2026-09-06T11:39:28.527937Z 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: Streamed, local_weight_staging: Direct } 2026-09-06T11:39:28.993353Z 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 } 2026-09-06T11:39:29.533955Z INFO retained operator-plan finalist finalist=0 values=7 operations=4 estimated_cycles=311599 estimated_exchange_cycles=125160 exchange_row_bytes=27244 peak_standard_bytes=141932 peak_interleaved_bytes=88064 peak_total_bytes=229996 maximum_standard_allocation_bytes=114688 active_tile_counts={1440, 1472} padding_group_counts={} conversion_sources=[Some(OperationId(2))] 2026-09-06T11:39:29.539235Z 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=1299 success=true 2026-09-06T11:39:33.180128Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="select_finalist"}: selected analytical operator plan estimated_cycles=278147 estimated_exchange_cycles=82488 2026-09-06T11:39:33.266217Z 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 2026-09-06T11:39:33.267970Z 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=3728 success=true 2026-09-06T11:39:33.267987Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}: lowered graph for package construction logical_shards=26264 exchange_phases=6 2026-09-06T11:39:33.268182Z 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 2026-09-06T11:39:33.268849Z 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 2026-09-06T11:39:33.269104Z 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 2026-09-06T11:39:33.270750Z 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 2026-09-06T11:39:33.384680Z 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 2026-09-06T11:39:33.491802Z 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=5380 maximum_identical_destinations=1 2026-09-06T11:39:33.491827Z 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=3416 selected_horizon=3416 endpoint_lower_bound=3312 lower_bound_gap=104 selected_kind="full-duplex" neighborhood_improvements=0 2026-09-06T11:39:33.495251Z 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=1159 row_words=30 horizon=3416 2026-09-06T11:39:33.573457Z 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=4842 maximum_identical_destinations=1 2026-09-06T11:39:33.573477Z 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=2377 selected_horizon=2377 endpoint_lower_bound=2256 lower_bound_gap=121 selected_kind="full-duplex" neighborhood_improvements=0 2026-09-06T11:39:33.576648Z 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=973 row_words=27 horizon=2377 2026-09-06T11:39:33.660483Z 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=4842 maximum_identical_destinations=1 2026-09-06T11:39:33.660508Z 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=3455 selected_horizon=3455 endpoint_lower_bound=3360 lower_bound_gap=95 selected_kind="full-duplex" neighborhood_improvements=0 2026-09-06T11:39:33.663617Z 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=1091 row_words=39 horizon=3455 2026-09-06T11:39:41.482462Z 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=4 candidates=4028 ordinary_horizon=51847 paired_horizon=41194 use_paired=true 2026-09-06T11:39:41.568994Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges_provisional"}: prepared large physical exchange phase phase=4 transfers=5562 maximum_identical_destinations=1 2026-09-06T11:39:41.569015Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges_provisional"}: optimized physical exchange schedule phase=4 initial_horizon=41194 selected_horizon=41194 endpoint_lower_bound=23544 lower_bound_gap=17650 selected_kind="full-duplex" neighborhood_improvements=0 2026-09-06T11:39:41.613989Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges_provisional"}: finished large physical exchange phase phase=4 tile=1182 row_words=301 horizon=41194 2026-09-06T11:39:47.734402Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges_provisional"}: prepared large physical exchange phase phase=5 transfers=63720 maximum_identical_destinations=1 2026-09-06T11:39:47.734437Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges_provisional"}: optimized physical exchange schedule phase=5 initial_horizon=7991 selected_horizon=7991 endpoint_lower_bound=4704 lower_bound_gap=3287 selected_kind="full-duplex" neighborhood_improvements=0 2026-09-06T11:39:47.812293Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges_provisional"}: finished large physical exchange phase phase=5 tile=1058 row_words=294 horizon=7991 2026-09-06T11:39:47.848956Z 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=14464 