docs: add teaching examples and video project
This commit is contained in:
parent
e93bc20b0a
commit
7a06f94577
42 changed files with 8022 additions and 0 deletions
1
show/results/C_outer_sum.json
Normal file
1
show/results/C_outer_sum.json
Normal file
|
|
@ -0,0 +1 @@
|
|||
{"seed_start":61692151016558,"seeds":1,"x0":46973,"z0":415028,"width":8193,"height":8193,"n":5,"candidate_count":67125249,"gpu":"NVIDIA GeForce RTX 3060 Laptop GPU","setup_ms":261.544059,"comparison_equal":true,"rows":[{"mode":3,"kernel_samples_ms":[2.719743967,4.548607826,2.719743967,2.71359992,3.421184063,2.719743967,2.721791983,4.546559811,2.71359992,2.714623928,2.717695951,2.719743967,2.716671944,5.061632156,2.717695951,2.718719959,2.71359992,2.715647936,2.71359992,4.462592125,2.715647936,2.719743967,2.718719959,2.718719959,2.714623928,3.991552114,4.080639839,2.715647936,2.716671944,2.718719959,2.714623928,3.131392002,4.841472149,2.718719959,2.717695951,2.71359992,2.718719959,2.718719959,5.118976116,2.717695951,2.718719959,3.597311974,2.717695951,2.714623928,4.768767834,2.353152037,2.357248068,4.742144108,2.61836791,2.350080013,2.343935966,2.343935966,2.352128029,2.34700799,2.619391918,2.369535923,2.367487907,2.363392115,4.854784012,2.362368107,2.362368107,4.595712185,2.362368107,2.361344099,2.367487907,2.361344099,2.365439892,2.360320091,3.052544117,2.360320091,2.360320091,2.371583939,4.817920208,2.376703978,2.370559931,4.264959812,2.379776001,2.385920048,2.380800009,2.371583939,2.370559931,2.370559931,2.872319937,2.38489604,2.379776001,4.811776161,2.378751993,2.367487907,2.360320091,2.362368107,3.404799938,3.628031969,6.178815842,2.3664639,2.361344099,2.349056005,2.349056005,2.349056005,4.595712185,2.374655962],"kernel_median_ms":2.714623928,"scan_samples_ms":[3.361799,5.427067,3.262892,3.256716,4.0131,3.125633,3.140041,5.201408,3.133867,3.08945,3.14145,3.247291,3.207966,5.791283,3.204174,3.179908,3.246966,3.235266,3.267225,5.118424,3.255958,3.1889,3.150117,3.118158,3.131592,4.524433,4.937291,3.1382,3.121191,3.147733,3.128991,3.577925,5.585233,3.1161,3.103642,3.121733,3.170592,3.147192,5.81685,3.104834,3.176983,4.392916,3.136574,3.098659,5.483508,2.83205,2.804316,5.437791,3.179041,2.733033,2.688617,2.784058,2.816017,2.7391,3.169725,2.728158,2.768133,2.930417,5.615133,2.786441,2.788933,5.239433,2.7404,2.761416,2.738233,2.7417,2.744516,2.758059,3.5204,2.721117,2.760225,2.75275,5.519799,2.753183,2.783083,4.988533,2.859675,2.929659,2.876033,2.840716,2.790558,2.781891,3.403725,3.063125,2.996175,5.555333,2.8769,2.736175,2.819375,2.763041,3.908559,4.207558,7.026717,2.722525,2.790125,2.696308,2.720684,2.699992,5.185483,2.718517],"scan_median_ms":3.127312},{"mode":4,"kernel_samples_ms":[1.602560043,1.604608059,1.602560043,1.598464012,3.100672007,1.602560043,1.602560043,1.597440004,1.598464012,1.597440004,3.857408047,1.598464012,1.597440004,1.602560043,1.602560043,1.603584051,3.83180809,2.126847982,1.598464012,1.598464012,1.602560043,1.602560043,3.572736025,1.602560043,1.602560043,1.602560043,1.602560043,1.597440004,3.282943964,1.602560043,1.605631948,1.602560043,1.603584051,1.602560043,2.043904066,2.509824038,1.602560043,1.602560043,1.606655955,1.602560043,1.597440004,2.599936008,1.598464012,1.602560043,1.598464012,1.469439983,1.392639995,1.388543963,1.389567971,1.384448051,1.619968057,2.686975956,1.387519956,1.387519956,2.667520046,1.398784041,1.397760034,1.39468801,1.393664002,1.393664002,1.397760034,1.946624041,1.395712018,1.39468801,2.056191921,2.760704041,1.395712018,1.395712018,1.894400001,1.39468801,1.391615987,1.397760034,1.396736026,1.400832057,1.400832057,1.396736026,1.401855946,1.401855946,1.401855946,2.65625596,1.398784041,1.397760034,2.949120045,1.401855946,1.404927969,1.406975985,1.404927969,1.404927969,2.736128092,2.593791962,1.398784041,1.395712018,1.402879953,1.402879953,2.193408012,2.944000006,1.39468801,1.39468801,1.401855946,1.404927969],"kernel_median_ms":1.598464012,"scan_samples_ms":[2.081192,2.017816,2.022583,1.983042,3.886783,1.923133,1.953575,1.913058,1.916525,1.901358,4.444266,1.985209,1.931908,1.913384,1.983909,1.960941,4.444699,2.614408,1.977083,1.954767,1.934833,1.912733,4.119917,1.919666,1.9136,1.901574,1.923675,2.015975,3.7778,1.9786,1.969716,1.907533,1.9669,1.9149,2.430566,3.039184,1.923458,1.904283,1.922158,1.914358,1.891283,3.0251,1.904284,1.930391,1.994199,1.850008,1.762042,1.787716,1.692925,1.673858,2.019116,3.393867,1.702241,1.683825,3.373283,1.712966,1.703217,1.828233,1.725641,1.709392,1.690867,2.282366,1.692491,1.671692,2.446708,3.304491,1.735825,1.695308,2.4349,1.689999,1.697909,1.716975,1.776342,1.6809,1.711992,1.761392,1.805592,1.847625,1.826934,3.585725,1.699317,1.695308,3.960775,1.921508,1.832675,1.792158,1.675484,1.686641,3.621367,3.119025,1.729975,1.696934,1.825742,1.665517,2.606825,3.577491,1.65945,1.658258,1.75695,1.668333],"scan_median_ms":1.913492}],"hits":[[61692151016558,51069,419124]]}
|
||||
324
show/results/coordinate_range_diagnostics.json
Normal file
324
show/results/coordinate_range_diagnostics.json
Normal file
|
|
@ -0,0 +1,324 @@
|
|||
{
|
||||
"note": "地图规模变化的历史诊断实验,已移出视频/博客主线,不作为新的优化步骤。",
|
||||
"metadata": {
