2026-09-06T21:13:18.793271Z  INFO retained operator-plan finalist finalist=0 values=16 operations=1 estimated_cycles=22038 estimated_exchange_cycles=9240 exchange_row_bytes=300 peak_standard_bytes=33068 peak_interleaved_bytes=46720 peak_total_bytes=79660 maximum_standard_allocation_bytes=16384 active_tile_counts={64} padding_group_counts={} conversion_sources=[]
2026-09-06T21:13:18.801996Z  INFO ipu_codegen.package.build{tile_count=64 operations=1}:ipu_codegen.package.phase{phase="lower_mid"}: package build phase finished phase="lower_mid" elapsed_ms=567 success=true
2026-09-06T21:13:18.810916Z  INFO ipu_codegen.package.build{tile_count=64 operations=1}:ipu_codegen.package.phase{phase="select_finalist"}: screened tile mappings by exchange resource load candidates=10 baseline_cycles=1224 candidate_cycles=1224 baseline_pressure=813 candidate_pressure=813
2026-09-06T21:13:18.811233Z  INFO ipu_codegen.package.build{tile_count=64 operations=1}:ipu_codegen.package.phase{phase="select_finalist"}: modelled expanded operator plan finalist=0 modelled_cycles=21018 estimated_cycles=31674 estimated_exchange_cycles=17280
2026-09-06T21:13:18.829395Z  INFO ipu_codegen.package.build{tile_count=64 operations=1}:ipu_codegen.package.phase{phase="select_finalist"}: scheduled operator-plan finalist finalist=0 mapped=false analytical_cycles=31674 analytical_exchange_cycles=17280 scheduled_exchange_cycles=7467 refined_cycles=21861
2026-09-06T21:13:18.829446Z  INFO ipu_codegen.package.build{tile_count=64 operations=1}:ipu_codegen.package.phase{phase="select_finalist"}: selected physically scheduled operator-plan finalist selected=0 mapped=false
2026-09-06T21:13:18.829452Z  INFO ipu_codegen.package.build{tile_count=64 operations=1}:ipu_codegen.package.phase{phase="select_finalist"}: package build phase finished phase="select_finalist" elapsed_ms=27 success=true
2026-09-06T21:13:18.829461Z  INFO ipu_codegen.package.build{tile_count=64 operations=1}: lowered graph for package construction logical_shards=992 exchange_phases=3
2026-09-06T21:13:18.829624Z  INFO ipu_codegen.package.build{tile_count=64 operations=1}:ipu_codegen.package.phase{phase="compile_runtime"}: package build phase finished phase="compile_runtime" elapsed_ms=0 success=true
2026-09-06T21:13:18.829674Z  INFO ipu_codegen.package.build{tile_count=64 operations=1}:ipu_codegen.package.phase{phase="plan_kernels"}: package build phase finished phase="plan_kernels" elapsed_ms=0 success=true
2026-09-06T21:13:18.829810Z  INFO ipu_codegen.package.build{tile_count=64 operations=1}: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_k16_c16_r18_r18" target=ipu21
2026-09-06T21:13:18.884731Z  INFO ipu_codegen.package.build{tile_count=64 operations=1}:ipu_codegen.package.phase{phase="compile_kernels"}: kernel artifact created object=/srv/home/.cache/ipu-stack/kernels/e91258bc6d0f3ac91f8efa09fc0ced4204adb6497b40df1b80aa87c05a62d91a/kernel.o metadata=/srv/home/.cache/ipu-stack/kernels/e91258bc6d0f3ac91f8efa09fc0ced4204adb6497b40df1b80aa87c05a62d91a/kernel.json
2026-09-06T21:13:18.884944Z  INFO ipu_codegen.package.build{tile_count=64 operations=1}: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_k64_c32_r1_r2" target=ipu21
2026-09-06T21:13:18.926857Z  INFO ipu_codegen.package.build{tile_count=64 operations=1}:ipu_codegen.package.phase{phase="compile_kernels"}: kernel artifact created object=/srv/home/.cache/ipu-stack/kernels/d5395ed65338c45b88819041f145a8bf4e03ed366a42e0dca9976ace7cde0378/kernel.o metadata=/srv/home/.cache/ipu-stack/kernels/d5395ed65338c45b88819041f145a8bf4e03ed366a42e0dca9976ace7cde0378/kernel.json
2026-09-06T21:13:18.927190Z  INFO ipu_codegen.package.build{tile_count=64 operations=1}:ipu_codegen.package.phase{phase="compile_kernels"}: package build phase finished phase="compile_kernels" elapsed_ms=97 success=true
2026-09-06T21:13:18.927573Z  INFO ipu_codegen.package.build{tile_count=64 operations=1}:ipu_codegen.package.phase{phase="link_runtime"}: package build phase finished phase="link_runtime" elapsed_ms=0 success=true
2026-09-06T21:13:18.957332Z  INFO ipu_codegen.package.build{tile_count=64 operations=1}:ipu_codegen.package.phase{phase="size_tile_code"}: package build phase finished phase="size_tile_code" elapsed_ms=1 success=true
