Commit Graph

10 Commits

Author SHA1 Message Date
Jan Wassenberg 275135d7e8 Rename-only: remove Allocator2 etc suffixes now that refactoring is complete
PiperOrigin-RevId: 755397220
2025-05-06 09:12:43 -07:00
Jan Wassenberg 8532da47f7 Major refactor of allocator/args:
use new ThreadingContext2 instead of monostate/init in each frontend
Add ThreadingArgs(replaces AppArgs)

backprop: use Packed() accessor and MakePacked factory and row-based access to allow for stride
compress_weights: remove, moving to py-only exporter instead

Move MatPtr to mat.h and revise interface:
- Generic MatOwner
- rename accessors to Packed*
- support stride/row accessors, fix RowPtr stride

Add TypeBits(Type)
Move GenerateMat to test_util-inl for sharing between matmul test/bench
Move internal init to gemma.cc to avoid duplication
Rename GemmaEnv model_ to gemma_ for disambiguating vs upcoming ModelStorage
Remove --compressed_weights, use --weights instead.
tensor_index: add ExtentsFromInfo and TensorIndexLLM/Img
Allocator: use normal unique_ptr for AllocBytes so users can call directly
threading: use -> because AlignedPtr no longer assumes arrays
PiperOrigin-RevId: 745918637
2025-04-10 01:29:54 -07:00
Jan Wassenberg 1b72c22345 Refactor Gemma ctor and improve pool NUMA support
Gemma receives a MatMulEnv arg, with comment on lifetime
Split threading into topology so the latter can be used in allocator
Add AllocClasses() for non-POD (ThreadPool)
Support binding pool to NUMA node
Update threading_test with latency measurements
Also update Highway version.

PiperOrigin-RevId: 736904748
2025-03-14 10:19:00 -07:00
Jan Wassenberg bdf5d25e97 Only temporarily enable spinning in threading benchmark
PiperOrigin-RevId: 727114863
2025-02-14 17:15:38 -08:00
Jan Wassenberg 06c70dccd9 Less verbose threading_test output, improve formatting.
PiperOrigin-RevId: 726364085
2025-02-13 00:56:34 -08:00
Jan Wassenberg 5563d94811 Add fork/join latency benchmark
PiperOrigin-RevId: 725174042
2025-02-10 05:23:44 -08:00
Jan Wassenberg c4398fc72d Infra improvements:
allocator: support mmap, fixed Bind, add padding
bench_matmul: Add PreventElision
BUILD: add ops_test build target
matmul.h: move ConstMat here; dynamic alloc of MatMulEnv
matmul_test: remove benchmarking
replace fprintf with HWY_WARN
threading.cc: support splitting large clusters (disabled); package_idx->pkg_idx, smaller IndexRangePartition
PiperOrigin-RevId: 717512274
2025-01-20 06:22:49 -08:00
Jan Wassenberg f74d496879 Threading/infra improvements.
* Add Parallelize*Range helpers and partitioning helpers
* Refactor Pinning class, store original affinity (required to construct another NestedPools after pinning happened)

Compress:
* prevent Compress printing stats in tests
* zero-pad tensors

Matmul:
* add matmul_unit_test (TODO) and bench_matmul
* matmul_test: change norm to row vectors (that is what is added) and include bf16 rounding error
* Prepare for L2/L3 retrieval
PiperOrigin-RevId: 700603811
2024-11-27 01:12:00 -08:00
Jan Wassenberg 02ce1e344f Use NestedPools, add NUMA infra
Improved threading.h, fix thread counts for single package/cluster systems
Temporarily forces to a single socket. Prefill 29.28 tps, decode 6.92.

Also fix benchmarks.cc build, update tensor allocator to Allocator

PiperOrigin-RevId: 687307167
2024-10-18 08:11:18 -07:00
Jan Wassenberg 2c28b18eb0 Add NestedPools: one per socket/cluster
Use in dot_test
app.h: add new flags and rename num_threads to max_threads
matmul: Parallelize MatMulSlow and enable spinning, more large/fewer medium test cases
PiperOrigin-RevId: 683216386
2024-10-07 09:40:19 -07:00