2026-09-06T11:37:19.685428Z  INFO applied GEMM plan constraint source_operation=0 matching_plans=1 constraint=GemmPlanConstraint { source_operation: 0, orientation: Normal, row_partitions: 2, column_partitions: 135, inner_partitions: 5, result_row_partitions: 5, result_column_partitions: 1, output_column_block: 32, weight_memory_class: Ipu21Interleaved, reduction_staging: Complete, local_weight_staging: Direct }
2026-09-06T11:37:20.145272Z  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: Ipu21Interleaved, reduction_staging: Complete, local_weight_staging: Direct }
2026-09-06T11:37:20.689408Z  INFO retained operator-plan finalist finalist=0 values=7 operations=4 estimated_cycles=310833 estimated_exchange_cycles=119800 exchange_row_bytes=26300 peak_standard_bytes=206524 peak_interleaved_bytes=75776 peak_total_bytes=282300 maximum_standard_allocation_bytes=180224 active_tile_counts={1350, 1440} padding_group_counts={} conversion_sources=[Some(OperationId(2))]
2026-09-06T11:37:20.696344Z  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=1303 success=true
2026-09-06T11:37:23.559982Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="select_finalist"}: selected analytical operator plan estimated_cycles=250218 estimated_exchange_cycles=66760
2026-09-06T11:37:23.645869Z  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
2026-09-06T11:37:23.647610Z  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=2951 success=true
2026-09-06T11:37:23.647627Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}: lowered graph for package construction logical_shards=25326 exchange_phases=4
2026-09-06T11:37:23.647810Z  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
2026-09-06T11:37:23.648368Z  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
2026-09-06T11:37:23.649397Z  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=1 success=true
2026-09-06T11:37:23.651278Z  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
2026-09-06T11:37:23.763768Z  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=112 success=true
2026-09-06T11:37:24.031524Z  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=12105 maximum_identical_destinations=1
2026-09-06T11:37:24.031553Z  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=6541 selected_horizon=5157 endpoint_lower_bound=4800 lower_bound_gap=357 selected_kind="matching-waves" neighborhood_improvements=0
2026-09-06T11:37:24.042604Z  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=599 row_words=66 horizon=5157
2026-09-06T11:37:28.556027Z  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=2995 ordinary_horizon=44606 paired_horizon=41646 use_paired=true
2026-09-06T11:37:28.613108Z  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=4217 maximum_identical_destinations=1
2026-09-06T11:37:28.613141Z  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=41646 selected_horizon=41646 endpoint_lower_bound=25488 lower_bound_gap=16158 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T11:37:28.642973Z  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=781 row_words=214 horizon=41646
2026-09-06T11:37:34.809617Z  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
2026-09-06T11:37:34.809666Z  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
2026-09-06T11:37:34.871341Z  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
2026-09-06T11:37:34.895827Z  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=11132 success=true
2026-09-06T11:37:35.742599Z  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
2026-09-06T11:37:35.742641Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}: allocated package support memory linked_end=319128 profile_bytes=132 exchange_table_bytes=2048 host_code_bytes=3476 generated_code_bytes=1744 code_address=322608 standard_ranges=[(409600, 524288)]
2026-09-06T11:37:35.845090Z  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=102 success=true
2026-09-06T11:37:35.850319Z  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
2026-09-06T11:37:35.926666Z  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
2026-09-06T11:37:35.931508Z  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=12105 maximum_identical_destinations=1
2026-09-06T11:37:35.931521Z  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=5157 selected_horizon=5157 endpoint_lower_bound=4800 lower_bound_gap=357 selected_kind="reused" neighborhood_improvements=0
2026-09-06T11:37:35.941569Z  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=599 row_words=66 horizon=5157
2026-09-06T11:37:41.124143Z  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=2995 ordinary_horizon=44606 paired_horizon=41646 use_paired=true
