2026-09-06T16:39:27.354990Z  INFO retained operator-plan finalist finalist=0 values=11 operations=7 estimated_cycles=569331 estimated_exchange_cycles=173640 exchange_row_bytes=35532 peak_standard_bytes=96716 peak_interleaved_bytes=114688 peak_total_bytes=166604 maximum_standard_allocation_bytes=16384 active_tile_counts={12, 64} padding_group_counts={} conversion_sources=[]
2026-09-06T16:39:27.355124Z  INFO retained operator-plan finalist finalist=1 values=11 operations=7 estimated_cycles=579969 estimated_exchange_cycles=191640 exchange_row_bytes=38796 peak_standard_bytes=99980 peak_interleaved_bytes=44480 peak_total_bytes=132748 maximum_standard_allocation_bytes=16384 active_tile_counts={12, 30, 64} padding_group_counts={} conversion_sources=[]
2026-09-06T16:39:27.355147Z  INFO retained operator-plan finalist finalist=2 values=11 operations=7 estimated_cycles=582050 estimated_exchange_cycles=187440 exchange_row_bytes=38244 peak_standard_bytes=99428 peak_interleaved_bytes=46592 peak_total_bytes=132196 maximum_standard_allocation_bytes=16384 active_tile_counts={12, 32, 64} padding_group_counts={} conversion_sources=[]
2026-09-06T16:39:27.355235Z  INFO retained operator-plan finalist finalist=3 values=12 operations=8 estimated_cycles=585611 estimated_exchange_cycles=188320 exchange_row_bytes=38180 peak_standard_bytes=99364 peak_interleaved_bytes=73344 peak_total_bytes=139620 maximum_standard_allocation_bytes=16384 active_tile_counts={12, 30, 64} padding_group_counts={} conversion_sources=[Some(OperationId(2))]
2026-09-06T16:39:27.362187Z  INFO ipu_codegen.package.phase{phase="lower_mid"}: package build phase finished phase="lower_mid" elapsed_ms=452 success=true
2026-09-06T16:39:27.700335Z  INFO screened tile mappings by exchange resource load candidates=15 baseline_cycles=63344 candidate_cycles=63344 baseline_pressure=61298 candidate_pressure=61298
2026-09-06T16:39:27.703819Z  INFO modelled expanded operator plan finalist=0 modelled_cycles=445149 estimated_cycles=466885 estimated_exchange_cycles=94080
2026-09-06T16:39:27.867483Z  INFO screened tile mappings by exchange resource load candidates=19 baseline_cycles=68656 candidate_cycles=68656 baseline_pressure=64224 candidate_pressure=64224
2026-09-06T16:39:27.868194Z  INFO screened tile mappings by exchange resource load candidates=23 baseline_cycles=71376 candidate_cycles=71376 baseline_pressure=67290 candidate_pressure=67290
2026-09-06T16:39:27.871349Z  INFO modelled expanded operator plan finalist=2 modelled_cycles=506193 estimated_cycles=567449 estimated_exchange_cycles=140712
2026-09-06T16:39:27.871658Z  INFO modelled expanded operator plan finalist=1 modelled_cycles=470163 estimated_cycles=531227 estimated_exchange_cycles=145040
2026-09-06T16:39:27.899492Z  INFO screened tile mappings by exchange resource load candidates=23 baseline_cycles=70952 candidate_cycles=70952 baseline_pressure=66149 candidate_pressure=66149
2026-09-06T16:39:27.903182Z  INFO modelled expanded operator plan finalist=3 modelled_cycles=459022 estimated_cycles=519270 estimated_exchange_cycles=143200
2026-09-06T16:39:27.990615Z  INFO ipu_codegen.package.phase{phase="select_finalist"}: prepared large physical exchange phase phase=1 transfers=1038 maximum_identical_destinations=1
2026-09-06T16:39:27.990651Z  INFO ipu_codegen.package.phase{phase="select_finalist"}: optimized physical exchange schedule phase=1 initial_horizon=1121 selected_horizon=1121 endpoint_lower_bound=736 lower_bound_gap=385 selected_kind="full-duplex" neighborhood_improvements=0
2026-09-06T16:39:27.991594Z  INFO ipu_codegen.package.phase{phase="select_finalist"}: finished large physical exchange phase phase=1 tile=49 row_words=162 horizon=1121
2026-09-06T16:39:28.161452Z  INFO ipu_codegen.package.phase{phase="select_finalist"}: scheduled operator-plan finalist finalist=0 mapped=false analytical_cycles=466885 analytical_exchange_cycles=94080 scheduled_exchange_cycles=74373 refined_cycles=447178
2026-09-06T16:39:28.170688Z  INFO ipu_codegen.package.phase{phase="select_finalist"}: selected physically scheduled operator-plan finalist selected=0 mapped=false
