2026-09-06T11:39:55.223851Z  INFO applied GEMM plan constraint source_operation=0 matching_plans=1 constraint=GemmPlanConstraint { source_operation: 0, orientation: Normal, row_partitions: 4, column_partitions: 92, inner_partitions: 4, result_row_partitions: 4, result_column_partitions: 1, output_column_block: 48, weight_memory_class: Ipu21Interleaved, reduction_staging: Complete, local_weight_staging: Direct }
2026-09-06T11:39:55.652792Z  INFO applied GEMM plan constraint source_operation=2 matching_plans=1 constraint=GemmPlanConstraint { source_operation: 2, orientation: Normal, row_partitions: 20, column_partitions: 36, inner_partitions: 2, result_row_partitions: 2, result_column_partitions: 1, output_column_block: 32, weight_memory_class: Ipu21Interleaved, reduction_staging: Complete, local_weight_staging: Direct }
2026-09-06T11:39:55.803087Z  INFO retained operator-plan finalist finalist=0 values=7 operations=4 estimated_cycles=460489 estimated_exchange_cycles=218520 exchange_row_bytes=48512 peak_standard_bytes=228736 peak_interleaved_bytes=276480 peak_total_bytes=505216 maximum_standard_allocation_bytes=180224 active_tile_counts={1440, 1472} padding_group_counts={} conversion_sources=[Some(OperationId(2))]
2026-09-06T11:39:55.806142Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="lower_mid"}: package build phase finished phase="lower_mid" elapsed_ms=759 success=true
2026-09-06T11:40:06.222256Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="select_finalist"}: selected analytical operator plan estimated_cycles=312166 estimated_exchange_cycles=99312
2026-09-06T11:40:06.270583Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="select_finalist"}: eliminated finite GEMM padding clears using load-time SRAM initialization removed=684
2026-09-06T11:40:06.272708Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="select_finalist"}: package build phase finished phase="select_finalist" elapsed_ms=10466 success=true
2026-09-06T11:40:06.272724Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}: lowered graph for package construction logical_shards=26192 exchange_phases=4
2026-09-06T11:40:06.272906Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="compile_runtime"}: package build phase finished phase="compile_runtime" elapsed_ms=0 success=true
2026-09-06T11:40:06.273520Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="plan_kernels"}: package build phase finished phase="plan_kernels" elapsed_ms=0 success=true
2026-09-06T11:40:06.273796Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}: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_k2160_c32_r36_r38" target=ipu21
2026-09-06T11:40:06.325478Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="compile_kernels"}: kernel artifact created object=/srv/home/.cache/ipu-stack/kernels/e6f5acfe8fa5ab780465b6edfb0d1e9beafe2854dd21d3441a734d4ddf057190/kernel.o metadata=/srv/home/.cache/ipu-stack/kernels/e6f5acfe8fa5ab780465b6edfb0d1e9beafe2854dd21d3441a734d4ddf057190/kernel.json
2026-09-06T11:40:06.325803Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="compile_kernels"}: package build phase finished phase="compile_kernels" elapsed_ms=52 success=true
2026-09-06T11:40:06.329235Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="link_runtime"}: package build phase finished phase="link_runtime" elapsed_ms=0 success=true
2026-09-06T11:40:06.358561Z ERROR tile allocation does not fit tile=368 class=Ipu21Standard bytes=163840 alignment=16384 first=10 last=14 free=[(362208, 524288), (819200, 949168)] active=[] tensor_type=TensorType { shape: TensorShape([1, 729, 4304]), format: TensorFormat { precision: F16, layout: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1440, replicas: 36, axes: [AxisTiling { axis: FromEnd(1), partitions: 2, padding_groups: 1, block_size: 2160, padding_multiple: 2160, shard_padding_multiple: 1, padding: Zero, tile_stride: None }, AxisTiling { axis: FromEnd(2), partitions: 20, padding_groups: 1, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } } }
2026-09-06T11:40:06.370730Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="plan_exchange_storage"}: package build phase finished phase="plan_exchange_storage" elapsed_ms=41 success=false
Error: placement failed: tile 368 has insufficient Ipu21Standard SRAM for 163840 bytes

Caused by:
    tile 368 has insufficient Ipu21Standard SRAM for 163840 bytes