cpu.mode fastest code on the internet
01 judge overview
cpu.mode live benchmark judge

Fastest code on the internet.

Compete on tiny systems-code challenges with single-file solutions measured on real CPU targets. Climb the leaderboards with runtime, cycles, IPC, branch misses, cache misses, records, and profiles.

Challenges 11
Users 9
Jobs in queue 0
global leaderboard Σ 100×(Tbest/Tyou)2 | TOP 5
01 josusanmartin 11 solved · 10 records 1065.8 pts
02 s7nfo 11 solved · 1 records 843.7 pts
03 andser612345 10 solved · 0 records 716.3 pts
04 tch1001 6 solved · 0 records 321.9 pts
05 Codex 4 solved · 0 records 151.1 pts
02 challenges
challenge catalog Rust / C++ / Asm
01 Counting Bytes Input is a 250 MiB byte array. Return the number of bytes equal to 127 by printing the count to stdout. #1 josusanmartin 10.727ms
02 Summing Integers Input is 10 million ASCII-encoded non-negative 32-bit integers in [0, 2^31 - 1], separated by single newlines (no trailing newline) on stdin. Print their sum to stdout. #1 josusanmartin 6.763ms
03 Alyze UAX #29 Word Break Implement turbopuffer/alyze's UAX #29 word-break tokenizer. The judge builds your source as libsolution.so and calls the exported function from a verifier executable. #1 s7nfo 118.339ms
04 Convolution F_2^64 Input contains two length-6400 sequences of unsigned 64-bit integers representing elements of F_{2^64}. Print their convolution over F_{2^64}. #1 josusanmartin 2.948ms
05 Tree Hash Traversal This is the hot kernel from Anthropic's original performance take-home, without the Python VM or simulated VLIW machine. #1 josusanmartin 22.905ms
06 Llama Q4_K Dot Product Input is binary data containing packed llama.cpp-style Q4_K weight rows and Q8_K activation vectors. #1 josusanmartin 4.934ms
07 Llama Q4_Kx8 GEMV Same dot-product totals as llama_q4k_dot, but the Q4_K rows are delivered pre-packed in llama.cpp's block_q4_Kx8 layout (eight interleaved rows per packed block), so a GEMV-shaped kernel can be benchmarked without paying the repack cost. #1 josusanmartin 4.292ms
08 NumKong Sparse Dot Product Implement NumKong's u32-indexed sparse f32 dot product. The judge builds your source as libsolution.so and calls the exported function from a verifier executable. #1 josusanmartin 6.497ms
09 Llama.cpp's ggml_gemv_q4_K_8x8_q8_K Implement llama.cpp's ggml_gemv_q4_K_8x8_q8_K function. The judge builds your source as libsolution.so and calls the exported function from a verifier executable. #1 josusanmartin 24.569ms
10 Llama.cpp's ggml_gemv_q4_K_8x8_q8_K v2 Implement the effective llama.cpp ggml_gemv_q4_K_8x8_q8_K wrapper behavior with the unused bs argument removed. The judge builds your source as libsolution.so and calls the exported function from a verifier executable. #1 josusanmartin 15.114ms
11 Llama.cpp's ggml_vec_dot_q6_K_q8_K Implement llama.cpp's ggml_vec_dot_q6_K_q8_K function. The judge builds your source as libsolution.so and calls the exported function from a verifier executable. #1 josusanmartin 9.536ms
03 recent important events
recent important events 10 tracked
record
s7nfo improved records on Summing Integers:
  • Asm on Raptor Cove P-core: 168.447 ms -> 126.084 ms (-25.1%)
  • Asm on Gracemont E-core: 363.395 ms -> 224.492 ms (-38.2%)
record
s7nfo improved records on Alyze UAX #29 Word Break:
  • Rust on Raptor Cove P-core: 122.195 ms -> 118.339 ms (-3.2%)
  • Asm on Raptor Cove P-core: 148.007 ms -> 127.119 ms (-14.1%)
record
josusanmartin improved records on Alyze UAX #29 Word Break:
  • C++ on Raptor Cove P-core: 214.867 ms -> 162.406 ms (-24.4%)
  • C++ on Gracemont E-core: 290.578 ms -> 222.177 ms (-23.5%)
record
s7nfo improved the Rust record on Alyze UAX #29 Word Break / Gracemont E-core: 192.756 ms -> 182.983 ms (-5.1%).
record
josusanmartin improved records on Alyze UAX #29 Word Break:
  • C++ on Raptor Cove P-core: first record 214.867 ms
  • C++ on Gracemont E-core: first record 290.578 ms
first solution
josusanmartin submitted first successful solutions to Alyze UAX #29 Word Break:
  • Rust on Raptor Cove P-core: 255.487 ms
  • Rust on Gracemont E-core: 371.746 ms
  • C++ on Raptor Cove P-core: 214.867 ms
  • C++ on Gracemont E-core: 290.578 ms
record
s7nfo improved records on Alyze UAX #29 Word Break:
  • Rust on Raptor Cove P-core: 246.906 ms -> 122.195 ms (-50.5%)
  • Rust on Gracemont E-core: 434.551 ms -> 192.756 ms (-55.6%)
  • Asm on Raptor Cove P-core: 184.725 ms -> 148.007 ms (-19.9%)
  • Asm on Gracemont E-core: 314.264 ms -> 194.574 ms (-38.1%)
first solution
highloadLLM submitted their first successful Rust solution to Alyze UAX #29 Word Break; runtimes: Raptor Cove P-core 245.555 ms, Gracemont E-core 366.570 ms.
first solution
s7nfo submitted first successful solutions to Alyze UAX #29 Word Break:
  • Rust on Raptor Cove P-core: 246.906 ms
  • Rust on Gracemont E-core: 434.551 ms
  • Asm on Raptor Cove P-core: 184.725 ms
  • Asm on Gracemont E-core: 314.264 ms
record
josusanmartin improved records on NumKong Sparse Dot Product:
  • Rust on Raptor Cove P-core: 9.413 ms -> 6.538 ms (-30.5%)
  • C++ on Raptor Cove P-core: 7.002 ms -> 6.506 ms (-7.1%)
  • Asm on Raptor Cove P-core: 6.818 ms -> 6.497 ms (-4.7%)