2026-09-06T18:00:07.170145Z  INFO retained operator-plan finalist finalist=0 values=3 operations=1 estimated_cycles=17734 estimated_exchange_cycles=0 exchange_row_bytes=0 peak_standard_bytes=32768 peak_interleaved_bytes=40960 peak_total_bytes=73728 maximum_standard_allocation_bytes=32768 active_tile_counts={64} padding_group_counts={} conversion_sources=[]
2026-09-06T18:00:07.170230Z  INFO retained operator-plan finalist finalist=1 values=3 operations=1 estimated_cycles=18028 estimated_exchange_cycles=0 exchange_row_bytes=0 peak_standard_bytes=32768 peak_interleaved_bytes=40960 peak_total_bytes=73728 maximum_standard_allocation_bytes=32768 active_tile_counts={64} padding_group_counts={} conversion_sources=[]
2026-09-06T18:00:07.170259Z  INFO retained operator-plan finalist finalist=2 values=3 operations=1 estimated_cycles=18278 estimated_exchange_cycles=0 exchange_row_bytes=0 peak_standard_bytes=40960 peak_interleaved_bytes=32768 peak_total_bytes=73728 maximum_standard_allocation_bytes=32768 active_tile_counts={64} padding_group_counts={} conversion_sources=[]
2026-09-06T18:00:07.170284Z  INFO retained operator-plan finalist finalist=3 values=3 operations=1 estimated_cycles=36556 estimated_exchange_cycles=0 exchange_row_bytes=0 peak_standard_bytes=49152 peak_interleaved_bytes=32768 peak_total_bytes=81920 maximum_standard_allocation_bytes=32768 active_tile_counts={64} padding_group_counts={} conversion_sources=[]
2026-09-06T18:00:07.171093Z  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=22 success=true
2026-09-06T18:00:07.182188Z  INFO eliminated finite GEMM padding clears using load-time SRAM initialization removed=0
2026-09-06T18:00:07.182314Z  INFO eliminated finite GEMM padding clears using load-time SRAM initialization removed=0
2026-09-06T18:00:07.182416Z  INFO eliminated finite GEMM padding clears using load-time SRAM initialization removed=0
2026-09-06T18:00:07.182422Z  INFO eliminated finite GEMM padding clears using load-time SRAM initialization removed=0
2026-09-06T18:00:07.183480Z  INFO screened tile mappings by exchange resource load candidates=5 baseline_cycles=0 candidate_cycles=0 baseline_pressure=0 candidate_pressure=0
2026-09-06T18:00:07.183513Z  INFO modelled expanded operator plan finalist=0 modelled_cycles=17734 estimated_cycles=17734 estimated_exchange_cycles=0
2026-09-06T18:00:07.183521Z  INFO screened tile mappings by exchange resource load candidates=5 baseline_cycles=0 candidate_cycles=0 baseline_pressure=0 candidate_pressure=0
2026-09-06T18:00:07.183529Z  INFO screened tile mappings by exchange resource load candidates=5 baseline_cycles=0 candidate_cycles=0 baseline_pressure=0 candidate_pressure=0
2026-09-06T18:00:07.183581Z  INFO modelled expanded operator plan finalist=3 modelled_cycles=36556 estimated_cycles=36556 estimated_exchange_cycles=0
2026-09-06T18:00:07.183589Z  INFO modelled expanded operator plan finalist=1 modelled_cycles=18028 estimated_cycles=18028 estimated_exchange_cycles=0
2026-09-06T18:00:07.183596Z  INFO screened tile mappings by exchange resource load candidates=5 baseline_cycles=0 candidate_cycles=0 baseline_pressure=0 candidate_pressure=0
2026-09-06T18:00:07.183695Z  INFO modelled expanded operator plan finalist=2 modelled_cycles=18278 estimated_cycles=18278 estimated_exchange_cycles=0
2026-09-06T18:00:07.183795Z  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=17734 analytical_exchange_cycles=0 scheduled_exchange_cycles=0 refined_cycles=17734
2026-09-06T18:00:07.184069Z  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
2026-09-06T18:00:07.184076Z  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=12 success=true
2026-09-06T18:00:07.184090Z  INFO ipu_codegen.package.build{tile_count=64 operations=1}: lowered graph for package construction logical_shards=192 exchange_phases=0
