimumTileCycles=172404 deviceMicroseconds=122.936 effectiveGemmTflops=117.607 peakTflops=282.624 efficiencyPercent=41.61 maximumAbsoluteError=0.011719
package=artifacts/layout-sweep/alternatives-v1/mapping-transpose-4/model.ipuexe tiles=1472 hardwareTest=PASS