2026-09-06T12:26:14.496699Z INFO retained operator-plan finalist finalist=0 values=7 operations=4 estimated_cycles=237698 estimated_exchange_cycles=106840 exchange_row_bytes=23384 peak_standard_bytes=224088 peak_interleaved_bytes=53248 peak_total_bytes=272216 maximum_standard_allocation_bytes=180224 active_tile_counts={1458, 1470} padding_group_counts={} conversion_sources=[Some(OperationId(2))] 2026-09-06T12:26:14.845516Z 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=12900 success=true 2026-09-06T12:26:17.266552Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="select_finalist"}: selected analytical operator plan estimated_cycles=205680 estimated_exchange_cycles=81992 2026-09-06T12:26:17.358277Z 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=36 2026-09-06T12:26:17.360801Z 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=2515 success=true 2026-09-06T12:26:17.360829Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}: lowered graph for package construction logical_shards=26664 exchange_phases=4 2026-09-06T12:26:17.361063Z 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 2026-09-06T12:26:17.361848Z 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 2026-09-06T12:26:17.362228Z 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 2026-09-06T12:26:17.364392Z 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 2026-09-06T12:26:17.501067Z 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=136 success=true 2026-09-06T12:26:17.959243Z 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 2026-09-06T12:26:17.959290Z 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=6557 selected_horizon=5174 endpoint_lower_bound=4800 lower_bound_gap=374 selected_kind="matching-waves" neighborhood_improvements=0 2026-09-06T12:26:17.970252Z 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=619 row_words=66 horizon=5174 2026-09-06T12:26:20.225236Z 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=3062 ordinary_horizon=28839 paired_horizon=31187 use_paired=false 2026-09-06T12:26:20.272102Z 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=4200 maximum_identical_destinations=1 2026-09-06T12:26:20.272134Z 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=29705 selected_horizon=28839 endpoint_lower_bound=24640 lower_bound_gap=4199 selected_kind="critical-neighborhood" neighborhood_improvements=1 2026-09-06T12:26:20.292666Z 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=1102 row_words=118 horizon=28839 2026-09-06T12:27:02.990350Z 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=155880 maximum_identical_destinations=1 2026-09-06T12:27:02.990406Z 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=15700 selected_horizon=15700 endpoint_lower_bound=8640 lower_bound_gap=7060 selected_kind="full-duplex" neighborhood_improvements=0 2026-09-06T12:27:03.180436Z 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=447 row_words=633 horizon=15700 2026-09-06T12:27:03.241339Z 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=45740 success=true 2026-09-06T12:27:04.223066Z 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=4 success=true 2026-09-06T12:27:04.223121Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}: allocated package support memory linked_end=318892 profile_bytes=100 exchange_table_bytes=3140 host_code_bytes=3360 generated_code_bytes=1640 code_address=322256 standard_ranges=[(409600, 524288)] 2026-09-06T12:27:04.334260Z 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 2026-09-06T12:27:04.339887Z 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 2026-09-06T12:27:04.424075Z 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 2026-09-06T12:27:04.429635Z 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 2026-09-06T12:27:04.429655Z 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=5174 selected_horizon=5174 endpoint_lower_bound=4800 lower_bound_gap=374 selected_kind="reused" neighborhood_improvements=0 2026-09-06T12:27:04.440023Z 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=619 row_words=66 horizon=5174 2026-09-06T12:27:04.675804Z 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=2 2026-09-06T12:27:04.686033Z 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=4200 maximum_identical_destinations=1 2026-09-06T12:27:04.686057Z 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=28839 selected_horizon=28839 endpoint_lower_bound=24640 lower_bound_gap=4199 selected_kind="reused" neighborhood_improvements=0 2026-09-06T12:27:04.699626Z 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=1102 row_words=118 horizon=28839 2026-09-06T12:27:48.052504Z 