Arkar Min Aung 6d01528e90 feat: Add benchmarking and documentation updates for Metal SVD ... - Add comprehensive SVD benchmark script (benchmarks/python/svd_benchmark.py): * Performance comparison between CPU and GPU implementations * Batch processing benchmarks * Correctness verification tests * Detailed timing and speedup analysis - Update linalg documentation to mention Metal GPU acceleration - Add implementation summary document for development reference This addresses CONTRIBUTING.md requirements: - Benchmarks for efficiency impact measurement (point 3) - Documentation updates for API changes (point 4) - Comprehensive testing coverage (point 2)		2025-06-14 17:28:19 +10:00
..
jit	feat: Add Metal SVD infrastructure and parameter structures	2025-06-13 23:28:52 +10:00
kernels	feat: Add benchmarking and documentation updates for Metal SVD	2025-06-14 17:28:19 +10:00
allocator.cpp	Add memory cache to CUDA backend (#2221)	2025-05-30 12:12:54 -07:00
allocator.h	Add memory cache to CUDA backend (#2221)	2025-05-30 12:12:54 -07:00
binary.cpp	Improve metal elementwise kernels (#2247)	2025-06-06 11:37:40 -07:00
binary.h	Fixes for large arrays with a few ops (#1299)	2024-07-30 17:18:39 -07:00
CMakeLists.txt	feat: Add Metal SVD infrastructure and parameter structures	2025-06-13 23:28:52 +10:00
compiled.cpp	Improve metal elementwise kernels (#2247)	2025-06-06 11:37:40 -07:00
conv.cpp	Collection of refactors (#2274)	2025-06-13 10:44:56 -07:00
copy.cpp	Improve metal elementwise kernels (#2247)	2025-06-06 11:37:40 -07:00
custom_kernel.cpp	Fix unintuitive metal kernel caching (#2242)	2025-06-06 20:08:15 -07:00
device.cpp	Collection of refactors (#2274)	2025-06-13 10:44:56 -07:00
device.h	Collection of refactors (#2274)	2025-06-13 10:44:56 -07:00
distributed.cpp	Move common gpu primitives to backend/gpu (#2145)	2025-05-05 13:45:29 -07:00
eval.cpp	Generalize gpu backend (#2138)	2025-04-30 09:08:17 -07:00
event.cpp	Generalize gpu backend (#2138)	2025-04-30 09:08:17 -07:00
fence.cpp	fix input coherent kernel launch (#2153)	2025-05-05 17:30:50 -07:00
fft.cpp	Fix fft for integer overflow (#2161)	2025-05-09 14:25:12 -07:00
hadamard.cpp	Move common gpu primitives to backend/gpu (#2145)	2025-05-05 13:45:29 -07:00
indexing.cpp	Add remove_index utility (#2173)	2025-05-13 17:09:56 -07:00
jit_kernels.cpp	feat: Implement basic one-sided Jacobi SVD algorithm in Metal	2025-06-14 17:05:10 +10:00
kernels.h	feat: Add Metal SVD infrastructure and parameter structures	2025-06-13 23:28:52 +10:00
logsumexp.cpp	Move common gpu primitives to backend/gpu (#2145)	2025-05-05 13:45:29 -07:00
make_compiled_preamble.sh	Dispatch bf16 at run time when using the JIT (#1584)	2024-11-15 16:54:36 -08:00
matmul.cpp	Collection of refactors (#2274)	2025-06-13 10:44:56 -07:00
matmul.h	Collection of refactors (#2274)	2025-06-13 10:44:56 -07:00
metal.cpp	Generalize gpu backend (#2138)	2025-04-30 09:08:17 -07:00
metal.h	Generalize gpu backend (#2138)	2025-04-30 09:08:17 -07:00
no_metal.cpp	start cuda circle config (#2256)	2025-06-10 21:19:47 -07:00
nojit_kernels.cpp	Add load_safe to the general conv loaders (#2258)	2025-06-10 20:58:16 -07:00
normalization.cpp	Collection of refactors (#2274)	2025-06-13 10:44:56 -07:00
primitives.cpp	feat: Add Metal SVD infrastructure and parameter structures	2025-06-13 23:28:52 +10:00
quantized.cpp	5bit quants (#2226)	2025-05-30 12:12:10 -07:00
reduce.cpp	Move common gpu primitives to backend/gpu (#2145)	2025-05-05 13:45:29 -07:00
reduce.h	Reductions update (#1351)	2024-11-04 22:25:16 -08:00
resident.cpp	Generalize gpu backend (#2138)	2025-04-30 09:08:17 -07:00
resident.h	Wired (#1510)	2024-10-25 09:35:33 -07:00
rope.cpp	Fast primitives decide when to use the fallback (#2216)	2025-06-02 13:26:37 -07:00
scaled_dot_product_attention.cpp	Fix unintuitive metal kernel caching (#2242)	2025-06-06 20:08:15 -07:00
scan.cpp	Move common gpu primitives to backend/gpu (#2145)	2025-05-05 13:45:29 -07:00
slicing.cpp	Move common gpu primitives to backend/gpu (#2145)	2025-05-05 13:45:29 -07:00
softmax.cpp	Move common gpu primitives to backend/gpu (#2145)	2025-05-05 13:45:29 -07:00
sort.cpp	Move common gpu primitives to backend/gpu (#2145)	2025-05-05 13:45:29 -07:00
svd.cpp	feat: Add benchmarking and documentation updates for Metal SVD	2025-06-14 17:28:19 +10:00
ternary.cpp	Improve metal elementwise kernels (#2247)	2025-06-06 11:37:40 -07:00
ternary.h	Add some internal GPU apis (#1177)	2024-06-04 09:24:26 -07:00
unary.cpp	CUDA backend: unary ops (#2158)	2025-06-09 06:45:08 -07:00
unary.h	Add some internal GPU apis (#1177)	2024-06-04 09:24:26 -07:00
utils.cpp	Move some dims utils to common (#2223)	2025-05-29 06:48:30 -07:00
utils.h	Improve metal elementwise kernels (#2247)	2025-06-06 11:37:40 -07:00