Hermann Stamm-Wilbrandt Hermann-SW
Hermann-SW
/ ecm.cpp
Created
October 9, 2026 21:18
After longer discussion with Gemini on Lenstra's ECM factoring method I got sample code that worked ...
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #include <iostream> | |
| #include <vector> | |
| #include <string> | |
| #include <stdexcept> | |
| #include <chrono> | |
| #include <gmpxx.h> | |
| #include <gmp.h> | |
| class FactorFoundException : public std::exception { | |
| public: |
Hermann-SW
/ ec_ipts.gp
Created
October 9, 2026 18:36
Script to test differences on how SageMath and PARI/GP determine integral points on elliptic curves
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| sage(cmd) = eval(externstr(Str("sage -q -c \"", cmd, "\""))[1]); | |
| ellintpoints(E) = { | |
| sage(Str("print([[int(P[0]), int(P[1])] for P in EllipticCurve(", | |
| E[1..5],").integral_points(both_signs=True)])")); | |
| } | |
| as=eval(getenv("as")); | |
| E=ellinit(as); | |
| print(" E[1..5]=",E[1..5]); |
Hermann-SW
/ integral_points_coefficients.gp
Created
October 6, 2026 22:19
demonstrate how to call sagemath E.integral_points() from PARI/GP
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| sage(cmd) = eval(externstr(Str("sage -q -c \"", cmd, "\""))[1]); | |
| ellintpoints(E) = { | |
| sage(Str("print([[int(P[0]), int(P[1])] for P in EllipticCurve(", | |
| E[1..5],").integral_points()])")); | |
| } | |
| xy=eval(getenv("xy")); | |
| [y1,x1]=xy; | |
| [x2,y2]=xy;x2*=-1; |
Hermann-SW
/ is_prime_u32.cpp
Created
September 20, 2026 08:50
100% deterministic Miller-Rabin primality test for N < 2^32
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #include <iostream> | |
| #include <cstdint> | |
| #include <gmpxx.h> | |
| #include <cassert> | |
| #include <omp.h> | |
| // Single-round Miller-Rabin test using GMP modular exponentiation | |
| inline bool miller_rabin_test(uint32_t n, uint32_t a, uint32_t d, int s) { | |
| mpz_class base(a), exp(d), mod(n), x; | |
Hermann-SW
/ build_graph.py
Last active
October 14, 2026 23:48
Latex labels for Graphviz (work in progress)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| This Python script became obsolete with this new repo: | |
| https://github.com/Hermann-SW/graphviz_latex_pipeline | |
| Because that repo's texdot.py compiles the LaTeX in each node or edge separately, with the real LaTeX. | |
| You can still access this gist's Python code by opening the file at earlier revisions. |
Hermann-SW
/ gfx900_multi_precision_bench.cpp
Last active
August 29, 2026 12:37
INT16 add and mul as well as FP16 fma benchmark for gfx900 GPUS
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| /* | |
| f=gfx900_multi_precision_bench | |
| hipcc -O3 --offload-arch=gfx900 $f.cpp -o $f | |
| */ | |
| #include <hip/hip_runtime.h> | |
| #include <hip/hip_fp16.h> | |
| #include <iostream> | |
| #include <iomanip> | |
| #include <vector> |
Hermann-SW
/ mi50_multi_precision_bench.cpp
Created
August 12, 2026 09:53
Multi GPU INT4/INT8/FP16 benchmark from long gemini session
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #include <hip/hip_runtime.h> | |
| #include <hip/hip_fp16.h> | |
| #include <iostream> | |
| #include <vector> | |
| #include <thread> | |
| #include <chrono> | |
| #include <iomanip> | |
| #include <atomic> | |
| #include <string> |
Hermann-SW
/ benchmark_fp8_ptx.cu
Created
August 2, 2026 20:02
Synthetic benchmark from long gemini session for >170 TFLOPS FP8
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #include <iostream> | |
| #include <cstdint> | |
| #include <cuda_runtime.h> | |
| #define CUDA_CHECK(status) \ | |
| do { \ | |
| cudaError_t err = (status); \ | |
| if (err != cudaSuccess) { \ | |
| std::cerr << "[CUDA Error] " << cudaGetErrorString(err) \ | |
| << " (" << err << ") at line " << __LINE__ << std::endl; \ |
Hermann-SW
/ benchmark_fp16.cu
Created
August 1, 2026 22:01
Demonstrate 77 TFLOPS FP16 (__half) on NVIDIA RTX 5060 GPU
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #include <iostream> | |
| #include <vector> | |
| #include <cuda_runtime.h> | |
| #include <cublas_v2.h> | |
| #define CUDA_CHECK(status) \ | |
| if (status != cudaSuccess) { \ | |
| std::cerr << "CUDA Error: " << cudaGetErrorString(status) \ | |
| << " at line " << __LINE__ << std::endl; \ | |
| exit(EXIT_FAILURE); \ |
Hermann-SW
/ AVX2.vsqrtpd.cpp
Created
June 26, 2026 20:23
Demonstrate maximal "double sqrt" GFLOPS performance for AVX2 CPUs
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| /* | |
| f=AVX2.vsqrtpd | |
| g++ -O3 -fopenmp -Wall -Wextra -pedantic $f.cpp -o $f | |
| cpplint --filter=-legal/copyright $f.cpp | |
| cppcheck --enable=all --suppress=missingIncludeSystem $f.cpp --check-config | |
| echo off | sudo tee /sys/devices/system/cpu/smt/control | |
| echo 0 | sudo tee /proc/sys/kernel/perf_event_paranoid | |
| perf stat -a -e cycles,instructions,task-clock ./$f |
NewerOlder