2026-09-06T12:37:31.413739Z  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: 2, result_column_partitions: 1, output_column_block: 48, weight_memory_class: Ipu21Interleaved, reduction_staging: Complete, local_weight_staging: Direct }
2026-09-06T12:37:31.957694Z  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 }
2026-09-06T12:37:32.501333Z  INFO retained operator-plan finalist finalist=0 values=7 operations=4 estimated_cycles=281020 estimated_exchange_cycles=132280 exchange_row_bytes=29108 peak_standard_bytes=171444 peak_interleaved_bytes=60416 peak_total_bytes=231860 maximum_standard_allocation_bytes=114688 active_tile_counts={736, 1440} padding_group_counts={} conversion_sources=[Some(OperationId(2))]
2026-09-06T12:37:32.508011Z  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=1392 success=true
2026-09-06T12:37:36.052876Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="select_finalist"}: selected analytical operator plan estimated_cycles=207936 estimated_exchange_cycles=72264
2026-09-06T12:37:36.137342Z  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
2026-09-06T12:37:36.139529Z  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=3631 success=true
2026-09-06T12:37:36.139560Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}: lowered graph for package construction logical_shards=22584 exchange_phases=4
2026-09-06T12:37:36.140703Z  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=1 success=true
2026-09-06T12:37:36.141455Z  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
2026-09-06T12:37:36.141679Z  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
2026-09-06T12:37:36.143696Z  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
2026-09-06T12:37:36.374994Z  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=231 success=true
2026-09-06T12:37:36.974609Z  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=10222 maximum_identical_destinations=1
2026-09-06T12:37:36.974646Z  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=9486 selected_horizon=9481 endpoint_lower_bound=8832 lower_bound_gap=649 selected_kind="critical-neighborhood" neighborhood_improvements=1
2026-09-06T12:37:36.979849Z  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=465 row_words=57 horizon=9481
2026-09-06T12:37:39.784267Z  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=2104 ordinary_horizon=37751 paired_horizon=27172 use_paired=true
2026-09-06T12:37:39.832837Z  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=3410 maximum_identical_destinations=1
2026-09-06T12:37:39.832870Z  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=27172 selected_horizon=27172 endpoint_lower_bound=26784 lower_bound_gap=388 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:37:39.854568Z  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=723 row_words=167 horizon=27172
2026-09-06T12:37:47.097914Z  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
2026-09-06T12:37:47.097966Z  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=7991 selected_horizon=7991 endpoint_lower_bound=4704 lower_bound_gap=3287 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:37:47.162652Z  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=1058 row_words=294 horizon=7991
2026-09-06T12:37:47.191264Z  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=10816 success=true
2026-09-06T12:37:47.886857Z  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=6 success=true
2026-09-06T12:37:47.886918Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}: allocated package support memory linked_end=317036 profile_bytes=112 exchange_table_bytes=1736 host_code_bytes=2416 generated_code_bytes=1292 code_address=319456 standard_ranges=[(409600, 524288)]
2026-09-06T12:37:47.998700Z  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=111 success=true
2026-09-06T12:37:48.008228Z  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
2026-09-06T12:37:48.069360Z  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
2026-09-06T12:37:48.074237Z  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=10222 maximum_identical_destinations=1
2026-09-06T12:37:48.074253Z  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=9481 selected_horizon=9481 endpoint_lower_bound=8832 lower_bound_gap=649 selected_kind="reused" neighborhood_improvements=0
2026-09-06T12:37:48.079432Z  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=465 row_words=57 horizon=9481
2026-09-06T12:37:51.119639Z  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=2104 ordinary_horizon=37751 paired_horizon=27172 use_paired=true
2026-09-06T12:37:51.161130Z  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=3410 maximum_identical_destinations=1