success=true 2026-09-06T11:39:48.510660Z 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 2026-09-06T11:39:48.510714Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}: allocated package support memory linked_end=317272 profile_bytes=148 exchange_table_bytes=2448 host_code_bytes=2420 generated_code_bytes=1736 code_address=319696 standard_ranges=[(409600, 524288)] 2026-09-06T11:39:48.619452Z 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=108 success=true 2026-09-06T11:39:48.627339Z 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 2026-09-06T11:39:48.679989Z 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 2026-09-06T11:39:48.683139Z 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=5380 maximum_identical_destinations=1 2026-09-06T11:39:48.683159Z 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=3416 selected_horizon=3416 endpoint_lower_bound=3312 lower_bound_gap=104 selected_kind="reused" neighborhood_improvements=0 2026-09-06T11:39:48.689097Z 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=1159 row_words=30 horizon=3416 2026-09-06T11:39:48.719818Z 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 2026-09-06T11:39:48.721803Z 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=4842 maximum_identical_destinations=1 2026-09-06T11:39:48.721816Z 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=2377 selected_horizon=2377 endpoint_lower_bound=2256 lower_bound_gap=121 selected_kind="reused" neighborhood_improvements=0 2026-09-06T11:39:48.724968Z 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=973 row_words=27 horizon=2377 2026-09-06T11:39:48.759322Z 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=3 2026-09-06T11:39:48.761564Z 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=4842 maximum_identical_destinations=1 2026-09-06T11:39:48.761581Z 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=3455 selected_horizon=3455 endpoint_lower_bound=3360 lower_bound_gap=95 selected_kind="reused" neighborhood_improvements=0 2026-09-06T11:39:48.765171Z 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=1091 row_words=39 horizon=3455 2026-09-06T11:39:54.145598Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: compared ordinary and paired exchange schedules phase=4 candidates=4028 ordinary_horizon=51847 paired_horizon=41194 use_paired=true 2026-09-06T11:39:54.201525Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: prepared large physical exchange phase phase=4 transfers=5562 maximum_identical_destinations=1 2026-09-06T11:39:54.201549Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: optimized physical exchange schedule phase=4 initial_horizon=41194 selected_horizon=41194 endpoint_lower_bound=23544 lower_bound_gap=17650 selected_kind="full-duplex" neighborhood_improvements=0 2026-09-06T11:39:54.226978Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: finished large physical exchange phase phase=4 tile=1182 row_words=301 horizon=41194 2026-09-06T11:39:58.444343Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: prepared large physical exchange phase phase=5 transfers=63720 maximum_identical_destinations=1 2026-09-06T11:39:58.444372Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: optimized physical exchange schedule phase=5 initial_horizon=7991 selected_horizon=7991 endpoint_lower_bound=4704 lower_bound_gap=3287 selected_kind="full-duplex" neighborhood_improvements=0 2026-09-06T11:39:58.481882Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_exchanges"}: finished large physical exchange phase phase=5 tile=1058 row_words=294 horizon=7991 2026-09-06T11:39:58.496923Z 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=9877 success=true 2026-09-06T11:39:59.672050Z 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 2026-09-06T11:39:59.693152Z 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 2026-09-06T11:39:59.694519Z 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=5380 maximum_identical_destinations=1 2026-09-06T11:39:59.694527Z 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=3416 selected_horizon=3416 endpoint_lower_bound=3312 lower_bound_gap=104 selected_kind="reused" neighborhood_improvements=0 2026-09-06T11:39:59.696512Z 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=1159 row_words=30 horizon=3416 2026-09-06T11:39:59.715592Z 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=2 2026-09-06T11:39:59.716837Z 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=4842 maximum_identical_destinations=1 2026-09-06T11:39:59.716845Z 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=2377 