2026-09-06T21:13:18.957369Z  INFO ipu_codegen.package.build{tile_count=64 operations=1}: allocated package support memory linked_end=316588 profile_bytes=16 exchange_table_bytes=352 host_code_bytes=648 generated_code_bytes=560 code_address=317304 standard_ranges=[(409600, 524288)]
2026-09-06T21:13:18.959178Z  INFO ipu_codegen.package.build{tile_count=64 operations=1}:ipu_codegen.package.phase{phase="place_storage"}: package build phase finished phase="place_storage" elapsed_ms=1 success=true
2026-09-06T21:13:18.964472Z  INFO ipu_codegen.package.build{tile_count=64 operations=1}:ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=0
2026-09-06T21:13:18.966339Z  INFO ipu_codegen.package.build{tile_count=64 operations=1}:ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=1
2026-09-06T21:13:18.967555Z  INFO ipu_codegen.package.build{tile_count=64 operations=1}:ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=2
2026-09-06T21:13:18.967763Z  INFO ipu_codegen.package.build{tile_count=64 operations=1}:ipu_codegen.package.phase{phase="lower_exchanges"}: package build phase finished phase="lower_exchanges" elapsed_ms=8 success=true
2026-09-06T21:13:18.968183Z  INFO ipu_codegen.package.build{tile_count=64 operations=1}:ipu_codegen.package.phase{phase="optimize_exchange_placement"}: package build phase finished phase="optimize_exchange_placement" elapsed_ms=0 success=true
2026-09-06T21:13:18.968243Z  INFO ipu_codegen.package.build{tile_count=64 operations=1}: costed final placed program final_cycles=21861 final_exchange=7467
2026-09-06T21:13:18.983979Z  INFO ipu_codegen.package.build{tile_count=64 operations=1}:ipu_codegen.package.phase{phase="prepare_tile_code"}: package build phase finished phase="prepare_tile_code" elapsed_ms=2 success=true
2026-09-06T21:13:18.986858Z  INFO ipu_codegen.package.build{tile_count=64 operations=1}:ipu_codegen.package.phase{phase="emit_tile_code"}: package build phase finished phase="emit_tile_code" elapsed_ms=2 success=true
2026-09-06T21:13:19.068131Z  INFO ipu_codegen.package.build{tile_count=64 operations=1}:ipu_codegen.package.phase{phase="build_tile_images"}: package build phase finished phase="build_tile_images" elapsed_ms=80 success=true
2026-09-06T21:13:19.073551Z  INFO writing application package tiles=1472
2026-09-06T21:13:19.081321Z  INFO application package written
2026-09-06T21:13:19.081808Z  INFO reading application package
2026-09-06T21:13:19.095857Z  INFO application package read tiles=1472 compiler=0.1.0
2026-09-06T21:13:19.096328Z  INFO waiting for hardware ownership path=artifacts/layout-sweep/device.lock
2026-09-06T21:13:19.096339Z  INFO acquired hardware ownership path=artifacts/layout-sweep/device.lock
2026-09-06T21:13:19.096344Z  INFO opening IPU device path="/dev/ipu0"
2026-09-06T21:13:19.096372Z  INFO IPU device attached path=/dev/ipu0
2026-09-06T21:13:19.096377Z  INFO initializing IPU device
2026-09-06T21:13:19.104187Z  INFO IPU device initialized
2026-09-06T21:13:19.104276Z  INFO replaying device configuration register_writes=2003
2026-09-06T21:13:19.108188Z  INFO loading application tile_count=1472 final_mark=23
2026-09-06T21:13:19.299390Z  INFO application loaded and initial synchronization completed tile_count=1472
2026-09-06T21:13:19.334444Z  INFO starting host exchange session startup_mark=23
2026-09-06T21:13:19.334469Z  INFO attaching host exchange pages pages=2
2026-09-06T21:13:19.335226Z  INFO host exchange session started
2026-09-06T21:13:19.335234Z  INFO invoking streaming host exchange call call="initialize" command=0 phases=12
2026-09-06T21:13:19.337071Z  INFO invoking streaming host exchange call call="run" command=0 phases=9
profile=artifacts/repeat-sweep-final/mlp-small-n3/execution.ipuprofile tiles=1472 samples=1472
workload=siglip-mlp-f16-b1-t17-d64-h128-n3 benchmark=siglip-mlp-f16 batch=1 tokens=17 rows=17 dimension=64 hiddenDimension=128 blocks=3 biases=false activeTiles=64 executionTiles=64 inputBytes=8704 weightBytes=835584 cycles=16656 minimumTileCycles=16092 deviceMicroseconds=11.104 effectiveGemmTflops=0.151 peakTflops=12.288 efficiencyPercent=1.22 maximumAbsoluteError=0.000008
package=artifacts/repeat-sweep-final/mlp-small-n3/model.ipuexe tiles=1472 hardwareTest=PASS