2026-09-06T17:57:00.797374Z  INFO retained operator-plan finalist finalist=0 values=11 operations=7 estimated_cycles=468886 estimated_exchange_cycles=177000 exchange_row_bytes=36288 peak_standard_bytes=76992 peak_interleaved_bytes=114688 peak_total_bytes=167360 maximum_standard_allocation_bytes=16384 active_tile_counts={12, 32, 64} padding_group_counts={} conversion_sources=[]
2026-09-06T17:57:00.797480Z  INFO retained operator-plan finalist finalist=1 values=11 operations=7 estimated_cycles=493594 estimated_exchange_cycles=173640 exchange_row_bytes=35532 peak_standard_bytes=76236 peak_interleaved_bytes=131072 peak_total_bytes=182988 maximum_standard_allocation_bytes=16384 active_tile_counts={12, 64} padding_group_counts={} conversion_sources=[]
2026-09-06T17:57:00.797551Z  INFO retained operator-plan finalist finalist=2 values=13 operations=9 estimated_cycles=522043 estimated_exchange_cycles=223760 exchange_row_bytes=46416 peak_standard_bytes=107856 peak_interleaved_bytes=92160 peak_total_bytes=185680 maximum_standard_allocation_bytes=61440 active_tile_counts={12, 32, 64} padding_group_counts={} conversion_sources=[Some(OperationId(1)), Some(OperationId(2))]
2026-09-06T17:57:00.797600Z  INFO retained operator-plan finalist finalist=3 values=13 operations=9 estimated_cycles=524135 estimated_exchange_cycles=217520 exchange_row_bytes=45012 peak_standard_bytes=106452 peak_interleaved_bytes=94208 peak_total_bytes=200660 maximum_standard_allocation_bytes=61440 active_tile_counts={12, 32, 64} padding_group_counts={} conversion_sources=[Some(OperationId(1)), Some(OperationId(2))]
2026-09-06T17:57:00.803734Z  INFO ipu_codegen.package.phase{phase="lower_mid"}: package build phase finished phase="lower_mid" elapsed_ms=382 success=true
2026-09-06T17:57:01.273843Z  INFO screened tile mappings by exchange resource load candidates=15 baseline_cycles=62960 candidate_cycles=62960 baseline_pressure=60716 candidate_pressure=60716
2026-09-06T17:57:01.277781Z  INFO modelled expanded operator plan finalist=1 modelled_cycles=398023 estimated_cycles=423463 estimated_exchange_cycles=96800
2026-09-06T17:57:01.305895Z  INFO screened tile mappings by exchange resource load candidates=19 baseline_cycles=70528 candidate_cycles=68480 baseline_pressure=66615 candidate_pressure=64567
2026-09-06T17:57:01.310094Z  INFO modelled expanded operator plan finalist=0 modelled_cycles=399596 estimated_cycles=459108 estimated_exchange_cycles=137592
2026-09-06T17:57:01.389264Z  INFO screened tile mappings by exchange resource load candidates=23 baseline_cycles=84280 candidate_cycles=83440 baseline_pressure=74540 candidate_pressure=73665
2026-09-06T17:57:01.389264Z  INFO screened tile mappings by exchange resource load candidates=23 baseline_cycles=78676 candidate_cycles=78676 baseline_pressure=70058 candidate_pressure=70058
2026-09-06T17:57:01.394965Z  INFO modelled expanded operator plan finalist=2 modelled_cycles=476567 estimated_cycles=571567 estimated_exchange_cycles=189240
2026-09-06T17:57:01.397460Z  INFO modelled expanded operator plan finalist=3 modelled_cycles=480586 estimated_cycles=579070 estimated_exchange_cycles=187960
2026-09-06T17:57:01.451240Z  INFO ipu_codegen.package.phase{phase="select_finalist"}: prepared large physical exchange phase phase=0 transfers=1005 maximum_identical_destinations=1
2026-09-06T17:57:01.451280Z  INFO ipu_codegen.package.phase{phase="select_finalist"}: optimized physical exchange schedule phase=0 initial_horizon=948 selected_horizon=948 endpoint_lower_bound=576 lower_bound_gap=372 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T17:57:01.452276Z  INFO ipu_codegen.package.phase{phase="select_finalist"}: finished large physical exchange phase phase=0 tile=54 row_words=178 horizon=948
2026-09-06T17:57:01.776684Z  INFO ipu_codegen.package.phase{phase="select_finalist"}: prepared large physical exchange phase phase=1 transfers=3299 maximum_identical_destinations=1
