2026-09-06T17:46:13.518523Z INFO retained operator-plan finalist finalist=0 values=11 operations=7 estimated_cycles=485686 estimated_exchange_cycles=173640 exchange_row_bytes=35532 peak_standard_bytes=76236 peak_interleaved_bytes=114688 peak_total_bytes=166604 maximum_standard_allocation_bytes=16384 active_tile_counts={12, 64} padding_group_counts={} conversion_sources=[] 2026-09-06T17:46:13.518659Z INFO retained operator-plan finalist finalist=1 values=13 operations=9 estimated_cycles=526835 estimated_exchange_cycles=216400 exchange_row_bytes=44760 peak_standard_bytes=106200 peak_interleaved_bytes=92160 peak_total_bytes=184024 maximum_standard_allocation_bytes=61440 active_tile_counts={12, 64} padding_group_counts={} conversion_sources=[Some(OperationId(1)), Some(OperationId(2))] 2026-09-06T17:46:13.518731Z INFO retained operator-plan finalist finalist=2 values=12 operations=8 estimated_cycles=546120 estimated_exchange_cycles=242000 exchange_row_bytes=50520 peak_standard_bytes=128344 peak_interleaved_bytes=71680 peak_total_bytes=189784 maximum_standard_allocation_bytes=61440 active_tile_counts={12, 64} padding_group_counts={} conversion_sources=[Some(OperationId(2))] 2026-09-06T17:46:13.518795Z INFO retained operator-plan finalist finalist=3 values=13 operations=9 estimated_cycles=547519 estimated_exchange_cycles=213840 exchange_row_bytes=44184 peak_standard_bytes=105624 peak_interleaved_bytes=94208 peak_total_bytes=199832 maximum_standard_allocation_bytes=61440 active_tile_counts={12, 64} padding_group_counts={} conversion_sources=[Some(OperationId(1)), Some(OperationId(2))] 2026-09-06T17:46:13.524165Z INFO ipu_codegen.package.phase{phase="lower_mid"}: package build phase finished phase="lower_mid" elapsed_ms=352 success=true 2026-09-06T17:46:13.898052Z INFO screened tile mappings by exchange resource load candidates=19 baseline_cycles=77644 candidate_cycles=77644 baseline_pressure=69478 candidate_pressure=69478 2026-09-06T17:46:13.898099Z INFO screened tile mappings by exchange resource load candidates=19 baseline_cycles=89548 candidate_cycles=89548 baseline_pressure=76364 candidate_pressure=76364 2026-09-06T17:46:13.903814Z INFO modelled expanded operator plan finalist=3 modelled_cycles=490239 estimated_cycles=571355 estimated_exchange_cycles=169560 2026-09-06T17:46:13.903898Z INFO modelled expanded operator plan finalist=2 modelled_cycles=545055 estimated_cycles=696787 estimated_exchange_cycles=252080 2026-09-06T17:46:14.000410Z INFO screened tile mappings by exchange resource load candidates=15 baseline_cycles=64048 candidate_cycles=64048 baseline_pressure=61303 candidate_pressure=61303 2026-09-06T17:46:14.003942Z INFO modelled expanded operator plan finalist=0 modelled_cycles=398594 estimated_cycles=427786 estimated_exchange_cycles=102240 2026-09-06T17:46:14.096170Z INFO screened tile mappings by exchange resource load candidates=19 baseline_cycles=78248 candidate_cycles=78248 baseline_pressure=69677 candidate_pressure=69677 2026-09-06T17:46:14.102131Z INFO modelled expanded operator plan finalist=1 modelled_cycles=467976 estimated_cycles=548488 estimated_exchange_cycles=169560 2026-09-06T17:46:14.201905Z INFO ipu_codegen.package.phase{phase="select_finalist"}: prepared large physical exchange phase phase=1 transfers=1045 maximum_identical_destinations=1 2026-09-06T17:46:14.201947Z INFO ipu_codegen.package.phase{phase="select_finalist"}: optimized physical exchange schedule phase=1 initial_horizon=1123 selected_horizon=1123 endpoint_lower_bound=928 lower_bound_gap=195 selected_kind="full-duplex" neighborhood_improvements=0 2026-09-06T17:46:14.202932Z INFO ipu_codegen.package.phase{phase="select_finalist"}: finished large physical exchange phase phase=1 tile=49 row_words=167 horizon=1123 2026-09-06T17:46:14.582546Z INFO ipu_codegen.package.phase{phase="select_finalist"}: prepared large physical exchange phase phase=2 transfers=3337 maximum_identical_destinations=1 2026-09-06T17:46:14.582594Z INFO ipu_codegen.package.phase{phase="select_finalist"}: optimized physical exchange schedule phase=2 