selected_horizon=2377 endpoint_lower_bound=2256 lower_bound_gap=121 selected_kind="reused" neighborhood_improvements=0 2026-09-06T11:39:59.718816Z 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=973 row_words=27 horizon=2377 2026-09-06T11:39:59.738695Z 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=3 2026-09-06T11:39:59.739965Z 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=4842 maximum_identical_destinations=1 2026-09-06T11:39:59.739975Z 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=3455 selected_horizon=3455 endpoint_lower_bound=3360 lower_bound_gap=95 selected_kind="reused" neighborhood_improvements=0 2026-09-06T11:39:59.741947Z 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=1091 row_words=39 horizon=3455 2026-09-06T11:40:04.810060Z 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=4 candidates=4028 ordinary_horizon=41592 paired_horizon=32939 use_paired=true 2026-09-06T11:40:04.859064Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: prepared large physical exchange phase phase=4 transfers=5562 maximum_identical_destinations=1 2026-09-06T11:40:04.859079Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: optimized physical exchange schedule phase=4 initial_horizon=32939 selected_horizon=32939 endpoint_lower_bound=23544 lower_bound_gap=9395 selected_kind="full-duplex" neighborhood_improvements=0 2026-09-06T11:40:04.885090Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: finished large physical exchange phase phase=4 tile=1182 row_words=303 horizon=32939 2026-09-06T11:40:08.994472Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: prepared large physical exchange phase phase=5 transfers=63720 maximum_identical_destinations=1 2026-09-06T11:40:08.994498Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: optimized physical exchange schedule phase=5 initial_horizon=7991 selected_horizon=7991 endpoint_lower_bound=4704 lower_bound_gap=3287 selected_kind="full-duplex" neighborhood_improvements=0 2026-09-06T11:40:09.032485Z INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: finished large physical exchange phase phase=5 tile=1058 row_words=294 horizon=7991 2026-09-06T11:40:09.053709Z 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=445300015104 score=170111729664 baseline_cycles=65481 candidate_cycles=57226 row_bytes=2440 row_capacity=16320 accepted=true 2026-09-06T11:40:09.063001Z 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=10566 success=true 2026-09-06T11:40:09.251562Z 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 2026-09-06T11:40:09.260342Z 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 2026-09-06T11:40:09.313085Z 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=49 success=true 2026-09-06T11:40:09.357741Z INFO writing application package tiles=1472 2026-09-06T11:40:09.415069Z INFO application package written 2026-09-06T11:40:09.417175Z INFO reading application package 2026-09-06T11:40:09.488267Z INFO application package read tiles=1472 compiler=0.1.0 2026-09-06T11:40:09.489672Z INFO waiting for hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/device.lock 2026-09-06T11:40:09.489681Z INFO acquired hardware ownership path=/srv/home/gc-sdk/ipu-stack/artifacts/layout-sweep/device.lock 2026-09-06T11:40:09.489684Z INFO opening IPU device path="/dev/ipu0" 2026-09-06T11:40:09.489704Z INFO IPU device attached path=/dev/ipu0 2026-09-06T11:40:09.489706Z INFO initializing IPU device 2026-09-06T11:40:09.497628Z INFO IPU device initialized 2026-09-06T11:40:09.497631Z INFO replaying device configuration register_writes=2003 2026-09-06T11:40:09.504476Z INFO loading application tile_count=1472 final_mark=23 2026-09-06T11:40:09.708923Z INFO application loaded and initial synchronization completed tile_count=1472 2026-09-06T11:40:11.472170Z INFO starting host exchange session startup_mark=23 2026-09-06T11:40:11.472226Z INFO attaching host exchange pages pages=2 2026-09-06T11:40:11.472725Z INFO host exchange session started 2026-09-06T11:40:11.472771Z INFO invoking streaming host exchange call call="initialize" command=0 phases=14 2026-09-06T11:40:11.477775Z INFO invoking streaming host exchange call call="run" command=0 phases=59 profile=artifacts/layout-sweep/up-21/execution.ipuprofile tiles=1472 samples=31676 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=206544 minimumTileCycles=190200 deviceMicroseconds=137.696 effectiveGemmTflops=105.000 peakTflops=282.624 efficiencyPercent=37.15 maximumAbsoluteError=0.011719 package=artifacts/layout-sweep/up-21/model.ipuexe tiles=1472 hardwareTest=PASS