|
||||
"date": "2026-10-08T00:28:41.318982+08:00",
|
||||
"cpu": "AMD Ryzen 7 5800H with Radeon Graphics",
|
||||
"platform": "Linux-6.18.40.1-microsoft-standard-WSL2-x86_64-with-glibc2.39",
|
||||
"repeats": 5,
|
||||
"gpu": {
|
||||
"command": [
|
||||
"nvidia-smi",
|
||||
"--query-gpu=name,driver_version,temperature.gpu,power.draw,utilization.gpu",
|
||||
"--format=csv"
|
||||
],
|
||||
"process_ms": 78.23648804333061,
|
||||
"stdout": "name, driver_version, temperature.gpu, power.draw [W], utilization.gpu [%]\nNVIDIA GeForce RTX 3060 Laptop GPU, 596.49, 67, 19.65 W, 29 %\n",
|
||||
"stderr": ""
|
||||
},
|
||||
"nvcc": {
|
||||
"command": [
|
||||
"nvcc",
|
||||
"--version"
|
||||
],
|
||||
"process_ms": 31.78272402146831,
|
||||
"stdout": "nvcc: NVIDIA (R) Cuda compiler driver\nCopyright (c) 2005-2023 NVIDIA Corporation\nBuilt on Fri_Jan__6_16:45:21_PST_2023\nCuda compilation tools, release 12.0, V12.0.140\nBuild cuda_12.0.r12.0/compiler.32267302_0\n",
|
||||
"stderr": ""
|
||||
},
|
||||
"gxx": {
|
||||
"command": [
|
||||
"g++",
|
||||
"--version"
|
||||
],
|
||||
"process_ms": 7.172641053330153,
|
||||
"stdout": "g++ (Ubuntu 13.3.0-6ubuntu2~24.04.1) 13.3.0\nCopyright (C) 2023 Free Software Foundation, Inc.\nThis is free software; see the source for copying conditions. There is NO\nwarranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.\n\n",
|
||||
"stderr": ""
|
||||
},
|
||||
"source_sha256": {
|
||||
"01_cpu.cpp": "b7fc5d25b32050bd3defdb3934e6bb4f1dd8b5d83d529bef8b8a90d719d17e8b",
|
||||
"08_seed_cpu.cpp": "b9722cc52e46eb720fb78ea1d3f0531249cf656d274771fd8c2bad9f06f27800",
|
||||
"07_residue.cu": "873bea97faec42ce87620ea8b6bea3ffdb329ba2cf7924ab2d11719a91347b38",
|
||||
"08_seed_cuda.cu": "e4e95df388e572c21fed0e87b81299265ed66221f7d37b90d5c8feb7839a1ed7",
|
||||
"08_upper_compare.cu": "f20dc272ebc821230c83d22ca5c9819e8b658b1b994025b2c31b1928f067335f",
|
||||
"cuda_steps.cu": "b81d7c85f96c1e1f36fa6cb6907e17f62955606821e86959b038095e10f4957a",
|
||||
"02_cuda_seed.cuh": "1f6a8bf1d780f569c1a685c67edd8242db9d658fb919247b0197c3b450854455",
|
||||
"03_cuda_position.cuh": "69ceeb76a9954b073826a613fe9b343bc3cbb106f47546b3af2bd00df589e34c",
|
||||
"04_cuda_outer_sum.cuh": "a316d3a4845351be996bee4930d817aa9d37edec05cbcf8e1869c086533a477d",
|
||||
"common.hpp": "686d1964fe2fd5cb17709d9c5de7cbfbf0530a7a5622604a138a65194f100a13",
|
||||
"../research/slime_solver_core.hpp": "feb1200518716b4d796fb60f60a83b6b798155bbd4e795531793181a5c7f9eba"
|
||||
},
|
||||
"mapping_updated_at": "2026-10-08T23:15:42.590910+08:00",
|
||||
"mapping_repeats": 5,
|
||||
"mapping_source_sha256": {
|
||||
"01_cpu.cpp": "b7fc5d25b32050bd3defdb3934e6bb4f1dd8b5d83d529bef8b8a90d719d17e8b",
|
||||
"cuda_steps.cu": "a5c639dafcdf581c35f4551195cf28e5ec82eac9b642631a6845fbfc6fa48cfb",
|
||||
"02_cuda_seed.cuh": "1f6a8bf1d780f569c1a685c67edd8242db9d658fb919247b0197c3b450854455",
|
||||
"03_cuda_position.cuh": "44f49a7db73e52ec87ac632a2cee2f7938a2241a356780e151b3ab0de5d9a506",
|
||||
"04_cuda_outer_sum.cuh": "a316d3a4845351be996bee4930d817aa9d37edec05cbcf8e1869c086533a477d"
|
||||
},
|
||||
"C_updated_at": "2026-10-08T23:58:18.383398+08:00",
|
||||
"verification_updated_at": "2026-10-08T23:58:18.383398+08:00",
|
||||
"verification_source_sha256": {
|
||||
"01_cpu.cpp": "b7fc5d25b32050bd3defdb3934e6bb4f1dd8b5d83d529bef8b8a90d719d17e8b",
|
||||
"08_seed_cpu.cpp": "b9722cc52e46eb720fb78ea1d3f0531249cf656d274771fd8c2bad9f06f27800",
|
||||
"07_residue.cu": "873bea97faec42ce87620ea8b6bea3ffdb329ba2cf7924ab2d11719a91347b38",
|
||||
"08_seed_cuda.cu": "e4e95df388e572c21fed0e87b81299265ed66221f7d37b90d5c8feb7839a1ed7",
|
||||
"08_upper_compare.cu": "f20dc272ebc821230c83d22ca5c9819e8b658b1b994025b2c31b1928f067335f",
|
||||
"cuda_steps.cu": "1015892b920383399368527e3c8c5620a004276c9db8fcb5c67188a00a2d3e7a",
|
||||
"02_cuda_seed.cuh": "1f6a8bf1d780f569c1a685c67edd8242db9d658fb919247b0197c3b450854455",
|
||||
"03_cuda_position.cuh": "82ce3adb0bca11dab7a48f75fdccbbb207dbffa43a0c2ad8b19ec0f741f2738c",
|
||||
"04_cuda_outer_sum.cuh": "a316d3a4845351be996bee4930d817aa9d37edec05cbcf8e1869c086533a477d",
|
||||
"common.hpp": "9d0814927d6905964c3288d20f502a7797800e3382795e6e7c2cbbfccea6da33",
|
||||
"../research/slime_solver_core.hpp": "feb1200518716b4d796fb60f60a83b6b798155bbd4e795531793181a5c7f9eba"
|
||||
},
|
||||
"C_source_sha256": {
|
||||
"cuda_steps.cu": "1015892b920383399368527e3c8c5620a004276c9db8fcb5c67188a00a2d3e7a",
|
||||
"02_cuda_seed.cuh": "1f6a8bf1d780f569c1a685c67edd8242db9d658fb919247b0197c3b450854455",
|
||||
"03_cuda_position.cuh": "82ce3adb0bca11dab7a48f75fdccbbb207dbffa43a0c2ad8b19ec0f741f2738c",
|
||||
"04_cuda_outer_sum.cuh": "a316d3a4845351be996bee4930d817aa9d37edec05cbcf8e1869c086533a477d",
|
||||
"common.hpp": "9d0814927d6905964c3288d20f502a7797800e3382795e6e7c2cbbfccea6da33"
|
||||
},
|
||||
"verification_note": "Timing sequence ends at 04. Random properties moved into a theory chapter. All 13 correctness tests passed after removing the 05 timing branch; older phase measurements retain their original dates and hashes, C was remeasured with the current binary."