2026-09-06T16:39:28.170730Z  INFO ipu_codegen.package.phase{phase="select_finalist"}: package build phase finished phase="select_finalist" elapsed_ms=808 success=true
2026-09-06T16:39:28.170742Z  INFO lowered graph for package construction logical_shards=5300 exchange_phases=15
2026-09-06T16:39:28.170985Z  INFO ipu_codegen.package.phase{phase="compile_runtime"}: package build phase finished phase="compile_runtime" elapsed_ms=0 success=true
2026-09-06T16:39:28.171656Z  INFO ipu_codegen.package.phase{phase="plan_kernels"}: package build phase finished phase="plan_kernels" elapsed_ms=0 success=true
2026-09-06T16:39:28.171839Z  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_k64_c80_r11_r12" target=ipu21
2026-09-06T16:39:28.234134Z  INFO ipu_codegen.package.phase{phase="compile_kernels"}: kernel artifact created object=/srv/home/.cache/ipu-stack/kernels/4e6c43abed853176425a783a129f9beba9a021d5b25406c8fa8f7e749807b02d/kernel.o metadata=/srv/home/.cache/ipu-stack/kernels/4e6c43abed853176425a783a129f9beba9a021d5b25406c8fa8f7e749807b02d/kernel.json
2026-09-06T16:39:28.234553Z  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_k80_c64_r11_r12" target=ipu21
2026-09-06T16:39:28.297734Z  INFO ipu_codegen.package.phase{phase="compile_kernels"}: kernel artifact created object=/srv/home/.cache/ipu-stack/kernels/684c91f6959636929d61f581c4a4076aace41387b992d4d780febcc8380ecd77/kernel.o metadata=/srv/home/.cache/ipu-stack/kernels/684c91f6959636929d61f581c4a4076aace41387b992d4d780febcc8380ecd77/kernel.json
2026-09-06T16:39:28.298119Z  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_c64_r22_r23" target=ipu21
2026-09-06T16:39:28.344949Z  INFO ipu_codegen.package.phase{phase="compile_kernels"}: kernel artifact created object=/srv/home/.cache/ipu-stack/kernels/56e1fa3ba6cbb09499166f3d553e9d5ddf61a26a76ae2d2b0bddc91b10976657/kernel.o metadata=/srv/home/.cache/ipu-stack/kernels/56e1fa3ba6cbb09499166f3d553e9d5ddf61a26a76ae2d2b0bddc91b10976657/kernel.json
2026-09-06T16:39:28.345331Z  INFO ipu_codegen.package.phase{phase="compile_kernels"}: compiling kernel source=/srv/home/gc-sdk/ipu-stack/crates/ipu-tests/../../device/attention_stages_f16.S name="attention_softmax_d72_p64_tail" target=ipu21
2026-09-06T16:39:28.406401Z  INFO ipu_codegen.package.phase{phase="compile_kernels"}: kernel artifact created object=/srv/home/.cache/ipu-stack/kernels/b227e17cdd6d4c8af04a2ec5184c6607aa2ee5eea241431ba435215990f54f61/kernel.o metadata=/srv/home/.cache/ipu-stack/kernels/b227e17cdd6d4c8af04a2ec5184c6607aa2ee5eea241431ba435215990f54f61/kernel.json
2026-09-06T16:39:28.406739Z  INFO ipu_codegen.package.phase{phase="compile_kernels"}: compiling kernel source=/srv/home/gc-sdk/ipu-stack/crates/ipu-tests/../../device/attention_softmax_f16.S name="attention_softmax_d72_p64_full" target=ipu21
2026-09-06T16:39:28.453561Z  INFO ipu_codegen.package.phase{phase="compile_kernels"}: kernel artifact created object=/srv/home/.cache/ipu-stack/kernels/0b83cfcd9a7fde1be76242afa0c4ab1a3c4dbd0b2ddd06ac0a1877a05957dddf/kernel.o metadata=/srv/home/.cache/ipu-stack/kernels/0b83cfcd9a7fde1be76242afa0c4ab1a3c4dbd0b2ddd06ac0a1877a05957dddf/kernel.json
2026-09-06T16:39:28.453754Z  INFO ipu_codegen.package.phase{phase="compile_kernels"}: package build phase finished phase="compile_kernels" elapsed_ms=282 success=true
2026-09-06T16:39:28.454076Z  INFO ipu_codegen.package.phase{phase="link_runtime"}: package build phase finished phase="link_runtime" elapsed_ms=0 success=true
2026-09-06T16:39:28.477139Z  INFO ipu_codegen.package.phase{phase="size_tile_code"}: package build phase finished phase="size_tile_code" elapsed_ms=3 success=true
2026-09-06T16:39:28.477177Z  INFO allocated package support memory linked_end=322548 profile_bytes=0 exchange_table_bytes=3852 host_code_bytes=1076 generated_code_bytes=2148 code_address=323632 standard_ranges=[(393216, 524288)]
2026-09-06T16:39:28.485070Z  INFO ipu_codegen.package.phase{phase="place_storage"}: package build phase finished phase="place_storage" elapsed_ms=7 success=true
2026-09-06T16:39:28.491989Z  INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=0
2026-09-06T16:39:28.529785Z  INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=1