2026-09-06T17:57:01.776717Z  INFO ipu_codegen.package.phase{phase="select_finalist"}: optimized physical exchange schedule phase=1 initial_horizon=2586 selected_horizon=2586 endpoint_lower_bound=512 lower_bound_gap=2074 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T17:57:01.779414Z  INFO ipu_codegen.package.phase{phase="select_finalist"}: finished large physical exchange phase phase=1 tile=52 row_words=230 horizon=2586
2026-09-06T17:57:01.901338Z  INFO ipu_codegen.package.phase{phase="select_finalist"}: scheduled operator-plan finalist finalist=1 mapped=false analytical_cycles=423463 analytical_exchange_cycles=96800 scheduled_exchange_cycles=74658 refined_cycles=401321
2026-09-06T17:57:01.910867Z  INFO ipu_codegen.package.phase{phase="select_finalist"}: selected physically scheduled operator-plan finalist selected=1 mapped=false
2026-09-06T17:57:01.910889Z  INFO ipu_codegen.package.phase{phase="select_finalist"}: package build phase finished phase="select_finalist" elapsed_ms=1107 success=true
2026-09-06T17:57:01.910901Z  INFO lowered graph for package construction logical_shards=5364 exchange_phases=14
2026-09-06T17:57:01.911154Z  INFO ipu_codegen.package.phase{phase="compile_runtime"}: package build phase finished phase="compile_runtime" elapsed_ms=0 success=true
2026-09-06T17:57:01.911771Z  INFO ipu_codegen.package.phase{phase="plan_kernels"}: package build phase finished phase="plan_kernels" elapsed_ms=0 success=true
2026-09-06T17:57:01.911950Z  INFO 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_packed64_k64_c64_r16_r16" target=ipu21
2026-09-06T17:57:01.971857Z  INFO ipu_codegen.package.phase{phase="compile_kernels"}: kernel artifact created object=/srv/home/.cache/ipu-stack/kernels/e3718d2b1795221abedcfe8129afd043470800357f8a044375cf0bcbdc04fcb1/kernel.o metadata=/srv/home/.cache/ipu-stack/kernels/e3718d2b1795221abedcfe8129afd043470800357f8a044375cf0bcbdc04fcb1/kernel.json
2026-09-06T17:57:01.972299Z  INFO 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_c80_r11_r12" target=ipu21
2026-09-06T17:57:02.025478Z  INFO ipu_codegen.package.phase{phase="compile_kernels"}: kernel artifact created object=/srv/home/.cache/ipu-stack/kernels/362c0298b3045f0c6b599e3c8e1deeff515db83696dbfa5c667d37625decddba/kernel.o metadata=/srv/home/.cache/ipu-stack/kernels/362c0298b3045f0c6b599e3c8e1deeff515db83696dbfa5c667d37625decddba/kernel.json
2026-09-06T17:57:02.025846Z  INFO 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_k80_c64_r11_r12" target=ipu21
2026-09-06T17:57:02.080381Z  INFO ipu_codegen.package.phase{phase="compile_kernels"}: kernel artifact created object=/srv/home/.cache/ipu-stack/kernels/40262b6676bf6e032f8f23d968b013b68e1eb9f362554ad905590cee55dd12ee/kernel.o metadata=/srv/home/.cache/ipu-stack/kernels/40262b6676bf6e032f8f23d968b013b68e1eb9f362554ad905590cee55dd12ee/kernel.json
2026-09-06T17:57:02.080732Z  INFO ipu_codegen.package.phase{phase="compile_kernels"}: compiling kernel source=/srv/home/gc-sdk/ipu-stack/crates/ipu-tests/../../device/unpack_amp_f16.cpp name="unpack_amp_f16_codelet_o3_r11_p16_c72_p128_b64_16" target=ipu21
2026-09-06T17:57:02.401516Z  INFO ipu_codegen.package.phase{phase="compile_kernels"}: kernel artifact created object=/srv/home/.cache/ipu-stack/kernels/71a4bb1540c68312cd3a1f7ffd695d20439ddcf931695fb5ccf5614f1463e354/kernel.o metadata=/srv/home/.cache/ipu-stack/kernels/71a4bb1540c68312cd3a1f7ffd695d20439ddcf931695fb5ccf5614f1463e354/kernel.json
2026-09-06T17:57:02.401860Z  INFO ipu_codegen.package.phase{phase="compile_kernels"}: compiling kernel source=/srv/home/gc-sdk/ipu-stack/crates/ipu-tests/../../device/worker_call.S name="unpack_amp_f16_wrapper_o3_r11_p16_c72_p128_b64_16" target=ipu21