|
||||
},
|
||||
"range_sweep": [
|
||||
{
|
||||
"case": {
|
||||
"seed": 61692151016558,
|
||||
"seeds": 65536,
|
||||
"x0": 50813,
|
||||
"z0": 418868,
|
||||
"width": 513,
|
||||
"height": 513
|
||||
},
|
||||
"data": {
|
||||
"seed_start": 61692151016558,
|
||||
"seeds": 65536,
|
||||
"x0": 50813,
|
||||
"z0": 418868,
|
||||
"width": 513,
|
||||
"height": 513,
|
||||
"n": 5,
|
||||
"candidate_count": 17247043584,
|
||||
"gpu": "NVIDIA GeForce RTX 3060 Laptop GPU",
|
||||
"setup_ms": 214.74635,
|
||||
"comparison_equal": true,
|
||||
"rows": [
|
||||
{
|
||||
"mode": 2,
|
||||
"kernel_samples_ms": [
|
||||
566.0969238
|
||||
],
|
||||
"kernel_median_ms": 566.0969238,
|
||||
"scan_samples_ms": [
|
||||
613.641925
|
||||
],
|
||||
"scan_median_ms": 613.641925
|
||||
},
|
||||
{
|
||||
"mode": 3,
|
||||
"kernel_samples_ms": [
|
||||
310.4040833
|
||||
],
|
||||
"kernel_median_ms": 310.4040833,
|
||||
"scan_samples_ms": [
|
||||
336.619617
|
||||
],
|
||||
"scan_median_ms": 336.619617
|
||||
}
|
||||
],
|
||||
"hits": [
|
||||
[
|
||||
61692151016558,
|
||||
51069,
|
||||
419124
|
||||
]
|
||||
]
|
||||
},
|
||||
"raw": {
|
||||
"command": [
|
||||
"/mnt/d/dev/slime/show/bin/cuda_steps",
|
||||
"--seed",
|
||||
"61692151016558",
|
||||
"--seeds",
|
||||
"65536",
|
||||
"--x0",
|
||||
"50813",
|
||||
"--z0",
|
||||
"418868",
|
||||
"--width",
|
||||
"513",
|
||||
"--height",
|
||||
"513",
|
||||
"-n",
|
||||
"5",
|
||||
"--repeats",
|
||||
"1",
|
||||
"--modes",
|
||||
"2,3"
|
||||
],
|
||||
"process_ms": 2072.731592000082,
|
||||
"stdout": "{\"seed_start\":61692151016558,\"seeds\":65536,\"x0\":50813,\"z0\":418868,\"width\":513,\"height\":513,\"n\":5,\"candidate_count\":17247043584,\"gpu\":\"NVIDIA GeForce RTX 3060 Laptop GPU\",\"setup_ms\":214.74635,\"comparison_equal\":true,\"rows\":[{\"mode\":2,\"kernel_samples_ms\":[566.0969238],\"kernel_median_ms\":566.0969238,\"scan_samples_ms\":[613.641925],\"scan_median_ms\":613.641925},{\"mode\":3,\"kernel_samples_ms\":[310.4040833],\"kernel_median_ms\":310.4040833,\"scan_samples_ms\":[336.619617],\"scan_median_ms\":336.619617}],\"hits\":[[61692151016558,51069,419124]]}\n",
|
||||
"stderr": ""
|
||||
}
|
||||
},
|
||||
{
|
||||
"case": {
|
||||
"seed": 61692151016558,
|
||||
"seeds": 65536,
|
||||
"x0": 50557,
|
||||
"z0": 418612,
|
||||
"width": 1025,
|
||||
"height": 1025
|
||||
},
|
||||
"data": {
|
||||
"seed_start": 61692151016558,
|
||||
"seeds": 65536,
|
||||
"x0": 50557,
|
||||
"z0": 418612,
|
||||
"width": 1025,
|
||||
"height": 1025,
|
||||
"n": 5,
|
||||
"candidate_count": 68853760000,
|
||||
"gpu": "NVIDIA GeForce RTX 3060 Laptop GPU",
|
||||
"setup_ms": 229.882141,
|
||||
"comparison_equal": true,
|
||||
"rows": [
|
||||
{
|
||||
"mode": 2,
|
||||
"kernel_samples_ms": [
|
||||
2155.086914
|
||||
],
|
||||
"kernel_median_ms": 2155.086914,
|
||||
"scan_samples_ms": [
|
||||
2335.14515
|
||||
],
|
||||
"scan_median_ms": 2335.14515
|
||||
},
|
||||
{
|
||||
"mode": 3,
|
||||
"kernel_samples_ms": [
|
||||
1197.010986
|
||||
],
|
||||
"kernel_median_ms": 1197.010986,
|
||||
"scan_samples_ms": [
|
||||
1297.136859
|
||||
],
|
||||
"scan_median_ms": 1297.136859
|
||||
}
|
||||
],
|
||||
"hits": [
|
||||
[
|
||||
61692151016558,
|
||||
51069,
|
||||
419124
|
||||
]
|
||||
]
|
||||
},
|
||||
"raw": {
|
||||
"command": [
|
||||
"/mnt/d/dev/slime/show/bin/cuda_steps",
|
||||
"--seed",
|
||||
"61692151016558",
|
||||
"--seeds",
|
||||
"65536",
|
||||
"--x0",
|
||||
"50557",
|
||||
"--z0",
|
||||
"418612",
|
||||
"--width",
|
||||
"1025",
|
||||
"--height",
|
||||
"1025",
|
||||
"-n",
|
||||
"5",
|
||||
"--repeats",
|
||||
"1",
|
||||
"--modes",
|
||||
"2,3"
|
||||
],
|
||||
"process_ms": 7595.587693000198,
|
||||
"stdout": "{\"seed_start\":61692151016558,\"seeds\":65536,\"x0\":50557,\"z0\":418612,\"width\":1025,\"height\":1025,\"n\":5,\"candidate_count\":68853760000,\"gpu\":\"NVIDIA GeForce RTX 3060 Laptop GPU\",\"setup_ms\":229.882141,\"comparison_equal\":true,\"rows\":[{\"mode\":2,\"kernel_samples_ms\":[2155.086914],\"kernel_median_ms\":2155.086914,\"scan_samples_ms\":[2335.14515],\"scan_median_ms\":2335.14515},{\"mode\":3,\"kernel_samples_ms\":[1197.010986],\"kernel_median_ms\":1197.010986,\"scan_samples_ms\":[1297.136859],\"scan_median_ms\":1297.136859}],\"hits\":[[61692151016558,51069,419124]]}\n",
|
||||
"stderr": ""
|
||||
}
|
||||
},
|
||||
{
|
||||
"case": {
|
||||
"seed": 61692151016558,
|
||||
"seeds": 65536,
|
||||
"x0": 50045,
|
||||
"z0": 418100,
|
||||
"width": 2049,
|
||||
"height": 2049
|
||||
},
|
||||
"data": {
|
||||
"seed_start": 61692151016558,
|
||||
"seeds": 65536,
|
||||
"x0": 50045,
|
||||
"z0": 418100,
|
||||
"width": 2049,
|
||||
"height": 2049,
|
||||
"n": 5,
|
||||
"candidate_count": 275146407936,
|
||||