2026-09-06T11:37:41.184557Z  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=4217 maximum_identical_destinations=1
2026-09-06T11:37:41.184582Z  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=41646 selected_horizon=41646 endpoint_lower_bound=25488 lower_bound_gap=16158 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T11:37:41.214634Z  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=781 row_words=214 horizon=41646
2026-09-06T11:37:47.862900Z  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
2026-09-06T11:37:47.862946Z  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
2026-09-06T11:37:47.923854Z  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
2026-09-06T11:37:47.944896Z  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=12099 success=true
2026-09-06T11:37:49.203287Z  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
2026-09-06T11:37:49.280334Z  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
2026-09-06T11:37:49.285315Z  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=12105 maximum_identical_destinations=1
2026-09-06T11:37:49.285328Z  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=5157 selected_horizon=5157 endpoint_lower_bound=4800 lower_bound_gap=357 selected_kind="reused" neighborhood_improvements=0
2026-09-06T11:37:49.295636Z  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=599 row_words=66 horizon=5157
2026-09-06T11:37:52.817859Z  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=2995 ordinary_horizon=40644 paired_horizon=31300 use_paired=true
2026-09-06T11:37:52.855156Z  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=4217 maximum_identical_destinations=1
2026-09-06T11:37:52.855177Z  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=31300 selected_horizon=31300 endpoint_lower_bound=25488 lower_bound_gap=5812 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T11:37:52.874395Z  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=1024 row_words=215 horizon=31300
2026-09-06T11:37:57.214496Z  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
2026-09-06T11:37:57.214531Z  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
2026-09-06T11:37:57.262181Z  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
2026-09-06T11:37:57.284300Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: evaluated exchange placement finalist offset=4096 baseline_score=448685899776 score=173497614336 baseline_cycles=58848 candidate_cycles=48502 row_bytes=2032 row_capacity=16320 accepted=true
2026-09-06T11:37:57.293664Z  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=9348 success=true
2026-09-06T11:37:57.565384Z  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
2026-09-06T11:37:57.576869Z  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
2026-09-06T11:37:57.725509Z  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=144 success=true
2026-09-06T11:37:57.815925Z  INFO writing application package tiles=1472
2026-09-06T11:37:57.886913Z  INFO application package written
2026-09-06T11:37:57.888815Z  INFO reading application package
2026-09-06T11:37:57.972944Z  INFO application package read tiles=1472 compiler=0.1.0
2026-09-06T11:37:57.975327Z  INFO waiting for hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/device.lock
2026-09-06T11:37:59.188296Z  INFO acquired hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/device.lock
2026-09-06T11:37:59.188348Z  INFO opening IPU device path="/dev/ipu0"
2026-09-06T11:37:59.188421Z  INFO IPU device attached path=/dev/ipu0
2026-09-06T11:37:59.188428Z  INFO initializing IPU device
2026-09-06T11:37:59.196301Z  INFO IPU device initialized
2026-09-06T11:37:59.196343Z  INFO replaying device configuration register_writes=2003
2026-09-06T11:37:59.207453Z  INFO loading application tile_count=1472 final_mark=23
2026-09-06T11:37:59.535281Z  INFO application loaded and initial synchronization completed tile_count=1472
2026-09-06T11:38:03.246481Z  INFO starting host exchange session startup_mark=23
2026-09-06T11:38:03.246508Z  INFO attaching host exchange pages pages=2
2026-09-06T11:38:03.247218Z  INFO host exchange session started
2026-09-06T11:38:03.247251Z  INFO invoking streaming host exchange call call="initialize" command=0 phases=14
2026-09-06T11:38:03.252866Z  INFO invoking streaming host exchange call call="run" command=0 phases=93
profile=artifacts/layout-sweep/up-11/execution.ipuprofile tiles=1472 samples=25154
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=236520000 weightBytes=20282880 cycles=207828 minimumTileCycles=184752 deviceMicroseconds=138.552 effectiveGemmTflops=104.352 peakTflops=282.624 efficiencyPercent=36.92 maximumAbsoluteError=0.011719
package=artifacts/layout-sweep/up-11/model.ipuexe tiles=1472 hardwareTest=PASS