2026-09-06T18:00:07.184276Z  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
2026-09-06T18:00:07.184318Z  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
2026-09-06T18:00:07.184450Z  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_packed64_k64_c64_r128_r128" target=ipu21
2026-09-06T18:00:07.236462Z  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/4b962a96559ea50038f257a9b15103e268a683b8e913d59e26e357406beba5ea/kernel.o metadata=/srv/home/.cache/ipu-stack/kernels/4b962a96559ea50038f257a9b15103e268a683b8e913d59e26e357406beba5ea/kernel.json
2026-09-06T18:00:07.236537Z  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=52 success=true
2026-09-06T18:00:07.236702Z  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
2026-09-06T18:00:07.249821Z  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
2026-09-06T18:00:07.249882Z  INFO ipu_codegen.package.build{tile_count=64 operations=1}: allocated package support memory linked_end=312804 profile_bytes=8 exchange_table_bytes=0 host_code_bytes=1296 generated_code_bytes=264 code_address=314104 standard_ranges=[(393216, 524288)]
2026-09-06T18:00:07.250790Z  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=0 success=true
2026-09-06T18:00:07.250806Z  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=0 success=true
2026-09-06T18:00:07.250815Z  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
2026-09-06T18:00:07.250844Z  INFO ipu_codegen.package.build{tile_count=64 operations=1}: costed final placed program final_cycles=17734 final_exchange=0
2026-09-06T18:00:07.256637Z  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=1 success=true
2026-09-06T18:00:07.257635Z  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=0 success=true
2026-09-06T18:00:07.297872Z  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=40 success=true
2026-09-06T18:00:07.301006Z  INFO writing application package tiles=1472
2026-09-06T18:00:07.303375Z  INFO application package written
2026-09-06T18:00:07.303512Z  INFO reading application package
2026-09-06T18:00:07.308229Z  INFO application package read tiles=1472 compiler=0.1.0
2026-09-06T18:00:07.308790Z  INFO waiting for hardware ownership path=artifacts/layout-sweep/device.lock
2026-09-06T18:00:07.308799Z  INFO acquired hardware ownership path=artifacts/layout-sweep/device.lock
2026-09-06T18:00:07.308803Z  INFO opening IPU device path="/dev/ipu0"
2026-09-06T18:00:07.308827Z  INFO IPU device attached path=/dev/ipu0
2026-09-06T18:00:07.308829Z  INFO initializing IPU device
2026-09-06T18:00:07.316820Z  INFO IPU device initialized
2026-09-06T18:00:07.316844Z  INFO replaying device configuration register_writes=2003
2026-09-06T18:00:07.320377Z  INFO loading application tile_count=1472 final_mark=23
2026-09-06T18:00:07.488860Z  INFO application loaded and initial synchronization completed tile_count=1472
2026-09-06T18:00:07.518043Z  INFO starting host exchange session startup_mark=23
2026-09-06T18:00:07.518053Z  INFO attaching host exchange pages pages=2
2026-09-06T18:00:07.518845Z  INFO host exchange session started
2026-09-06T18:00:07.518852Z  INFO invoking streaming host exchange call call="initialize" command=0 phases=4
2026-09-06T18:00:07.519432Z  INFO invoking streaming host exchange call call="run" command=0 phases=21
profile=artifacts/layout-sweep/gemm-packed-panel-boundaries/execution.ipuprofile tiles=64 samples=64
workload=gemm-f16-r8192-k64-c64 benchmark=gemm-f16 rows=8192 inner=64 columns=64 activeTiles=64 executionTiles=64 inputBytes=1048576 weightBytes=524288 cycles=20124 minimumTileCycles=20124 deviceMicroseconds=13.416 tflops=5.002 peakTflops=12.288 efficiencyPercent=40.71 maximumAbsoluteError=0.000000
package=artifacts/layout-sweep/gemm-packed-panel-boundaries/model.ipuexe tiles=1472 hardwareTest=PASS