"gpu": "NVIDIA GeForce RTX 3060 Laptop GPU",
|
||||
"setup_ms": 218.339333,
|
||||
"comparison_equal": true,
|
||||
"rows": [
|
||||
{
|
||||
"mode": 2,
|
||||
"kernel_samples_ms": [
|
||||
8471.788086
|
||||
],
|
||||
"kernel_median_ms": 8471.788086,
|
||||
"scan_samples_ms": [
|
||||
9178.481975
|
||||
],
|
||||
"scan_median_ms": 9178.481975
|
||||
},
|
||||
{
|
||||
"mode": 3,
|
||||
"kernel_samples_ms": [
|
||||
4668.789551
|
||||
],
|
||||
"kernel_median_ms": 4668.789551,
|
||||
"scan_samples_ms": [
|
||||
5058.365918
|
||||
],
|
||||
"scan_median_ms": 5058.365918
|
||||
}
|
||||
],
|
||||
"hits": [
|
||||
[
|
||||
61692151016558,
|
||||
51069,
|
||||
419124
|
||||
]
|
||||
]
|
||||
},
|
||||
"raw": {
|
||||
"command": [
|
||||
"/mnt/d/dev/slime/show/bin/cuda_steps",
|
||||
"--seed",
|
||||
"61692151016558",
|
||||
"--seeds",
|
||||
"65536",
|
||||
"--x0",
|
||||
"50045",
|
||||
"--z0",
|
||||
"418100",
|
||||
"--width",
|
||||
"2049",
|
||||
"--height",
|
||||
"2049",
|
||||
"-n",
|
||||
"5",
|
||||
"--repeats",
|
||||
"1",
|
||||
"--modes",
|
||||
"2,3"
|
||||
],
|
||||
"process_ms": 28857.863240999905,
|
||||
"stdout": "{\"seed_start\":61692151016558,\"seeds\":65536,\"x0\":50045,\"z0\":418100,\"width\":2049,\"height\":2049,\"n\":5,\"candidate_count\":275146407936,\"gpu\":\"NVIDIA GeForce RTX 3060 Laptop GPU\",\"setup_ms\":218.339333,\"comparison_equal\":true,\"rows\":[{\"mode\":2,\"kernel_samples_ms\":[8471.788086],\"kernel_median_ms\":8471.788086,\"scan_samples_ms\":[9178.481975],\"scan_median_ms\":9178.481975},{\"mode\":3,\"kernel_samples_ms\":[4668.789551],\"kernel_median_ms\":4668.789551,\"scan_samples_ms\":[5058.365918],\"scan_median_ms\":5058.365918}],\"hits\":[[61692151016558,51069,419124]]}\n",
|
||||
"stderr": ""
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
1840
show/results/latest.json
Normal file
1840
show/results/latest.json
Normal file
File diff suppressed because it is too large
Load diff
232
show/results/mapping_comparison.json
Normal file
232
show/results/mapping_comparison.json
Normal file
|
|
@ -0,0 +1,232 @@
|
|||
{
|
||||
"date": "2026-10-08T01:12:22.661151+08:00",
|
||||
"repeats": 5,
|
||||
"note": "此前测量中保留下来的 02/03 样本;其他实验分支已删除。这些不是删除分支后的重新测量。",
|
||||
"cases": [
|
||||
{
|
||||
"case": {
|
||||
"name": "A:小地图、多 seed",
|
||||
"seed": 61692151016558,
|
||||
"seeds": 65536,
|
||||
"x0": 51053,
|
||||
"z0": 419108,
|
||||
"width": 33,
|
||||
"height": 33,
|
||||
"n": 5
|
||||
},
|
||||
"gpu": "NVIDIA GeForce RTX 3060 Laptop GPU",
|
||||
"rows": [
|
||||
{
|
||||
"mode": 2,
|
||||
"kernel_samples_ms": [
|
||||
1.719295979,
|
||||
1.72339201,
|
||||
1.474560022,
|
||||
1.470463991,
|
||||
1.47558403
|
||||
],
|
||||
"kernel_median_ms": 1.47558403,
|
||||
"scan_samples_ms": [
|
||||
2.067108,
|
||||
2.053242,
|
||||
1.774716,
|
||||
1.760308,
|
||||
1.777425
|
||||
],
|
||||
"scan_median_ms": 1.777425
|
||||
},
|
||||
{
|
||||
"mode": 3,
|
||||
"kernel_samples_ms": [
|
||||
25.17913628,
|
||||
27.14112091,
|
||||
23.79264069,
|
||||
21.79686356,
|
||||
21.46816063
|
||||
],
|
||||
"kernel_median_ms": 23.79264069,
|
||||
"scan_samples_ms": [
|
||||
27.637457,
|
||||
29.684524,
|
||||
26.08049,
|
||||
23.880349,
|
||||
23.558274
|
||||
],
|
||||
"scan_median_ms": 26.08049
|
||||
}
|
||||
],
|
||||
"hits": [
|
||||
[
|
||||
61692151016558,
|
||||
51069,
|
||||
419124
|
||||
]
|
||||
],
|
||||
"comparison_equal": true,
|
||||
"verification": {
|
||||
"cpu_case": {
|
||||
"name": "A:小地图、多 seed",
|
||||
"seed": 61692151016558,
|
||||
"seeds": 65536,
|
||||
"x0": 51053,
|
||||
"z0": 419108,
|
||||
"width": 33,
|
||||
"height": 33,
|
||||
"n": 5
|
||||
},
|
||||
"cpu_window_equal": true,
|
||||
"all_gpu_hits_exact": true
|
||||
}
|
||||
},
|
||||
{
|
||||
"case": {
|
||||
"name": "B:大地图、多 seed",
|
||||
"seed": 61692151016558,
|
||||
"seeds": 65536,
|
||||
"x0": 50557,
|
||||
"z0": 418612,
|
||||
"width": 1025,
|
||||
"height": 1025,
|
||||
"n": 5
|
||||
},
|
||||
"gpu": "NVIDIA GeForce RTX 3060 Laptop GPU",
|
||||
"rows": [
|
||||
{
|
||||
"mode": 2,
|
||||
"kernel_samples_ms": [
|
||||
1587.146729,
|
||||
1605.599243,
|
||||
1620.303833,
|
||||
1643.439087,
|
||||
1693.452271
|
||||
],
|
||||
"kernel_median_ms": 1620.303833,
|
||||
"scan_samples_ms": [
|
||||
1720.192965,
|
||||
1739.794472,
|
||||
1755.845789,
|
||||
1780.816188,
|
||||
1835.03301
|
||||
],
|
||||
"scan_median_ms": 1755.845789
|
||||
},
|
||||
{
|
||||
"mode": 3,
|
||||
"kernel_samples_ms": [
|
||||
1505.31897,
|
||||
1512.71521,
|
||||
1520.886841,
|
||||
1538.606079,
|
||||
1601.283081
|
||||
],
|
||||
"kernel_median_ms": 1520.886841,
|
||||
"scan_samples_ms": [
|
||||
1631.207428,
|
||||
1639.15866,
|
||||
1648.096918,
|
||||
1667.257617,
|
||||
1735.300914
|
||||
],
|
||||