2026-09-06T12:37:51.161169Z  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=27172 selected_horizon=27172 endpoint_lower_bound=26784 lower_bound_gap=388 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:37:51.177248Z  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=723 row_words=167 horizon=27172
2026-09-06T12:37:59.577413Z  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
2026-09-06T12:37:59.577487Z  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=7991 selected_horizon=7991 endpoint_lower_bound=4704 lower_bound_gap=3287 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:37:59.647261Z  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=1058 row_words=294 horizon=7991
2026-09-06T12:37:59.675582Z  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=11676 success=true
2026-09-06T12:38:01.771132Z  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
2026-09-06T12:38:01.991520Z  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
2026-09-06T12:38:01.998343Z  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=10222 maximum_identical_destinations=1
2026-09-06T12:38:01.998367Z  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=9481 selected_horizon=9481 endpoint_lower_bound=8832 lower_bound_gap=649 selected_kind="reused" neighborhood_improvements=0
2026-09-06T12:38:02.007123Z  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=465 row_words=57 horizon=9481
2026-09-06T12:38:06.144954Z  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=2104 ordinary_horizon=37751 paired_horizon=27135 use_paired=true
2026-09-06T12:38:06.195885Z  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=3410 maximum_identical_destinations=1
2026-09-06T12:38:06.195932Z  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=27135 selected_horizon=27135 endpoint_lower_bound=26784 lower_bound_gap=351 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:38:06.218957Z  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=721 row_words=169 horizon=27135
2026-09-06T12:38:14.070942Z  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
2026-09-06T12:38:14.070974Z  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=7991 selected_horizon=7991 endpoint_lower_bound=4704 lower_bound_gap=3287 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T12:38:14.157299Z  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=1058 row_words=294 horizon=7991
2026-09-06T12:38:14.198870Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: evaluated exchange placement finalist offset=24576 baseline_score=173497614336 score=132737826816 baseline_cycles=51692 candidate_cycles=51655 row_bytes=1736 row_capacity=16320 accepted=true
2026-09-06T12:38:14.210551Z  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=14534 success=true
2026-09-06T12:38:14.676365Z  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=12 success=true
2026-09-06T12:38:14.687269Z  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=10 success=true
2026-09-06T12:38:14.816081Z  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=124 success=true
2026-09-06T12:38:14.880574Z  INFO writing application package tiles=1472
2026-09-06T12:38:14.921749Z  INFO application package written
2026-09-06T12:38:14.922370Z  INFO reading application package
2026-09-06T12:38:15.024616Z  INFO application package read tiles=1472 compiler=0.1.0
2026-09-06T12:38:15.024922Z  INFO waiting for hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/alternatives-v1/device.lock
2026-09-06T12:38:20.628949Z  INFO acquired hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/alternatives-v1/device.lock
2026-09-06T12:38:20.629022Z  INFO opening IPU device path="/dev/ipu0"
2026-09-06T12:38:20.629092Z  INFO IPU device attached path=/dev/ipu0
2026-09-06T12:38:20.629099Z  INFO initializing IPU device
2026-09-06T12:38:20.637626Z  INFO IPU device initialized
2026-09-06T12:38:20.637667Z  INFO replaying device configuration register_writes=2003
2026-09-06T12:38:20.646610Z  INFO loading application tile_count=1472 final_mark=23
2026-09-06T12:38:20.921363Z  INFO application loaded and initial synchronization completed tile_count=1472
2026-09-06T12:38:24.035394Z  INFO starting host exchange session startup_mark=23
2026-09-06T12:38:24.035427Z  INFO attaching host exchange pages pages=2
2026-09-06T12:38:24.035839Z  INFO host exchange session started
2026-09-06T12:38:24.035915Z  INFO invoking streaming host exchange call call="initialize" command=0 phases=14
2026-09-06T12:38:24.041968Z  INFO invoking streaming host exchange call call="run" command=0 phases=59
profile=artifacts/layout-sweep/alternatives-v1/up-result-2x1/execution.ipuprofile tiles=1472 samples=22216
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=194196 minimumTileCycles=181740 deviceMicroseconds=129.464 effectiveGemmTflops=111.677 peakTflops=282.624 efficiencyPercent=39.51 maximumAbsoluteError=0.011719
package=artifacts/layout-sweep/alternatives-v1/up-result-2x1/model.ipuexe tiles=1472 hardwareTest=PASS