2026-09-06T11:41:28.818522Z 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 } 2026-09-06T11:41:29.287358Z INFO applied GEMM plan constraint source_operation=2 matching_plans=2 constraint=GemmPlanConstraint { source_operation: 2, orientation: Normal, row_partitions: 9, column_partitions: 9, inner_partitions: 18, result_row_partitions: 18, result_column_partitions: 1, output_column_block: 128, weight_memory_class: Ipu21Interleaved, reduction_staging: Complete, local_weight_staging: Direct } 2026-09-06T11:41:29.648008Z INFO retained operator-plan finalist finalist=0 values=7 operations=4 estimated_cycles=312887 estimated_exchange_cycles=107960 exchange_row_bytes=23636 peak_standard_bytes=138324 peak_interleaved_bytes=122880 peak_total_bytes=260180 maximum_standard_allocation_bytes=114688 active_tile_counts={1458, 1472} padding_group_counts={} conversion_sources=[Some(OperationId(2))] 2026-09-06T11:41:29.652448Z 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=1127 success=true 2026-09-06T11:41:34.851705Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="select_finalist"}: selected analytical operator plan estimated_cycles=313847 estimated_exchange_cycles=109032 2026-09-06T11:41:34.882156Z 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 2026-09-06T11:41:34.883801Z 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=5231 success=true 2026-09-06T11:41:34.883818Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}: lowered graph for package construction logical_shards=26075 exchange_phases=4 2026-09-06T11:41:34.884018Z 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 2026-09-06T11:41:34.884544Z 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 2026-09-06T11:41:34.884691Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="compile_kernels"}: compiling kernel source=/srv/home/gc-sdk/ipu-stack/crates/ipu-tests/../../device/gemm_f16_amp.S name="gemm_f16_interleaved_k240_c128_r80_r82" target=ipu21 2026-09-06T11:41:34.936763Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="compile_kernels"}: kernel artifact created object=/srv/home/.cache/ipu-stack/kernels/1bbd7696bfb29ed83c3cde3895993881e39fc996109d0eaafbc7fc8f77d35226/kernel.o metadata=/srv/home/.cache/ipu-stack/kernels/1bbd7696bfb29ed83c3cde3895993881e39fc996109d0eaafbc7fc8f77d35226/kernel.json 2026-09-06T11:41:34.937418Z 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=52 success=true 2026-09-06T11:41:34.940122Z 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 2026-09-06T11:41:35.053795Z 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=113 success=true 2026-09-06T11:41:35.419817Z 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 2026-09-06T11:41:35.419862Z 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 2026-09-06T11:41:35.435585Z 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 2026-09-06T11:41:38.300095Z 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=28 ordinary_horizon=33886 paired_horizon=33846 use_paired=true 2026-09-06T11:41:38.335412Z 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=7104 maximum_identical_destinations=1 2026-09-06T11:41:38.335431Z 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=33846 selected_horizon=33846 endpoint_lower_bound=25200 lower_bound_gap=8646 selected_kind="full-duplex" neighborhood_improvements=0 2026-09-06T11:41:38.353432Z 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=304 row_words=156 horizon=33846 2026-09-06T11:42:27.581978Z 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=206136 maximum_identical_destinations=1 2026-09-06T11:42:27.582037Z 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=14393 selected_horizon=14393 endpoint_lower_bound=6912 lower_bound_gap=7481 selected_kind="full-duplex" neighborhood_improvements=0 2026-09-06T11:42:27.848073Z 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=247 row_words=789 horizon=14393 2026-09-06T11:42:27.939346Z 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=52885 success=true 2026-09-06T11:42:28.572947Z 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 2026-09-06T11:42:28.572980Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}: allocated package support memory linked_end=319176 profile_bytes=116 exchange_table_bytes=3940 host_code_bytes=2916 generated_code_bytes=1472 code_address=322096 standard_ranges=[(409600, 524288)] 2026-09-06T11:42:28.677568Z 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=104 success=true 2026-09-06T11:42:28.686093Z 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 2026-09-06T11:42:28.756038Z 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 2026-09-06T11:42:28.759755Z 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 2026-09-06T11:42:28.759764Z 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 2026-09-06T11:42:28.765618Z 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 2026-09-06T11:42:31.559627Z 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=28 ordinary_horizon=33886 