2026-09-07T16:27:25.650014Z  INFO retained operator-plan finalist finalist=0 values=17 operations=1 estimated_cycles=73326 estimated_exchange_cycles=29120 exchange_row_bytes=2228 peak_standard_bytes=28212 peak_interleaved_bytes=38912 peak_total_bytes=65076 maximum_standard_allocation_bytes=16384 active_tile_counts={64} padding_group_counts={} conversion_sources=[]
2026-09-07T16:27:25.656480Z  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=378 success=true
2026-09-07T16:27:25.706272Z  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=23 baseline_cycles=7856 candidate_cycles=7856 baseline_pressure=6436 candidate_pressure=6436
2026-09-07T16:27:25.706606Z  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=51238 estimated_cycles=120054 estimated_exchange_cycles=82672
2026-09-07T16:27:26.077609Z  INFO ipu_codegen.package.build{tile_count=64 operations=1}:ipu_codegen.package.phase{phase="select_finalist"}: prepared large physical exchange phase phase=2 transfers=2076 maximum_identical_destinations=1
2026-09-07T16:27:26.077674Z  INFO ipu_codegen.package.build{tile_count=64 operations=1}:ipu_codegen.package.phase{phase="select_finalist"}: optimized physical exchange schedule phase=2 initial_horizon=2760 selected_horizon=2760 endpoint_lower_bound=1392 lower_bound_gap=1368 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-07T16:27:26.080024Z  INFO ipu_codegen.package.build{tile_count=64 operations=1}:ipu_codegen.package.phase{phase="select_finalist"}: finished large physical exchange phase phase=2 tile=13 row_words=411 horizon=2760
2026-09-07T16:27:26.081716Z  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=120054 analytical_exchange_cycles=82672 scheduled_exchange_cycles=18314 refined_cycles=55696
2026-09-07T16:27:26.082795Z  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
2026-09-07T16:27:26.082848Z  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=426 success=true
2026-09-07T16:27:26.082865Z  INFO ipu_codegen.package.build{tile_count=64 operations=1}: lowered graph for package construction logical_shards=1700 exchange_phases=5
2026-09-07T16:27:26.083293Z  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
2026-09-07T16:27:26.083617Z  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
2026-09-07T16:27:26.083963Z  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_f8_k96_c32_r26_r26" target=ipu21
2026-09-07T16:27:26.138533Z  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/3e0d84ac99c771e433672356765671a24d7c5a869df40d681b7f7e78f96fe777/kernel.o metadata=/srv/home/.cache/ipu-stack/kernels/3e0d84ac99c771e433672356765671a24d7c5a869df40d681b7f7e78f96fe777/kernel.json
2026-09-07T16:27:26.139354Z  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/cast_f8.cpp name="cast_f16_f8_codelet" target=ipu21
2026-09-07T16:27:26.491954Z  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/7ba6c2dc3e21c9511eb3481725f6fb3623ac9c84943934d359e2369cd0484dfe/kernel.o metadata=/srv/home/.cache/ipu-stack/kernels/7ba6c2dc3e21c9511eb3481725f6fb3623ac9c84943934d359e2369cd0484dfe/kernel.json
2026-09-07T16:27:26.492311Z  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/worker_call.S name="cast_f16_f8_wrapper" target=ipu21
2026-09-07T16:27:26.554038Z  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/91eb5f6493214dc20a2445d0a61f81344f4b81b218b12e44c597b42c782cb04b/kernel.o metadata=/srv/home/.cache/ipu-stack/kernels/91eb5f6493214dc20a2445d0a61f81344f4b81b218b12e44c597b42c782cb04b/kernel.json
2026-09-07T16:27:26.554417Z  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=470 success=true
2026-09-07T16:27:26.554812Z  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
2026-09-07T16:27:26.584960Z  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