"scan_median_ms": 1648.096918
|
||||
}
|
||||
],
|
||||
"hits": [
|
||||
[
|
||||
61692151016558,
|
||||
51069,
|
||||
419124
|
||||
]
|
||||
],
|
||||
"comparison_equal": true,
|
||||
"verification": {
|
||||
"cpu_case": {
|
||||
"name": "B:大地图、多 seed",
|
||||
"seed": 61692151016558,
|
||||
"seeds": 65536,
|
||||
"x0": 51053,
|
||||
"z0": 419108,
|
||||
"width": 33,
|
||||
"height": 33,
|
||||
"n": 5
|
||||
},
|
||||
"cpu_window_equal": true,
|
||||
"all_gpu_hits_exact": true
|
||||
}
|
||||
},
|
||||
{
|
||||
"case": {
|
||||
"name": "D:同一大地图、少 seed",
|
||||
"seed": 61692151016558,
|
||||
"seeds": 256,
|
||||
"x0": 50557,
|
||||
"z0": 418612,
|
||||
"width": 1025,
|
||||
"height": 1025,
|
||||
"n": 5
|
||||
},
|
||||
"gpu": "NVIDIA GeForce RTX 3060 Laptop GPU",
|
||||
"rows": [
|
||||
{
|
||||
"mode": 2,
|
||||
"kernel_samples_ms": [
|
||||
354.4719238,
|
||||
357.1487122,
|
||||
355.1600647,
|
||||
355.5502625,
|
||||
352.5959778
|
||||
],
|
||||
"kernel_median_ms": 355.1600647,
|
||||
"scan_samples_ms": [
|
||||
384.401641,
|
||||
387.353291,
|
||||
385.320633,
|
||||
385.6751,
|
||||
382.439508
|
||||
],
|
||||
"scan_median_ms": 385.320633
|
||||
},
|
||||
{
|
||||
"mode": 3,
|
||||
"kernel_samples_ms": [
|
||||
6.311935902,
|
||||
5.736447811,
|
||||
5.041152,
|
||||
5.049344063,
|
||||
5.649407864
|
||||
],
|
||||
"kernel_median_ms": 5.649407864,
|
||||
"scan_samples_ms": [
|
||||
7.155417,
|
||||
6.451358,
|
||||
5.790092,
|
||||
5.803958,
|
||||
6.47205
|
||||
],
|
||||
"scan_median_ms": 6.451358
|
||||
}
|
||||
],
|
||||
"hits": [
|
||||
[
|
||||
61692151016558,
|
||||
51069,
|
||||
419124
|
||||
]
|
||||
],
|
||||
"comparison_equal": true,
|
||||
"verification": {
|
||||
"cpu_case": {
|
||||
"name": "D:同一大地图、少 seed",
|
||||
"seed": 61692151016558,
|
||||
"seeds": 256,
|
||||
"x0": 51053,
|
||||
"z0": 419108,
|
||||
"width": 33,
|
||||
"height": 33,
|
||||
"n": 5
|
||||
},
|
||||
"cpu_window_equal": true,
|
||||
"all_gpu_hits_exact": true
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
704
show/results/mapping_diagnostics.json
Normal file
704
show/results/mapping_diagnostics.json
Normal file
|
|
@ -0,0 +1,704 @@
|
|||
{
|
||||
"metadata": {
|
||||
"date": "2026-10-07T22:59:59.732843+08:00",
|
||||
"cpu": "AMD Ryzen 7 5800H with Radeon Graphics",
|
||||
"platform": "Linux-6.18.40.1-microsoft-standard-WSL2-x86_64-with-glibc2.39",
|
||||
"repeats": 5,
|
||||
"gpu": {
|
||||
"command": [
|
||||
"nvidia-smi",
|
||||
"--query-gpu=name,driver_version,temperature.gpu,power.draw,utilization.gpu",
|
||||
"--format=csv"
|
||||
],
|
||||
"process_ms": 78.16004200140014,
|
||||
"stdout": "name, driver_version, temperature.gpu, power.draw [W], utilization.gpu [%]\nNVIDIA GeForce RTX 3060 Laptop GPU, 596.49, 63, 27.45 W, 21 %\n",
|
||||
"stderr": ""
|
||||
},
|
||||
"nvcc": {
|
||||
"command": [
|
||||
"nvcc",
|
||||
"--version"
|
||||
],
|
||||
"process_ms": 3.6383759579621255,
|
||||
"stdout": "nvcc: NVIDIA (R) Cuda compiler driver\nCopyright (c) 2005-2023 NVIDIA Corporation\nBuilt on Fri_Jan__6_16:45:21_PST_2023\nCuda compilation tools, release 12.0, V12.0.140\nBuild cuda_12.0.r12.0/compiler.32267302_0\n",
|
||||
"stderr": ""
|
||||
},
|
||||
"gxx": {
|
||||
"command": [
|
||||
"g++",
|
||||
"--version"
|
||||
],
|
||||
"process_ms": 1.5936919953674078,
|
||||
"stdout": "g++ (Ubuntu 13.3.0-6ubuntu2~24.04.1) 13.3.0\nCopyright (C) 2023 Free Software Foundation, Inc.\nThis is free software; see the source for copying conditions. There is NO\nwarranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.\n\n",
|
||||
"stderr": ""
|
||||
},
|
||||
"source_sha256": {
|
||||
"01_cpu.cpp": "b7fc5d25b32050bd3defdb3934e6bb4f1dd8b5d83d529bef8b8a90d719d17e8b",
|
||||
"08_seed_cpu.cpp": "b9722cc52e46eb720fb78ea1d3f0531249cf656d274771fd8c2bad9f06f27800",
|
||||
"07_residue.cu": "873bea97faec42ce87620ea8b6bea3ffdb329ba2cf7924ab2d11719a91347b38",
|
||||
"08_seed_cuda.cu": "e4e95df388e572c21fed0e87b81299265ed66221f7d37b90d5c8feb7839a1ed7",
|
||||
"08_upper_compare.cu": "f20dc272ebc821230c83d22ca5c9819e8b658b1b994025b2c31b1928f067335f",
|
||||
"cuda_steps.cu": "99a224471d68bf5f1404c4c391eda054f50757194589d9ddedccded652f14f65",
|
||||
"02_cuda_seed.cuh": "1f6a8bf1d780f569c1a685c67edd8242db9d658fb919247b0197c3b450854455",
|
||||
"03_cuda_position.cuh": "de7adcf92ddc0354b809eb65a177099f6f512f2fa00d28ba9e92c28a276d7fa3",
|
||||
"04_cuda_outer_sum.cuh": "6ef956bc59750bd4a900b1b38aedf7b188d869f3c51d13559b771529daec8255",
|
||||
"common.hpp": "50cb3915578826b7ea4edb2ceb79c5253dea53ee2365d7c3d393aab625d236d0",
|
||||
"../research/slime_solver_core.hpp": "feb1200518716b4d796fb60f60a83b6b798155bbd4e795531793181a5c7f9eba"
|
||||
}
|
||||
},
|
||||
"mapping": [
|
||||
{
|
||||
"case": {
|
||||
"name": "少 seed/大地图",
