2026-09-06T11:43:21.862847Z  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 }
2026-09-06T11:43:22.281569Z  INFO applied GEMM plan constraint source_operation=2 matching_plans=1 constraint=GemmPlanConstraint { source_operation: 2, orientation: Normal, row_partitions: 4, column_partitions: 72, inner_partitions: 5, result_row_partitions: 5, result_column_partitions: 1, output_column_block: 16, weight_memory_class: Ipu21Interleaved, reduction_staging: Complete, local_weight_staging: Direct }
2026-09-06T11:43:22.795619Z  INFO retained operator-plan finalist finalist=0 values=7 operations=4 estimated_cycles=446473 estimated_exchange_cycles=247640 exchange_row_bytes=55064 peak_standard_bytes=382744 peak_interleaved_bytes=88064 peak_total_bytes=443160 maximum_standard_allocation_bytes=327680 active_tile_counts={1440, 1472} padding_group_counts={} conversion_sources=[Some(OperationId(2))]
2026-09-06T11:43:22.800572Z  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=1236 success=true
2026-09-06T11:43:28.390974Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}:ipu_codegen.package.phase{phase="select_finalist"}: selected analytical operator plan estimated_cycles=275581 estimated_exchange_cycles=111776
2026-09-06T11:43:28.617503Z  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=216
2026-09-06T11:43:28.619858Z  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=5819 success=true
2026-09-06T11:43:28.619879Z  INFO ipu_codegen.package.build{tile_count=1472 operations=3}: lowered graph for package construction logical_shards=26696 exchange_phases=4
2026-09-06T11:43:28.620059Z  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
2026-09-06T11:43:28.620911Z  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
2026-09-06T11:43:28.621197Z  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_k864_c16_r182_r184" target=ipu21
2026-09-06T11:43:28.673288Z  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/693c1838f6306c68f798c49d5dba456e713e4013d9e246478e8ebf9fcc0a0200/kernel.o metadata=/srv/home/.cache/ipu-stack/kernels/693c1838f6306c68f798c49d5dba456e713e4013d9e246478e8ebf9fcc0a0200/kernel.json
2026-09-06T11:43:28.673613Z  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
2026-09-06T11:43:28.676403Z  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
2026-09-06T11:43:28.711975Z ERROR tile allocation does not fit tile=552 class=Ipu21Standard bytes=327680 alignment=16384 first=10 last=11 free=[(362208, 524288), (622592, 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: 72, axes: [AxisTiling { axis: FromEnd(1), partitions: 5, padding_groups: 1, block_size: 864, padding_multiple: 864, shard_padding_multiple: 1, padding: Zero, tile_stride: None }, AxisTiling { axis: FromEnd(2), partitions: 4, padding_groups: 1, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } } }
2026-09-06T11:43:28.713111Z ERROR tile allocation does not fit tile=368 class=Ipu21Standard bytes=327680 alignment=16384 first=10 last=14 free=[(362208, 524288), (622592, 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: 72, axes: [AxisTiling { axis: FromEnd(1), partitions: 5, padding_groups: 1, block_size: 864, padding_multiple: 864, shard_padding_multiple: 1, padding: Zero, tile_stride: None }, AxisTiling { axis: FromEnd(2), partitions: 4, padding_groups: 1, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } } }
2026-09-06T11:43:28.713307Z ERROR tile allocation does not fit tile=460 class=Ipu21Standard bytes=327680 alignment=16384 first=10 last=11 free=[(362208, 524288), (622592, 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: 72, axes: [AxisTiling { axis: FromEnd(1), partitions: 5, padding_groups: 1, block_size: 864, padding_multiple: 864, shard_padding_multiple: 1, padding: Zero, tile_stride: None }, AxisTiling { axis: FromEnd(2), partitions: 4, padding_groups: 1, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } } }
2026-09-06T11:43:28.720077Z  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=43 success=false
Error: placement failed: tile 552 has insufficient Ipu21Standard SRAM for 327680 bytes

Caused by:
    tile 552 has insufficient Ipu21Standard SRAM for 327680 bytes