initial_horizon=2828 selected_horizon=2828 endpoint_lower_bound=736 lower_bound_gap=2092 selected_kind="full-duplex" neighborhood_improvements=0 2026-09-06T17:46:14.585532Z INFO ipu_codegen.package.phase{phase="select_finalist"}: finished large physical exchange phase phase=2 tile=4 row_words=330 horizon=2828 2026-09-06T17:46:14.711101Z INFO ipu_codegen.package.phase{phase="select_finalist"}: scheduled operator-plan finalist finalist=0 mapped=false analytical_cycles=427786 analytical_exchange_cycles=102240 scheduled_exchange_cycles=76322 refined_cycles=401868 2026-09-06T17:46:14.724546Z INFO ipu_codegen.package.phase{phase="select_finalist"}: selected physically scheduled operator-plan finalist selected=0 mapped=false 2026-09-06T17:46:14.724583Z INFO ipu_codegen.package.phase{phase="select_finalist"}: package build phase finished phase="select_finalist" elapsed_ms=1200 success=true 2026-09-06T17:46:14.724596Z INFO lowered graph for package construction logical_shards=5364 exchange_phases=15 2026-09-06T17:46:14.724846Z INFO ipu_codegen.package.phase{phase="compile_runtime"}: package build phase finished phase="compile_runtime" elapsed_ms=0 success=true 2026-09-06T17:46:14.725581Z INFO ipu_codegen.package.phase{phase="plan_kernels"}: package build phase finished phase="plan_kernels" elapsed_ms=0 success=true 2026-09-06T17:46:14.725835Z 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_r32_r32" target=ipu21 2026-09-06T17:46:14.793707Z INFO ipu_codegen.package.phase{phase="compile_kernels"}: kernel artifact created object=/srv/home/.cache/ipu-stack/kernels/371a67537e29ee9a885c09b13a56fb06f37aa48ba0c256c0c59db0352abf4ca5/kernel.o metadata=/srv/home/.cache/ipu-stack/kernels/371a67537e29ee9a885c09b13a56fb06f37aa48ba0c256c0c59db0352abf4ca5/kernel.json 2026-09-06T17:46:14.793916Z 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 2026-09-06T17:46:14.856041Z INFO ipu_codegen.package.phase{phase="compile_kernels"}: kernel artifact created object=/srv/home/.cache/ipu-stack/kernels/3268926e4180c7347c62fee347f6bf39f96c8a2800885dd1b24b0ee982915075/kernel.o metadata=/srv/home/.cache/ipu-stack/kernels/3268926e4180c7347c62fee347f6bf39f96c8a2800885dd1b24b0ee982915075/kernel.json 2026-09-06T17:46:14.856282Z 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 2026-09-06T17:46:14.910234Z INFO ipu_codegen.package.phase{phase="compile_kernels"}: kernel artifact created object=/srv/home/.cache/ipu-stack/kernels/6c6768064ee2487b001b87b17a5244515fd625d6b2f92a9160156e98f3f25910/kernel.o metadata=/srv/home/.cache/ipu-stack/kernels/6c6768064ee2487b001b87b17a5244515fd625d6b2f92a9160156e98f3f25910/kernel.json 2026-09-06T17:46:14.910469Z 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_r22_p32_c8_p64_b64_16" target=ipu21 2026-09-06T17:46:15.247076Z INFO ipu_codegen.package.phase{phase="compile_kernels"}: kernel artifact created object=/srv/home/.cache/ipu-stack/kernels/fff1385b7da452213b5a6a55a62c91b01c9f25d8f88a461c466a76094e9452d3/kernel.o metadata=/srv/home/.cache/ipu-stack/kernels/fff1385b7da452213b5a6a55a62c91b01c9f25d8f88a461c466a76094e9452d3/kernel.json 2026-09-06T17:46:15.247299Z 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_r22_p32_c8_p64_b64_16" target=ipu21 2026-09-06T17:46:15.303348Z INFO ipu_codegen.package.phase{phase="compile_kernels"}: kernel artifact created object=/srv/home/.cache/ipu-stack/kernels/5132a71503f049918c4daa43ec02b4a169bae50f87568f11200debf5dfcfc9ad/kernel.o metadata=/srv/home/.cache/ipu-stack/kernels/5132a71503f049918c4daa43ec02b4a169bae50f87568f11200debf5dfcfc9ad/kernel.json 2026-09-06T17:46:15.303607Z 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_r22_p32_c64_p64_b64_16" target=ipu21 2026-09-06T17:46:15.661975Z INFO ipu_codegen.package.phase{phase="compile_kernels"}: kernel artifact created object=/srv/home/.cache/ipu-stack/kernels/6a5e7839a253923e2bf43803e69e5ee5cf0eb523d782a3d79f57f151e8f18849/kernel.o metadata=/srv/home/.cache/ipu-stack/kernels/6a5e7839a253923e2bf43803e69e5ee5cf0eb523d782a3d79f57f151e8f18849/kernel.json 2026-09-06T17:46:15.662378Z 