2026-09-06T17:57:02.452769Z  INFO ipu_codegen.package.phase{phase="compile_kernels"}: kernel artifact created object=/srv/home/.cache/ipu-stack/kernels/fafd13a01e0107261e1a850e95777176442c970a5c02cfe616490fd7316ad9a4/kernel.o metadata=/srv/home/.cache/ipu-stack/kernels/fafd13a01e0107261e1a850e95777176442c970a5c02cfe616490fd7316ad9a4/kernel.json
2026-09-06T17:57:02.453122Z  INFO ipu_codegen.package.phase{phase="compile_kernels"}: compiling kernel source=/srv/home/gc-sdk/ipu-stack/crates/ipu-tests/../../device/unpack_amp_f16.cpp name="unpack_amp_f16_codelet_o3_r12_p16_c72_p128_b64_16" target=ipu21
2026-09-06T17:57:02.760494Z  INFO ipu_codegen.package.phase{phase="compile_kernels"}: kernel artifact created object=/srv/home/.cache/ipu-stack/kernels/acf7aeded123b8ac93d12763bf03cc4e1026d13cac459caa4d1fca7bac23e778/kernel.o metadata=/srv/home/.cache/ipu-stack/kernels/acf7aeded123b8ac93d12763bf03cc4e1026d13cac459caa4d1fca7bac23e778/kernel.json
2026-09-06T17:57:02.761175Z  INFO ipu_codegen.package.phase{phase="compile_kernels"}: compiling kernel source=/srv/home/gc-sdk/ipu-stack/crates/ipu-tests/../../device/worker_call.S name="unpack_amp_f16_wrapper_o3_r12_p16_c72_p128_b64_16" target=ipu21
2026-09-06T17:57:02.815507Z  INFO ipu_codegen.package.phase{phase="compile_kernels"}: kernel artifact created object=/srv/home/.cache/ipu-stack/kernels/063a9ea19f4a49586d0bde05ef53177dd558ab3b42cdc125d1ed49ed4150e2c5/kernel.o metadata=/srv/home/.cache/ipu-stack/kernels/063a9ea19f4a49586d0bde05ef53177dd558ab3b42cdc125d1ed49ed4150e2c5/kernel.json
2026-09-06T17:57:02.816338Z  INFO ipu_codegen.package.phase{phase="compile_kernels"}: package build phase finished phase="compile_kernels" elapsed_ms=904 success=true
2026-09-06T17:57:02.816835Z  INFO ipu_codegen.package.phase{phase="link_runtime"}: package build phase finished phase="link_runtime" elapsed_ms=0 success=true
2026-09-06T17:57:02.844822Z  INFO ipu_codegen.package.phase{phase="size_tile_code"}: package build phase finished phase="size_tile_code" elapsed_ms=4 success=true
2026-09-06T17:57:02.844852Z  INFO allocated package support memory linked_end=320588 profile_bytes=0 exchange_table_bytes=4004 host_code_bytes=1788 generated_code_bytes=2420 code_address=322384 standard_ranges=[(393216, 524288)]
2026-09-06T17:57:02.852128Z  INFO ipu_codegen.package.phase{phase="place_storage"}: package build phase finished phase="place_storage" elapsed_ms=7 success=true
2026-09-06T17:57:02.881524Z  INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=0
2026-09-06T17:57:02.882038Z  INFO ipu_codegen.package.phase{phase="lower_exchanges"}: prepared large physical exchange phase phase=0 transfers=1005 maximum_identical_destinations=1
2026-09-06T17:57:02.882045Z  INFO ipu_codegen.package.phase{phase="lower_exchanges"}: optimized physical exchange schedule phase=0 initial_horizon=948 selected_horizon=948 endpoint_lower_bound=576 lower_bound_gap=372 selected_kind="reused" neighborhood_improvements=0
2026-09-06T17:57:02.883076Z  INFO ipu_codegen.package.phase{phase="lower_exchanges"}: finished large physical exchange phase phase=0 tile=54 row_words=178 horizon=948
2026-09-06T17:57:03.108851Z  INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=1
2026-09-06T17:57:03.110422Z  INFO ipu_codegen.package.phase{phase="lower_exchanges"}: prepared large physical exchange phase phase=1 transfers=3299 maximum_identical_destinations=1
2026-09-06T17:57:03.110440Z  INFO ipu_codegen.package.phase{phase="lower_exchanges"}: optimized physical exchange schedule phase=1 initial_horizon=2586 selected_horizon=2586 endpoint_lower_bound=512 lower_bound_gap=2074 selected_kind="reused" neighborhood_improvements=0
2026-09-06T17:57:03.113114Z  INFO ipu_codegen.package.phase{phase="lower_exchanges"}: finished large physical exchange phase phase=1 tile=52 row_words=230 horizon=2586
2026-09-06T17:57:03.119267Z  INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=2