|
||||
"seed": 61692151016558,
|
||||
"seeds": 64,
|
||||
"x0": 50557,
|
||||
"z0": 418612,
|
||||
"width": 1025,
|
||||
"height": 1025,
|
||||
"modes": "all"
|
||||
},
|
||||
"cpu": {
|
||||
"seed_start": 61692151016558,
|
||||
"seeds": 64,
|
||||
"x0": 50557,
|
||||
"z0": 418612,
|
||||
"width": 1025,
|
||||
"height": 1025,
|
||||
"n": 5,
|
||||
"candidate_count": 67240000,
|
||||
"mode": "01_cpu",
|
||||
"cpu_threads": 16,
|
||||
"samples_ms": [
|
||||
68.250787,
|
||||
65.500419,
|
||||
70.745813,
|
||||
66.927279,
|
||||
68.617713
|
||||
],
|
||||
"median_ms": 68.250787,
|
||||
"hits": [
|
||||
[
|
||||
61692151016558,
|
||||
51069,
|
||||
419124
|
||||
]
|
||||
]
|
||||
},
|
||||
"gpu": {
|
||||
"seed_start": 61692151016558,
|
||||
"seeds": 64,
|
||||
"x0": 50557,
|
||||
"z0": 418612,
|
||||
"width": 1025,
|
||||
"height": 1025,
|
||||
"n": 5,
|
||||
"candidate_count": 67240000,
|
||||
"gpu": "NVIDIA GeForce RTX 3060 Laptop GPU",
|
||||
"setup_ms": 245.809413,
|
||||
"comparison_equal": true,
|
||||
"rows": [
|
||||
{
|
||||
"mode": 2,
|
||||
"kernel_samples_ms": [
|
||||
315.2680969,
|
||||
314.944519,
|
||||
314.2410278,
|
||||
315.0305176,
|
||||
330.1017456
|
||||
],
|
||||
"kernel_median_ms": 315.0305176,
|
||||
"scan_samples_ms": [
|
||||
341.894404,
|
||||
341.50397,
|
||||
340.940854,
|
||||
341.613496,
|
||||
358.166944
|
||||
],
|
||||
"scan_median_ms": 341.613496
|
||||
},
|
||||
{
|
||||
"mode": 3,
|
||||
"kernel_samples_ms": [
|
||||
1.258496046,
|
||||
1.264639974,
|
||||
1.737728,
|
||||
1.259520054,
|
||||
3.163136005
|
||||
],
|
||||
"kernel_median_ms": 1.264639974,
|
||||
"scan_samples_ms": [
|
||||
1.557401,
|
||||
1.578742,
|
||||
2.176959,
|
||||
1.588709,
|
||||
3.73826
|
||||
],
|
||||
"scan_median_ms": 1.588709
|
||||
},
|
||||
{
|
||||
"mode": 31,
|
||||
"kernel_samples_ms": [
|
||||
1.898496032,
|
||||
2.692095995,
|
||||
1.894400001,
|
||||
1.893375993,
|
||||
1.894400001
|
||||
],
|
||||
"kernel_median_ms": 1.894400001,
|
||||
"scan_samples_ms": [
|
||||
2.214659,
|
||||
3.094326,
|
||||
2.320609,
|
||||
2.252793,
|
||||
2.351051
|
||||
],
|
||||
"scan_median_ms": 2.320609
|
||||
},
|
||||
{
|
||||
"mode": 4,
|
||||
"kernel_samples_ms": [
|
||||
1.445888042,
|
||||
1.441792011,
|
||||
1.444864035,
|
||||
1.696768045,
|
||||
1.445888042
|
||||
],
|
||||
"kernel_median_ms": 1.445888042,
|
||||
"scan_samples_ms": [
|
||||
1.714485,
|
||||
1.733875,
|
||||
1.761284,
|
||||
2.12366,
|
||||
1.765184
|
||||
],
|
||||
"scan_median_ms": 1.761284
|
||||
},
|
||||
{
|
||||
"mode": 5,
|
||||
"kernel_samples_ms": [
|
||||
1.888255954,
|
||||
1.883136034,
|
||||
1.891327977,
|
||||
1.888255954,
|
||||
2.775039911
|
||||
],
|
||||
"kernel_median_ms": 1.888255954,
|
||||
"scan_samples_ms": [
|
||||
2.186709,
|
||||
2.202851,
|
||||
2.223868,
|
||||
2.227226,
|
||||
3.193885
|
||||
],
|
||||
"scan_median_ms": 2.223868
|
||||
},
|
||||
{
|
||||
"mode": 6,
|
||||
"kernel_samples_ms": [
|
||||
3.779583931,
|
||||
3.779583931,
|
||||
4.055039883,
|
||||
3.786751986,
|
||||
4.895775795
|
||||
],
|
||||
"kernel_median_ms": 3.786751986,
|
||||
"scan_samples_ms": [
|
||||
4.419027,
|
||||
4.305927,
|
||||
4.690511,
|
||||
4.285452,
|
||||
5.657277
|
||||
],
|
||||
"scan_median_ms": 4.419027
|
||||
}
|
||||
],
|
||||
"hits": [
|
||||
[
|
||||
61692151016558,
|
||||
51069,
|
||||
419124
|
||||
]
|
||||
]
|
||||
},
|
||||
"raw": [
|
||||
{
|
||||
"command": [
|
||||
"/mnt/d/dev/slime/show/bin/01_cpu",
|
||||
"--seed",
|
||||
"61692151016558",
|
||||
"--seeds",
|
||||
"64",
|
||||
"--x0",
|
||||
"50557",
|
||||
"--z0",
|
||||
"418612",
|
||||
"--width",
|
||||
"1025",
|
||||
"--height",
|
||||
"1025",
|
||||
"-n",
|
||||
"5",
|
||||
"--repeats",
|
||||
"5",
|
||||
"--cpu-threads",
|
||||
"16"
|
||||
],
|
||||
"process_ms": 411.2323169829324,
|
||||
"stdout": "{\"seed_start\":61692151016558,\"seeds\":64,\"x0\":50557,\"z0\":418612,\"width\":1025,\"height\":1025,\"n\":5,\"candidate_count\":67240000,\"mode\":\"01_cpu\",\"cpu_threads\":16,\"samples_ms\":[68.250787,65.500419,70.745813,66.927279,68.617713],\"median_ms\":68.250787,\"hits\":[[61692151016558,51069,419124]]}\n",
|
||||
"stderr": ""
|
||||
},
|
||||
{
|
||||
"command": [
|
||||
"/mnt/d/dev/slime/show/bin/cuda_steps",
|
||||
"--seed",
|
||||
"61692151016558",
|
||||
"--seeds",
|
||||
"64",
|
||||
"--x0",
|
||||
"50557",
|
||||
"--z0",
|
||||
"418612",
|
||||
"--width",
|
||||
"1025",
|
||||
"--height",
|
||||
"1025",
|
||||
"-n",
|
||||
"5",
|
||||
"--repeats",
|
||||
"5",
|
||||
"--modes",
|
||||
"all"
|
||||
],
|
||||
"process_ms": 2509.6489019924775,
|
||||