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_r22_p32_c64_p64_b64_16" target=ipu21 2026-09-06T17:46:15.713576Z INFO ipu_codegen.package.phase{phase="compile_kernels"}: kernel artifact created object=/srv/home/.cache/ipu-stack/kernels/44966d6b58ddbbc603c54c63690449b80c9716f7006173fb9b993515605f4b37/kernel.o metadata=/srv/home/.cache/ipu-stack/kernels/44966d6b58ddbbc603c54c63690449b80c9716f7006173fb9b993515605f4b37/kernel.json 2026-09-06T17:46:15.713920Z 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_r23_p32_c8_p64_b64_16" target=ipu21 2026-09-06T17:46:16.080842Z INFO ipu_codegen.package.phase{phase="compile_kernels"}: kernel artifact created object=/srv/home/.cache/ipu-stack/kernels/b75ca108f46982d42f5e08e388d28e56052453898677b1366330045522d2c2d5/kernel.o metadata=/srv/home/.cache/ipu-stack/kernels/b75ca108f46982d42f5e08e388d28e56052453898677b1366330045522d2c2d5/kernel.json 2026-09-06T17:46:16.081281Z 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_r23_p32_c8_p64_b64_16" target=ipu21 2026-09-06T17:46:16.137074Z INFO ipu_codegen.package.phase{phase="compile_kernels"}: kernel artifact created object=/srv/home/.cache/ipu-stack/kernels/7b0ce9ff258f98b5bfce5809fd5929f8240fb6a402d4f79258e9692dd5d4c49b/kernel.o metadata=/srv/home/.cache/ipu-stack/kernels/7b0ce9ff258f98b5bfce5809fd5929f8240fb6a402d4f79258e9692dd5d4c49b/kernel.json 2026-09-06T17:46:16.137299Z 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_r23_p32_c64_p64_b64_16" target=ipu21 2026-09-06T17:46:16.512295Z INFO ipu_codegen.package.phase{phase="compile_kernels"}: kernel artifact created object=/srv/home/.cache/ipu-stack/kernels/d1bdeb081749119d65574dc5d15225558e9833e66729c9ab58f13ccb9e9b3627/kernel.o metadata=/srv/home/.cache/ipu-stack/kernels/d1bdeb081749119d65574dc5d15225558e9833e66729c9ab58f13ccb9e9b3627/kernel.json 2026-09-06T17:46:16.512596Z 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_r23_p32_c64_p64_b64_16" target=ipu21 2026-09-06T17:46:16.569138Z INFO ipu_codegen.package.phase{phase="compile_kernels"}: kernel artifact created object=/srv/home/.cache/ipu-stack/kernels/03af3dac2ae544f3cfa757cbb208dfbb0bf113583bc258921cf9083eabb64161/kernel.o metadata=/srv/home/.cache/ipu-stack/kernels/03af3dac2ae544f3cfa757cbb208dfbb0bf113583bc258921cf9083eabb64161/kernel.json 2026-09-06T17:46:16.569613Z INFO ipu_codegen.package.phase{phase="compile_kernels"}: package build phase finished phase="compile_kernels" elapsed_ms=1844 success=true 2026-09-06T17:46:16.569961Z INFO ipu_codegen.package.phase{phase="link_runtime"}: package build phase finished phase="link_runtime" elapsed_ms=0 success=true 2026-09-06T17:46:16.593323Z INFO ipu_codegen.package.phase{phase="size_tile_code"}: package build phase finished phase="size_tile_code" elapsed_ms=3 success=true 2026-09-06T17:46:16.593375Z INFO allocated package support memory linked_end=321036 profile_bytes=0 exchange_table_bytes=4516 host_code_bytes=1084 generated_code_bytes=2548 code_address=322128 standard_ranges=[(393216, 524288)] 2026-09-06T17:46:16.600390Z INFO ipu_codegen.package.phase{phase="place_storage"}: package build phase finished phase="place_storage" elapsed_ms=6 success=true 2026-09-06T17:46:16.610148Z INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=0 2026-09-06T17:46:16.654833Z INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=1 2026-09-06T17:46:16.655447Z INFO ipu_codegen.package.phase{phase="lower_exchanges"}: prepared large physical exchange phase phase=1 transfers=1045 maximum_identical_destinations=1 2026-09-06T17:46:16.655462Z INFO ipu_codegen.package.phase{phase="lower_exchanges"}: optimized physical exchange schedule phase=1 initial_horizon=1123 selected_horizon=1123 endpoint_lower_bound=928 lower_bound_gap=195 selected_kind="reused" neighborhood_improvements=0 2026-09-06T17:46:16.656471Z INFO ipu_codegen.package.phase{phase="lower_exchanges"}: finished large physical exchange phase phase=1 tile=49 row_words=167 horizon=1123 2026-09-06T17:46:16.851793Z INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=2 2026-09-06T17:46:16.853517Z INFO ipu_codegen.package.phase{phase="lower_exchanges"}: prepared large physical exchange phase phase=2 transfers=3337 maximum_identical_destinations=1 2026-09-06T17:46:16.853539Z INFO ipu_codegen.package.phase{phase="lower_exchanges"}: optimized physical exchange schedule phase=2 initial_horizon=2828 selected_horizon=2828 endpoint_lower_bound=736 lower_bound_gap=2092 selected_kind="reused" neighborhood_improvements=0 2026-09-06T17:46:16.856460Z INFO ipu_codegen.package.phase{phase="lower_exchanges"}: finished large physical exchange phase phase=2 tile=4 row_words=330 horizon=2828 2026-09-06T17:46:16.862181Z INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=3 2026-09-06T17:46:16.870418Z INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=4 2026-09-06T17:46:16.878773Z INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=5 2026-09-06T17:46:16.886904Z INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=6 2026-09-06T17:46:16.895289Z INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=7 2026-09-06T17:46:16.901455Z INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=8 2026-09-06T17:46:16.907959Z INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=9 2026-09-06T17:46:16.917519Z INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=10 2026-09-06T17:46:16.925860Z INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=11 2026-09-06T17:46:16.931806Z INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=12 2026-09-06T17:46:16.937405Z INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=13 2026-09-06T17:46:16.942847Z INFO ipu_codegen.package.phase{phase="lower_exchanges"}: reused exchange optimization after validating relocated rows phase=14 2026-09-06T17:46:16.943630Z INFO ipu_codegen.package.phase{phase="lower_exchanges"}: package build phase finished phase="lower_exchanges" elapsed_ms=343 success=true 2026-09-06T17:46:17.050007Z INFO ipu_codegen.package.phase{phase="optimize_exchange_placement"}: package build phase finished phase="optimize_exchange_placement" elapsed_ms=106 success=true 2026-09-06T17:46:17.050998Z INFO costed final placed program final_cycles=401868 final_exchange=76322 2026-09-06T17:46:17.078148Z INFO ipu_codegen.package.phase{phase="prepare_tile_code"}: package build phase finished phase="prepare_tile_code" elapsed_ms=15 success=true 2026-09-06T17:46:17.088962Z INFO ipu_codegen.package.phase{phase="emit_tile_code"}: package build phase finished phase="emit_tile_code" elapsed_ms=10 success=true 2026-09-06T17:46:17.329646Z INFO ipu_codegen.package.phase{phase="build_tile_images"}: package build phase finished phase="build_tile_images" elapsed_ms=236 success=true 2026-09-06T17:46:17.345786Z INFO writing application package tiles=1472 2026-09-06T17:46:17.362576Z INFO application package written 2026-09-06T17:46:17.363581Z INFO reading application package 2026-09-06T17:46:17.381417Z INFO application package read tiles=1472 compiler=0.1.0 2026-09-06T17:46:17.381737Z INFO waiting for hardware ownership path=artifacts/layout-sweep/device.lock 2026-09-06T17:46:17.381747Z INFO acquired hardware ownership path=artifacts/layout-sweep/device.lock 2026-09-06T17:46:17.381752Z INFO opening IPU device path="/dev/ipu0" 2026-09-06T17:46:17.381792Z INFO IPU device attached path=/dev/ipu0 2026-09-06T17:46:17.381795Z INFO initializing IPU device 2026-09-06T17:46:17.389641Z INFO IPU device initialized 2026-09-06T17:46:17.389648Z INFO replaying device configuration register_writes=2003 2026-09-06T17:46:17.394100Z INFO loading application tile_count=1472 final_mark=23 2026-09-06T17:46:17.586037Z INFO application loaded and initial synchronization completed tile_count=1472 2026-09-06T17:46:17.802264Z INFO starting host exchange session startup_mark=23 2026-09-06T17:46:17.802303Z INFO attaching host exchange pages pages=2 2026-09-06T17:46:17.803119Z INFO host exchange session started 2026-09-06T17:46:17.803128Z INFO invoking streaming host exchange call call="initialize" command=0 phases=24 2026-09-06T17:46:17.807323Z 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-packed-diagnostic3/model.ipuexe tiles=1472 hardwareTest=PASS