tile-ai/tilelang

Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

Python★ 8,159+163 that day#6 on trendingD 43.8 health15% duplicated

Analyzed October 2, 2026 at 994b44e (main) with jscpd v5 in 2.5s.

D43.8/100

Project health505,778 lines of code (L)

Duplication29

15.2% in python, cpp, c-header, cpp-header, bash, cmake, perl

Dead code95

0.5%

Complexity43

61.1%

Most complex files

3rdparty/hip-headers/include/hip/amd_detail/hip_prof_str.h3032 cx
src/ascend/codegen/codegen_pto.cc1728 cx
src/cuda/codegen/codegen_cuda.cc1438 cx
src/tl_templates/cpp/half.hpp1061 cx
src/ascend/codegen/codegen_ascend.cc962 cx
src/cuda/codegen/codegen_cutedsl.cc776 cx
src/transform/inject_pipeline.cc684 cx
src/rocm/codegen/codegen_hip.cc612 cx
src/cuda/transform/materialize_ws_schedule.cc530 cx
src/ascend/transform/insert_sync.cc494 cx

Dead code 0.52% unused · 104 findings

maint/scripts/pytest_cuda_scheduler.pyunused-file
tilelang/language/tir/ir.pyiunused-file
docs/conf.pyunused-file
maint/layout_inference/cases/broadcast_read.pyunused-file
maint/layout_inference/cases/reducer_scalar_candidates.pyunused-file
maint/layout_inference/cases/offset_region_copy.pyunused-file
maint/layout_inference/cases/reduce_broadcast.pyunused-file
maint/layout_inference/cases/mixed_dtype_chain.pyunused-file
maint/layout_inference/cases/elementwise_copy.pyunused-file
maint/layout_inference/cases/transposed_store.pyunused-file

1,897files

531,916lines

4,503,869tokens

5,837clones

79,786duplicated lines (15%)

794,040duplicated tokens (17.63%)

By format

Format	Files	Lines	Clones	Duplicated lines	Duplication
python	1,254	283,243	3,716	50,071	17.68%
c-header	207	80,969	1,052	11,205	13.84%
cpp	224	133,195	923	15,923	11.95%
cpp-header	4	8,138	78	706	8.68%
json	11	1,966	20	775	39.42%
yaml	19	2,043	19	330	16.15%
markdown	91	15,981	13	265	1.66%
bash	42	2,320	5	46	1.98%
txt	12	1,942	5	415	21.37%
markup	4	501	4	35	6.99%

Largest clones

1010 lines · 8,914 tokens cppsrc/ascend/transform/thread_storage_sync.cc:582–1591⇆src/transform/thread_storage_sync.cc:583–1592
670 lines · 6,121 tokens cppsrc/ascend/transform/layout_inference.cc:51–720⇆src/transform/layout_inference/layout_inference.cc:46–715
640 lines · 6,084 tokens cppsrc/ascend/transform/lower_tile_op.cc:515–1154⇆src/transform/lower_tile_op.cc:457–1096
495 lines · 4,279 tokens cppsrc/ascend/transform/thread_storage_sync.cc:61–555⇆src/transform/thread_storage_sync.cc:58–552
364 lines · 3,464 tokens cppsrc/ascend/transform/thread_storage_sync.cc:193–556⇆src/transform/thread_storage_sync.cc:190–553
287 lines · 1,807 tokens cppsrc/cuda/transform/ptx_async_copy_injector.cc:389–675⇆src/rocm/transform/async_copy_injector.cc:391–677
24 lines · 1,743 tokens c-header3rdparty/hip-headers/include/hip/hip_runtime_api.h:4102–4125⇆3rdparty/hip-headers/include/hip/hip_runtime_api.h:4141–4164
182 lines · 1,727 tokens txtTHIRDPARTYNOTICES.txt:5–186⇆THIRDPARTYNOTICES.txt:210–391
182 lines · 1,727 tokens txtTHIRDPARTYNOTICES.txt:5–186⇆THIRDPARTYNOTICES.txt:415–596
144 lines · 1,606 tokens pythonexamples/deepseek_nsa/benchmark/benchmark_nsa_fwd.py:306–449⇆examples/deepseek_nsa/reference.py:9–152

Trending appearances

Day	Rank	Stars	Files	Lines	Clones	Duplication	Health	Commit
Oct 2, 2026	#6	8,159 (+163)	1,897	531,916	5,837	15%	D 43.8	`994b44e`

Want this for your own project? Install jscpd and run jscpd .