2026-09-07T16:27:26.585003Z  INFO ipu_codegen.package.build{tile_count=64 operations=1}: allocated package support memory linked_end=318088 profile_bytes=24 exchange_table_bytes=2500 host_code_bytes=428 generated_code_bytes=920 code_address=318584 standard_ranges=[(409600, 524288)]
2026-09-07T16:27:26.587236Z  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=2 success=true
2026-09-07T16:27:26.590398Z  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
2026-09-07T16:27:26.591313Z  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=3
2026-09-07T16:27:26.611070Z  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=4
2026-09-07T16:27:26.620386Z  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
2026-09-07T16:27:26.826333Z  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
2026-09-07T16:27:26.828448Z  INFO ipu_codegen.package.build{tile_count=64 operations=1}:ipu_codegen.package.phase{phase="lower_exchanges"}: prepared large physical exchange phase phase=2 transfers=2076 maximum_identical_destinations=1
2026-09-07T16:27:26.828474Z  INFO ipu_codegen.package.build{tile_count=64 operations=1}:ipu_codegen.package.phase{phase="lower_exchanges"}: optimized physical exchange schedule phase=2 initial_horizon=2760 selected_horizon=2760 endpoint_lower_bound=1392 lower_bound_gap=1368 selected_kind="reused" neighborhood_improvements=0
2026-09-07T16:27:26.830541Z  INFO ipu_codegen.package.build{tile_count=64 operations=1}:ipu_codegen.package.phase{phase="lower_exchanges"}: finished large physical exchange phase phase=2 tile=13 row_words=411 horizon=2760
2026-09-07T16:27:26.831736Z  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=244 success=true
2026-09-07T16:27:26.858964Z  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=27 success=true
2026-09-07T16:27:26.859141Z  INFO ipu_codegen.package.build{tile_count=64 operations=1}: costed final placed program final_cycles=55696 final_exchange=18314
2026-09-07T16:27:26.879598Z  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=3 success=true
2026-09-07T16:27:26.886404Z  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=6 success=true
2026-09-07T16:27:27.041135Z  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=152 success=true
2026-09-07T16:27:27.051265Z  INFO writing application package tiles=1472
2026-09-07T16:27:27.067728Z  INFO application package written
2026-09-07T16:27:27.068777Z  INFO reading application package
2026-09-07T16:27:27.088484Z  INFO application package read tiles=1472 compiler=0.1.0
2026-09-07T16:27:27.089198Z  INFO waiting for hardware ownership path=artifacts/layout-sweep/device.lock
2026-09-07T16:27:27.089233Z  INFO acquired hardware ownership path=artifacts/layout-sweep/device.lock
2026-09-07T16:27:27.089243Z  INFO opening IPU device path="/dev/ipu0"
2026-09-07T16:27:27.089287Z  INFO IPU device attached path=/dev/ipu0
2026-09-07T16:27:27.089293Z  INFO initializing IPU device
2026-09-07T16:27:27.097259Z  INFO IPU device initialized
2026-09-07T16:27:27.097285Z  INFO replaying device configuration register_writes=2003
2026-09-07T16:27:27.101596Z  INFO loading application tile_count=1472 final_mark=23
2026-09-07T16:27:27.299398Z  INFO application loaded and initial synchronization completed tile_count=1472
2026-09-07T16:27:27.396907Z  INFO starting host exchange session startup_mark=23
2026-09-07T16:27:27.398818Z  INFO attaching host exchange pages pages=2
2026-09-07T16:27:27.399482Z  INFO host exchange session started
2026-09-07T16:27:27.399500Z  INFO invoking streaming host exchange call call="initialize" command=0 phases=4
2026-09-07T16:27:27.400031Z  INFO invoking streaming host exchange call call="run" command=0 phases=9
profile=artifacts/fp8-before-fanout/repeat-early/profile.ipuprof tiles=1472 samples=1472
referenceMaximumAbsoluteError=0.031250 numericalTest=PASS
package=artifacts/fp8-before-fanout/repeat-early/model.ipuexe tiles=1472 hardwareTest=PASS