"stdout": "{\"seed_start\":61692151016558,\"seeds\":64,\"x0\":50557,\"z0\":418612,\"width\":1025,\"height\":1025,\"n\":5,\"candidate_count\":67240000,\"gpu\":\"NVIDIA GeForce RTX 3060 Laptop GPU\",\"setup_ms\":245.809413,\"comparison_equal\":true,\"rows\":[{\"mode\":2,\"kernel_samples_ms\":[315.2680969,314.944519,314.2410278,315.0305176,330.1017456],\"kernel_median_ms\":315.0305176,\"scan_samples_ms\":[341.894404,341.50397,340.940854,341.613496,358.166944],\"scan_median_ms\":341.613496},{\"mode\":3,\"kernel_samples_ms\":[1.258496046,1.264639974,1.737728,1.259520054,3.163136005],\"kernel_median_ms\":1.264639974,\"scan_samples_ms\":[1.557401,1.578742,2.176959,1.588709,3.73826],\"scan_median_ms\":1.588709},{\"mode\":31,\"kernel_samples_ms\":[1.898496032,2.692095995,1.894400001,1.893375993,1.894400001],\"kernel_median_ms\":1.894400001,\"scan_samples_ms\":[2.214659,3.094326,2.320609,2.252793,2.351051],\"scan_median_ms\":2.320609},{\"mode\":4,\"kernel_samples_ms\":[1.445888042,1.441792011,1.444864035,1.696768045,1.445888042],\"kernel_median_ms\":1.445888042,\"scan_samples_ms\":[1.714485,1.733875,1.761284,2.12366,1.765184],\"scan_median_ms\":1.761284},{\"mode\":5,\"kernel_samples_ms\":[1.888255954,1.883136034,1.891327977,1.888255954,2.775039911],\"kernel_median_ms\":1.888255954,\"scan_samples_ms\":[2.186709,2.202851,2.223868,2.227226,3.193885],\"scan_median_ms\":2.223868},{\"mode\":6,\"kernel_samples_ms\":[3.779583931,3.779583931,4.055039883,3.786751986,4.895775795],\"kernel_median_ms\":3.786751986,\"scan_samples_ms\":[4.419027,4.305927,4.690511,4.285452,5.657277],\"scan_median_ms\":4.419027}],\"hits\":[[61692151016558,51069,419124]]}\n",
|
||||
"stderr": ""
|
||||
}
|
||||
],
|
||||
"equality": true
|
||||
},
|
||||
{
|
||||
"case": {
|
||||
"name": "多 seed/小地图",
|
||||
"seed": 61692151016558,
|
||||
"seeds": 65536,
|
||||
"x0": 51053,
|
||||
"z0": 419108,
|
||||
"width": 33,
|
||||
"height": 33,
|
||||
"modes": "all"
|
||||
},
|
||||
"cpu": {
|
||||
"seed_start": 61692151016558,
|
||||
"seeds": 65536,
|
||||
"x0": 51053,
|
||||
"z0": 419108,
|
||||
"width": 33,
|
||||
"height": 33,
|
||||
"n": 5,
|
||||
"candidate_count": 71368704,
|
||||
"mode": "01_cpu",
|
||||
"cpu_threads": 16,
|
||||
"samples_ms": [
|
||||
81.224901,
|
||||
73.117448,
|
||||
97.834792,
|
||||
108.934088,
|
||||
90.93493
|
||||
],
|
||||
"median_ms": 90.93493,
|
||||
"hits": [
|
||||
[
|
||||
61692151016558,
|
||||
51069,
|
||||
419124
|
||||
]
|
||||
]
|
||||
},
|
||||
"gpu": {
|
||||
"seed_start": 61692151016558,
|
||||
"seeds": 65536,
|
||||
"x0": 51053,
|
||||
"z0": 419108,
|
||||
"width": 33,
|
||||
"height": 33,
|
||||
"n": 5,
|
||||
"candidate_count": 71368704,
|
||||
"gpu": "NVIDIA GeForce RTX 3060 Laptop GPU",
|
||||
"setup_ms": 240.589803,
|
||||
"comparison_equal": true,
|
||||
"rows": [
|
||||
{
|
||||
"mode": 2,
|
||||
"kernel_samples_ms": [
|
||||
2.157567978,
|
||||
1.483775973,
|
||||
1.488896012,
|
||||
1.487872005,
|
||||
1.484799981
|
||||
],
|
||||
"kernel_median_ms": 1.487872005,
|
||||
"scan_samples_ms": [
|
||||
2.543776,
|
||||
1.868209,
|
||||
1.8044,
|
||||
1.923351,
|
||||
1.781325
|
||||
],
|
||||
"scan_median_ms": 1.868209
|
||||
},
|
||||
{
|
||||
"mode": 3,
|
||||
"kernel_samples_ms": [
|
||||
21.31967926,
|
||||
22.01600075,
|
||||
21.36166382,
|
||||
21.35961533,
|
||||
21.49785614
|
||||
],
|
||||
"kernel_median_ms": 21.36166382,
|
||||
"scan_samples_ms": [
|
||||
23.495235,
|
||||
24.324635,
|
||||
23.509535,
|
||||
23.510402,
|
||||
23.78871
|
||||
],
|
||||
"scan_median_ms": 23.510402
|
||||
},
|
||||
{
|
||||
"mode": 31,
|
||||
"kernel_samples_ms": [
|
||||
2.029567957,
|
||||
2.024447918,
|
||||
2.024447918,
|
||||
2.027519941,
|
||||
2.030591965
|
||||
],
|
||||
"kernel_median_ms": 2.027519941,
|
||||
"scan_samples_ms": [
|
||||
2.534134,
|
||||
2.450717,
|
||||
2.456026,
|
||||
2.422443,
|
||||
2.575627
|
||||
],
|
||||
"scan_median_ms": 2.456026
|
||||
},
|
||||
{
|
||||
"mode": 4,
|
||||
"kernel_samples_ms": [
|
||||
2.405375957,
|
||||
2.40435195,
|
||||
2.40435195,
|
||||
2.40435195,
|
||||
2.878463984
|
||||
],
|
||||
"kernel_median_ms": 2.40435195,
|
||||
"scan_samples_ms": [
|
||||
2.824468,
|
||||
2.812334,
|
||||
2.821326,
|
||||
2.880801,
|
||||
3.663077
|
||||
],
|
||||
"scan_median_ms": 2.824468
|
||||
},
|
||||
{
|
||||
"mode": 5,
|
||||
"kernel_samples_ms": [
|
||||
2.010112047,
|
||||
2.227231979,
|
||||
2.014208078,
|
||||
2.014208078,
|
||||
2.885632038
|
||||
],
|
||||
"kernel_median_ms": 2.014208078,
|
||||
"scan_samples_ms": [
|
||||
2.359826,
|
||||
2.74571,
|
||||
2.370009,
|
||||
2.579851,
|
||||
3.366243
|
||||
],
|
||||
"scan_median_ms": 2.579851
|
||||
},
|
||||
{
|
||||
"mode": 6,
|
||||
"kernel_samples_ms": [
|
||||
6.228991985,
|
||||
5.210175991,
|
||||
6.320127964,
|
||||
4.903935909,
|
||||
4.611072063
|
||||
],
|
||||
"kernel_median_ms": 5.210175991,
|
||||
"scan_samples_ms": [
|
||||