paired_horizon=33846 use_paired=true 2026-09-06T11:42:31.606473Z 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=7104 maximum_identical_destinations=1 2026-09-06T11:42:31.606496Z 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=33846 selected_horizon=33846 endpoint_lower_bound=25200 lower_bound_gap=8646 selected_kind="full-duplex" neighborhood_improvements=0 2026-09-06T11:42:31.631752Z 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=304 row_words=156 horizon=33846 2026-09-06T11:43:24.141629Z 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=206136 maximum_identical_destinations=1 2026-09-06T11:43:24.141662Z 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=14393 selected_horizon=14393 endpoint_lower_bound=6912 lower_bound_gap=7481 selected_kind="full-duplex" neighborhood_improvements=0 2026-09-06T11:43:24.297616Z 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=247 row_words=789 horizon=14393 2026-09-06T11:43:24.344037Z 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=55666 success=true 2026-09-06T11:43:25.387884Z 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 2026-09-06T11:43:25.479461Z 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 2026-09-06T11:43:25.485652Z 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 2026-09-06T11:43:25.485665Z 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 2026-09-06T11:43:25.495893Z 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 2026-09-06T11:43:28.508976Z 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=28 ordinary_horizon=33886 paired_horizon=33846 use_paired=true 2026-09-06T11:43:28.555922Z 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=7104 maximum_identical_destinations=1 2026-09-06T11:43:28.555942Z 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=33846 selected_horizon=33846 endpoint_lower_bound=25200 lower_bound_gap=8646 selected_kind="full-duplex" neighborhood_improvements=0 2026-09-06T11:43:28.581298Z 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=304 row_words=156 horizon=33846 2026-09-06T11:44:33.177682Z 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=206136 maximum_identical_destinations=1 2026-09-06T11:44:33.177728Z 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=14393 selected_horizon=14393 endpoint_lower_bound=6912 lower_bound_gap=7481 selected_kind="full-duplex" neighborhood_improvements=0 2026-09-06T11:44:33.439581Z 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=247 row_words=789 horizon=14393 2026-09-06T11:44:33.524743Z 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=394151854080 score=382591303680 baseline_cycles=59066 candidate_cycles=59066 row_bytes=3932 row_capacity=16320 accepted=false 2026-09-06T11:44:33.551366Z 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=69207 success=true 2026-09-06T11:44:33.744334Z 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 2026-09-06T11:44:33.753235Z 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=8 success=true 2026-09-06T11:44:33.819075Z 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=62 success=true 2026-09-06T11:44:33.868608Z INFO writing application package tiles=1472 2026-09-06T11:44:33.909812Z INFO application package written 2026-09-06T11:44:33.909835Z INFO reading application package 2026-09-06T11:44:33.981777Z INFO application package read tiles=1472 compiler=0.1.0 2026-09-06T11:44:33.984161Z INFO waiting for hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/device.lock 2026-09-06T11:44:33.984172Z INFO acquired hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/device.lock 2026-09-06T11:44:33.984178Z INFO opening IPU device path="/dev/ipu0" 2026-09-06T11:44:33.984210Z INFO IPU device attached path=/dev/ipu0 2026-09-06T11:44:33.984214Z INFO initializing IPU device 2026-09-06T11:44:33.992148Z INFO IPU device initialized 2026-09-06T11:44:33.992153Z INFO replaying device configuration register_writes=2003 2026-09-06T11:44:33.998761Z INFO loading application tile_count=1472 final_mark=23 2026-09-06T11:44:34.283648Z INFO application loaded and initial synchronization completed tile_count=1472 2026-09-06T11:44:37.045940Z INFO starting host exchange session startup_mark=23 2026-09-06T11:44:37.045972Z INFO attaching host exchange pages pages=2 2026-09-06T11:44:37.046494Z INFO host exchange session started 2026-09-06T11:44:37.046555Z INFO invoking streaming host exchange call call="initialize" command=0 phases=30 2026-09-06T11:44:37.054981Z INFO invoking streaming host exchange call call="run" command=0 phases=59 profile=artifacts/layout-sweep/down-07/execution.ipuprofile tiles=1472 samples=21286 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=154736640 weightBytes=19869696 cycles=214902 minimumTileCycles=187848 deviceMicroseconds=143.268 effectiveGemmTflops=100.917 peakTflops=282.624 efficiencyPercent=35.71 maximumAbsoluteError=0.011719 package=artifacts/layout-sweep/down-07/model.ipuexe tiles=1472 hardwareTest=PASS