2026-09-06T16:39:28.530394Z  INFO ipu_codegen.package.phase{phase="lower_exchanges"}: prepared large physical exchange phase phase=1 transfers=1038 maximum_identical_destinations=1
2026-09-06T16:39:28.530410Z  INFO ipu_codegen.package.phase{phase="lower_exchanges"}: optimized physical exchange schedule phase=1 initial_horizon=1121 selected_horizon=1121 endpoint_lower_bound=736 lower_bound_gap=385 selected_kind="reused" neighborhood_improvements=0
2026-09-06T16:39:28.531417Z  INFO ipu_codegen.package.phase{phase="lower_exchanges"}: finished large physical exchange phase phase=1 tile=49 row_words=162 horizon=1121
2026-09-06T16:39:28.554936Z  INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=2
2026-09-06T16:39:28.575539Z  INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=4
2026-09-06T16:39:28.580612Z  INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=5
2026-09-06T16:39:28.585801Z  INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=6
2026-09-06T16:39:28.591054Z  INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=7
2026-09-06T16:39:28.596300Z  INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=8
2026-09-06T16:39:28.601584Z  INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=9
2026-09-06T16:39:28.606743Z  INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=10
2026-09-06T16:39:28.611932Z  INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=11
2026-09-06T16:39:28.617288Z  INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=12
2026-09-06T16:39:28.622797Z  INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=13
2026-09-06T16:39:28.636577Z  INFO ipu_codegen.package.phase{phase="lower_exchanges"}: package build phase finished phase="lower_exchanges" elapsed_ms=151 success=true
2026-09-06T16:39:28.731047Z  INFO ipu_codegen.package.phase{phase="optimize_exchange_placement"}: package build phase finished phase="optimize_exchange_placement" elapsed_ms=94 success=true
2026-09-06T16:39:28.731776Z  INFO costed final placed program final_cycles=447367 final_exchange=74562
2026-09-06T16:39:28.746828Z  INFO ipu_codegen.package.phase{phase="prepare_tile_code"}: package build phase finished phase="prepare_tile_code" elapsed_ms=5 success=true
2026-09-06T16:39:28.753762Z  INFO ipu_codegen.package.phase{phase="emit_tile_code"}: package build phase finished phase="emit_tile_code" elapsed_ms=6 success=true
2026-09-06T16:39:28.884113Z  INFO ipu_codegen.package.phase{phase="build_tile_images"}: package build phase finished phase="build_tile_images" elapsed_ms=127 success=true
2026-09-06T16:39:28.894730Z  INFO writing application package tiles=1472
2026-09-06T16:39:28.912476Z  INFO application package written
2026-09-06T16:39:28.913432Z  INFO reading application package
2026-09-06T16:39:28.938638Z  INFO application package read tiles=1472 compiler=0.1.0
2026-09-06T16:39:28.939455Z  INFO waiting for hardware ownership path=artifacts/layout-sweep/device.lock
2026-09-06T16:39:28.939467Z  INFO acquired hardware ownership path=artifacts/layout-sweep/device.lock
2026-09-06T16:39:28.939473Z  INFO opening IPU device path="/dev/ipu0"
2026-09-06T16:39:28.939509Z  INFO IPU device attached path=/dev/ipu0
2026-09-06T16:39:28.939512Z  INFO initializing IPU device
2026-09-06T16:39:28.947527Z  INFO IPU device initialized
2026-09-06T16:39:28.947532Z  INFO replaying device configuration register_writes=2003
2026-09-06T16:39:28.951664Z  INFO loading application tile_count=1472 final_mark=23
2026-09-06T16:39:29.154450Z  INFO application loaded and initial synchronization completed tile_count=1472
2026-09-06T16:39:29.387043Z  INFO starting host exchange session startup_mark=23
2026-09-06T16:39:29.387089Z  INFO attaching host exchange pages pages=2
2026-09-06T16:39:29.387909Z  INFO host exchange session started
2026-09-06T16:39:29.387945Z  INFO invoking streaming host exchange call call="initialize" command=0 phases=24
2026-09-06T16:39:29.395228Z  INFO invoking streaming host exchange call call="run" command=0 phases=5
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-softmax-diagnostic/model.ipuexe tiles=1472 hardwareTest=PASS