2026-09-06T11:41:12.294330Z  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 }
2026-09-06T11:41:12.715927Z  INFO applied GEMM plan constraint source_operation=2 matching_plans=1 constraint=GemmPlanConstraint { source_operation: 2, orientation: Normal, row_partitions: 5, column_partitions: 24, inner_partitions: 12, result_row_partitions: 12, result_column_partitions: 1, output_column_block: 48, weight_memory_class: Ipu21Interleaved, reduction_staging: Complete, local_weight_staging: Direct }
2026-09-06T11:41:13.163255Z  INFO retained operator-plan finalist finalist=0 values=7 operations=4 estimated_cycles=314766 estimated_exchange_cycles=127160 exchange_row_bytes=27956 peak_standard_bytes=142644 peak_interleaved_bytes=95744 peak_total_bytes=238388 maximum_standard_allocation_bytes=114688 active_tile_counts={1440, 1472} padding_group_counts={} conversion_sources=[Some(OperationId(2))]
2026-09-06T11:41:13.168027Z  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=1160 success=true
2026-09-06T11:41:17.539475Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="select_finalist"}: selected analytical operator plan estimated_cycles=247303 estimated_exchange_cycles=69560
2026-09-06T11:41:17.611517Z  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=96
2026-09-06T11:41:17.613180Z  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=4445 success=true
2026-09-06T11:41:17.613216Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}: lowered graph for package construction logical_shards=26264 exchange_phases=4
2026-09-06T11:41:17.613411Z  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
2026-09-06T11:41:17.613943Z  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
2026-09-06T11:41:17.614810Z  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
2026-09-06T11:41:17.616747Z  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
2026-09-06T11:41:17.732419Z  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=115 success=true
2026-09-06T11:41:18.075793Z  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
2026-09-06T11:41:18.075827Z  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
2026-09-06T11:41:18.086319Z  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
2026-09-06T11:41:26.938874Z  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=4498 ordinary_horizon=52112 paired_horizon=39781 use_paired=true
2026-09-06T11:41:27.032912Z  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=6244 maximum_identical_destinations=1
2026-09-06T11:41:27.032938Z  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=39781 selected_horizon=39781 endpoint_lower_bound=27508 lower_bound_gap=12273 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T11:41:27.079266Z  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=78 row_words=285 horizon=39781
2026-09-06T11:41:30.237040Z  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=50976 maximum_identical_destinations=1
2026-09-06T11:41:30.237068Z  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=6265 selected_horizon=6265 endpoint_lower_bound=3696 lower_bound_gap=2569 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T11:41:30.266811Z  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=1132 row_words=232 horizon=6265
2026-09-06T11:41:30.278034Z  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=12545 success=true
2026-09-06T11:41:30.694691Z  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
2026-09-06T11:41:30.694739Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}: allocated package support memory linked_end=318224 profile_bytes=152 exchange_table_bytes=1984 host_code_bytes=2516 generated_code_bytes=1632 code_address=320744 standard_ranges=[(409600, 524288)]
2026-09-06T11:41:30.839192Z  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=144 success=true
2026-09-06T11:41:30.847236Z  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
2026-09-06T11:41:30.937422Z  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
2026-09-06T11:41:30.943417Z  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
2026-09-06T11:41:30.943429Z  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
2026-09-06T11:41:30.953463Z  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
2026-09-06T11:41:40.635990Z  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=4498 ordinary_horizon=52112 paired_horizon=39781 use_paired=true
2026-09-06T11:41:40.723947Z  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=6244 maximum_identical_destinations=1
2026-09-06T11:41:40.723970Z  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=39781 selected_horizon=39781 endpoint_lower_bound=27508 lower_bound_gap=12273 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T11:41:40.769977Z  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=78 row_words=285 horizon=39781
2026-09-06T11:41:45.062827Z  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=50976 maximum_identical_destinations=1
2026-09-06T11:41:45.062864Z  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=6265 selected_horizon=6265 endpoint_lower_bound=3696 lower_bound_gap=2569 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T11:41:45.111731Z  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=1132 row_words=232 horizon=6265
2026-09-06T11:41:45.128855Z  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=14289 success=true
2026-09-06T11:41:46.566614Z  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
2026-09-06T11:41:46.657884Z  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
2026-09-06T11:41:46.664221Z  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
2026-09-06T11:41:46.664234Z  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
2026-09-06T11:41:46.674604Z  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
2026-09-06T11:41:56.362125Z  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=4498 ordinary_horizon=43897 paired_horizon=31972 use_paired=true
2026-09-06T11:41:56.449438Z  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=6244 maximum_identical_destinations=1
2026-09-06T11:41:56.449460Z  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=31972 selected_horizon=31972 endpoint_lower_bound=27508 lower_bound_gap=4464 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T11:41:56.495178Z  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=78 row_words=284 horizon=31972
2026-09-06T11:42:00.897783Z  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=50976 maximum_identical_destinations=1
2026-09-06T11:42:00.897819Z  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=6265 selected_horizon=6265 endpoint_lower_bound=3696 lower_bound_gap=2569 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T11:42:00.945400Z  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=1132 row_words=232 horizon=6265
2026-09-06T11:42:00.971382Z  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=576808452096 score=168201977856 baseline_cycles=56873 candidate_cycles=49064 row_bytes=1984 row_capacity=16320 accepted=true
2026-09-06T11:42:00.982168Z  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=15853 success=true
2026-09-06T11:42:01.294883Z  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
2026-09-06T11:42:01.305725Z  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
2026-09-06T11:42:01.405403Z  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=95 success=true
2026-09-06T11:42:01.464275Z  INFO writing application package tiles=1472
2026-09-06T11:42:01.529154Z  INFO application package written
2026-09-06T11:42:01.531464Z  INFO reading application package
2026-09-06T11:42:01.631899Z  INFO application package read tiles=1472 compiler=0.1.0
2026-09-06T11:42:01.634005Z  INFO waiting for hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/device.lock
2026-09-06T11:42:01.634015Z  INFO acquired hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/device.lock
2026-09-06T11:42:01.634024Z  INFO opening IPU device path="/dev/ipu0"
2026-09-06T11:42:01.634057Z  INFO IPU device attached path=/dev/ipu0
2026-09-06T11:42:01.634059Z  INFO initializing IPU device
2026-09-06T11:42:01.642011Z  INFO IPU device initialized
2026-09-06T11:42:01.642016Z  INFO replaying device configuration register_writes=2003
2026-09-06T11:42:01.650535Z  INFO loading application tile_count=1472 final_mark=23
2026-09-06T11:42:01.932760Z  INFO application loaded and initial synchronization completed tile_count=1472
2026-09-06T11:42:04.527147Z  INFO starting host exchange session startup_mark=23
2026-09-06T11:42:04.527178Z  INFO attaching host exchange pages pages=2
2026-09-06T11:42:04.527653Z  INFO host exchange session started
2026-09-06T11:42:04.527692Z  INFO invoking streaming host exchange call call="initialize" command=0 phases=18
2026-09-06T11:42:04.534443Z  INFO invoking streaming host exchange call call="run" command=0 phases=59
profile=artifacts/layout-sweep/down-05/execution.ipuprofile tiles=1472 samples=25847
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=20090880 cycles=195984 minimumTileCycles=182466 deviceMicroseconds=130.656 effectiveGemmTflops=110.658 peakTflops=282.624 efficiencyPercent=39.15 maximumAbsoluteError=0.009766
package=artifacts/layout-sweep/down-05/model.ipuexe tiles=1472 hardwareTest=PASS