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=155880 maximum_identical_destinations=1 2026-09-06T12:27:48.052540Z 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=15700 selected_horizon=15700 endpoint_lower_bound=8640 lower_bound_gap=7060 selected_kind="full-duplex" neighborhood_improvements=0 2026-09-06T12:27:48.163329Z 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=447 row_words=633 horizon=15700 2026-09-06T12:27:48.196502Z 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=43862 success=true 2026-09-06T12:27:49.286800Z 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 2026-09-06T12:27:49.367822Z 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 2026-09-06T12:27:49.373134Z 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 2026-09-06T12:27:49.373158Z 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=5174 selected_horizon=5174 endpoint_lower_bound=4800 lower_bound_gap=374 selected_kind="reused" neighborhood_improvements=0 2026-09-06T12:27:49.384677Z 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=619 row_words=66 horizon=5174 2026-09-06T12:27:51.473161Z 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=3062 ordinary_horizon=28735 paired_horizon=28683 use_paired=true 2026-09-06T12:27:51.516106Z 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=4200 maximum_identical_destinations=1 2026-09-06T12:27:51.516126Z 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=29293 selected_horizon=28683 endpoint_lower_bound=24640 lower_bound_gap=4043 selected_kind="critical-neighborhood" neighborhood_improvements=2 2026-09-06T12:27:51.540040Z 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=905 row_words=165 horizon=28683 2026-09-06T12:28:24.934244Z 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=155880 maximum_identical_destinations=1 2026-09-06T12:28:24.934273Z 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=15700 selected_horizon=15700 endpoint_lower_bound=8640 lower_bound_gap=7060 selected_kind="full-duplex" neighborhood_improvements=0 2026-09-06T12:28:25.051440Z 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=447 row_words=633 horizon=15700 2026-09-06T12:28:25.094851Z 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=127958384640 score=105171517440 baseline_cycles=53767 candidate_cycles=53611 row_bytes=3288 row_capacity=16320 accepted=true 2026-09-06T12:28:25.108035Z 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=36911 success=true 2026-09-06T12:28:25.392533Z 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=6 success=true 2026-09-06T12:28:25.404716Z 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=12 success=true 2026-09-06T12:28:25.517486Z 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=108 success=true 2026-09-06T12:28:25.602823Z INFO writing application package tiles=1472 2026-09-06T12:28:25.636362Z INFO application package written 2026-09-06T12:28:25.636580Z INFO reading application package 2026-09-06T12:28:25.738904Z INFO application package read tiles=1472 compiler=0.1.0 2026-09-06T12:28:25.739276Z INFO waiting for hardware ownership path=artifacts/layout-sweep/device.lock 2026-09-06T12:28:25.739284Z INFO acquired hardware ownership path=artifacts/layout-sweep/device.lock 2026-09-06T12:28:25.739288Z INFO opening IPU device path="/dev/ipu0" 2026-09-06T12:28:25.739316Z INFO IPU device attached path=/dev/ipu0 2026-09-06T12:28:25.739321Z INFO initializing IPU device 2026-09-06T12:28:25.749819Z INFO IPU device initialized 2026-09-06T12:28:25.749866Z INFO replaying device configuration register_writes=2003 2026-09-06T12:28:25.761106Z INFO loading application tile_count=1472 final_mark=23 2026-09-06T12:28:26.015584Z INFO application loaded and initial synchronization completed tile_count=1472 2026-09-06T12:28:29.381980Z INFO starting host exchange session startup_mark=23 2026-09-06T12:28:29.382011Z INFO attaching host exchange pages pages=2 2026-09-06T12:28:29.382683Z INFO host exchange session started 2026-09-06T12:28:29.382722Z INFO invoking streaming host exchange call call="initialize" command=0 phases=10 2026-09-06T12:28:29.388338Z INFO invoking streaming host exchange call call="run" command=0 phases=93 profile=artifacts/layout-sweep/kernel-upgrade/automatic/execution.ipuprofile tiles=1472 samples=24048 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=1458 executionTiles=1472 inputBytes=257544000 weightBytes=20282880 cycles=181884 minimumTileCycles=160320 deviceMicroseconds=121.256 effectiveGemmTflops=119.236 peakTflops=282.624 efficiencyPercent=42.19 maximumAbsoluteError=0.011719 package=artifacts/layout-sweep/kernel-upgrade/automatic/model.ipuexe tiles=1472 hardwareTest=PASS