2026-09-06T17:57:03.125373Z  INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=3
2026-09-06T17:57:03.130645Z  INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=4
2026-09-06T17:57:03.136497Z  INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=5
2026-09-06T17:57:03.141799Z  INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=6
2026-09-06T17:57:03.147038Z  INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=7
2026-09-06T17:57:03.152249Z  INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=8
2026-09-06T17:57:03.157528Z  INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=9
2026-09-06T17:57:03.163097Z  INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=10
2026-09-06T17:57:03.168793Z  INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=11
2026-09-06T17:57:03.174093Z  INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=12
2026-09-06T17:57:03.179458Z  INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=13
2026-09-06T17:57:03.180145Z  INFO ipu_codegen.package.phase{phase="lower_exchanges"}: package build phase finished phase="lower_exchanges" elapsed_ms=327 success=true
2026-09-06T17:57:03.268723Z  INFO ipu_codegen.package.phase{phase="optimize_exchange_placement"}: package build phase finished phase="optimize_exchange_placement" elapsed_ms=88 success=true
2026-09-06T17:57:03.269612Z  INFO costed final placed program final_cycles=401321 final_exchange=74658
2026-09-06T17:57:03.288462Z  INFO ipu_codegen.package.phase{phase="prepare_tile_code"}: package build phase finished phase="prepare_tile_code" elapsed_ms=6 success=true
2026-09-06T17:57:03.295086Z  INFO ipu_codegen.package.phase{phase="emit_tile_code"}: package build phase finished phase="emit_tile_code" elapsed_ms=6 success=true
2026-09-06T17:57:03.441650Z  INFO ipu_codegen.package.phase{phase="build_tile_images"}: package build phase finished phase="build_tile_images" elapsed_ms=143 success=true
2026-09-06T17:57:03.457976Z  INFO writing application package tiles=1472
2026-09-06T17:57:03.473187Z  INFO application package written
2026-09-06T17:57:03.473907Z  INFO reading application package
2026-09-06T17:57:03.504641Z  INFO application package read tiles=1472 compiler=0.1.0
2026-09-06T17:57:03.504954Z  INFO waiting for hardware ownership path=artifacts/layout-sweep/device.lock
2026-09-06T17:57:03.504965Z  INFO acquired hardware ownership path=artifacts/layout-sweep/device.lock
2026-09-06T17:57:03.504971Z  INFO opening IPU device path="/dev/ipu0"
2026-09-06T17:57:03.505011Z  INFO IPU device attached path=/dev/ipu0
2026-09-06T17:57:03.505014Z  INFO initializing IPU device
2026-09-06T17:57:03.512997Z  INFO IPU device initialized
2026-09-06T17:57:03.513008Z  INFO replaying device configuration register_writes=2003
2026-09-06T17:57:03.517375Z  INFO loading application tile_count=1472 final_mark=23
2026-09-06T17:57:03.720567Z  INFO application loaded and initial synchronization completed tile_count=1472
2026-09-06T17:57:03.905598Z  INFO starting host exchange session startup_mark=23
2026-09-06T17:57:03.905632Z  INFO attaching host exchange pages pages=2
2026-09-06T17:57:03.906448Z  INFO host exchange session started
2026-09-06T17:57:03.906470Z  INFO invoking streaming host exchange call call="initialize" command=0 phases=48
2026-09-06T17:57:03.914885Z  INFO invoking streaming host exchange call call="run" command=0 phases=3
checkpoint=0 operation=0 tensors=1 samples=256 maximumAbsoluteError=0.000244
checkpoint=1 operation=1 tensors=1 samples=256 maximumAbsoluteError=0.000244
checkpoint=2 operation=2 tensors=1 samples=256 maximumAbsoluteError=0.000244
checkpoint=3 operation=6 tensors=1 samples=256 maximumAbsoluteError=0.000011
diagnosticCheckpoints=4 sampleLimit=256 numericalTest=PASS
package=artifacts/layout-sweep/attention-packed-balanced-diagnostic/model.ipuexe tiles=1472 hardwareTest=PASS