6.99162,
|
||||
5.999286,
|
||||
7.126278,
|
||||
5.851953,
|
||||
5.353186
|
||||
],
|
||||
"scan_median_ms": 5.999286
|
||||
}
|
||||
],
|
||||
"hits": [
|
||||
[
|
||||
61692151016558,
|
||||
51069,
|
||||
419124
|
||||
]
|
||||
]
|
||||
},
|
||||
"raw": [
|
||||
{
|
||||
"command": [
|
||||
"/mnt/d/dev/slime/show/bin/01_cpu",
|
||||
"--seed",
|
||||
"61692151016558",
|
||||
"--seeds",
|
||||
"65536",
|
||||
"--x0",
|
||||
"51053",
|
||||
"--z0",
|
||||
"419108",
|
||||
"--width",
|
||||
"33",
|
||||
"--height",
|
||||
"33",
|
||||
"-n",
|
||||
"5",
|
||||
"--repeats",
|
||||
"5",
|
||||
"--cpu-threads",
|
||||
"16"
|
||||
],
|
||||
"process_ms": 541.5888970019296,
|
||||
"stdout": "{\"seed_start\":61692151016558,\"seeds\":65536,\"x0\":51053,\"z0\":419108,\"width\":33,\"height\":33,\"n\":5,\"candidate_count\":71368704,\"mode\":\"01_cpu\",\"cpu_threads\":16,\"samples_ms\":[81.224901,73.117448,97.834792,108.934088,90.93493],\"median_ms\":90.93493,\"hits\":[[61692151016558,51069,419124]]}\n",
|
||||
"stderr": ""
|
||||
},
|
||||
{
|
||||
"command": [
|
||||
"/mnt/d/dev/slime/show/bin/cuda_steps",
|
||||
"--seed",
|
||||
"61692151016558",
|
||||
"--seeds",
|
||||
"65536",
|
||||
"--x0",
|
||||
"51053",
|
||||
"--z0",
|
||||
"419108",
|
||||
"--width",
|
||||
"33",
|
||||
"--height",
|
||||
"33",
|
||||
"-n",
|
||||
"5",
|
||||
"--repeats",
|
||||
"5",
|
||||
"--modes",
|
||||
"all"
|
||||
],
|
||||
"process_ms": 542.0670810271986,
|
||||
"stdout": "{\"seed_start\":61692151016558,\"seeds\":65536,\"x0\":51053,\"z0\":419108,\"width\":33,\"height\":33,\"n\":5,\"candidate_count\":71368704,\"gpu\":\"NVIDIA GeForce RTX 3060 Laptop GPU\",\"setup_ms\":240.589803,\"comparison_equal\":true,\"rows\":[{\"mode\":2,\"kernel_samples_ms\":[2.157567978,1.483775973,1.488896012,1.487872005,1.484799981],\"kernel_median_ms\":1.487872005,\"scan_samples_ms\":[2.543776,1.868209,1.8044,1.923351,1.781325],\"scan_median_ms\":1.868209},{\"mode\":3,\"kernel_samples_ms\":[21.31967926,22.01600075,21.36166382,21.35961533,21.49785614],\"kernel_median_ms\":21.36166382,\"scan_samples_ms\":[23.495235,24.324635,23.509535,23.510402,23.78871],\"scan_median_ms\":23.510402},{\"mode\":31,\"kernel_samples_ms\":[2.029567957,2.024447918,2.024447918,2.027519941,2.030591965],\"kernel_median_ms\":2.027519941,\"scan_samples_ms\":[2.534134,2.450717,2.456026,2.422443,2.575627],\"scan_median_ms\":2.456026},{\"mode\":4,\"kernel_samples_ms\":[2.405375957,2.40435195,2.40435195,2.40435195,2.878463984],\"kernel_median_ms\":2.40435195,\"scan_samples_ms\":[2.824468,2.812334,2.821326,2.880801,3.663077],\"scan_median_ms\":2.824468},{\"mode\":5,\"kernel_samples_ms\":[2.010112047,2.227231979,2.014208078,2.014208078,2.885632038],\"kernel_median_ms\":2.014208078,\"scan_samples_ms\":[2.359826,2.74571,2.370009,2.579851,3.366243],\"scan_median_ms\":2.579851},{\"mode\":6,\"kernel_samples_ms\":[6.228991985,5.210175991,6.320127964,4.903935909,4.611072063],\"kernel_median_ms\":5.210175991,\"scan_samples_ms\":[6.99162,5.999286,7.126278,5.851953,5.353186],\"scan_median_ms\":5.999286}],\"hits\":[[61692151016558,51069,419124]]}\n",
|
||||
"stderr": ""
|
||||
}
|
||||
],
|
||||
"equality": true
|
||||
},
|
||||
{
|
||||
"case": {
|
||||
"name": "固定 seed/大矩形",
|
||||
"seed": 61692151016558,
|
||||
"seeds": 1,
|
||||
"x0": 46973,
|
||||
"z0": 415028,
|
||||
"width": 8193,
|
||||
"height": 8193,
|
||||
"modes": "31,4,5,6"
|
||||
},
|
||||
"cpu": {
|
||||
"seed_start": 61692151016558,
|
||||
"seeds": 1,
|
||||
"x0": 46973,
|
||||
"z0": 415028,
|
||||
"width": 8193,
|
||||
"height": 8193,
|
||||
"n": 5,
|
||||
"candidate_count": 67125249,
|
||||
"mode": "01_cpu",
|
||||
"cpu_threads": 16,
|
||||
"samples_ms": [
|
||||
611.078369,
|
||||
917.563899,
|
||||
433.067884,
|
||||
427.50984,
|
||||
419.277371
|
||||
],
|
||||
"median_ms": 433.067884,
|
||||
"hits": [
|
||||
[
|
||||
61692151016558,
|
||||
51069,
|
||||
419124
|
||||
]
|
||||
]
|
||||
},
|
||||
"gpu": {
|
||||
"seed_start": 61692151016558,
|
||||
"seeds": 1,
|
||||
"x0": 46973,
|
||||
"z0": 415028,
|
||||
"width": 8193,
|
||||
"height": 8193,
|
||||
"n": 5,
|
||||
"candidate_count": 67125249,
|
||||
"gpu": "NVIDIA GeForce RTX 3060 Laptop GPU",
|
||||
"setup_ms": 224.834879,
|
||||
"comparison_equal": true,
|
||||
"rows": [
|
||||
{
|
||||
"mode": 31,
|
||||
"kernel_samples_ms": [
|
||||
2.184191942,
|
||||
2.183167934,
|
||||
2.189311981,
|
||||
2.189311981,
|
||||
2.188287973
|
||||
],
|
||||
"kernel_median_ms": 2.188287973,
|
||||
"scan_samples_ms": [
|
||||
2.579201,
|
||||
2.564684,
|
||||
2.605201,
|
||||
2.653518,
|
||||
2.550926
|
||||
],
|
||||
"scan_median_ms": 2.579201
|
||||
},
|
||||
{
|
||||
"mode": 4,
|
||||
"kernel_samples_ms": [
|
||||
1.633280039,
|
||||
1.633280039,
|
||||
1.629184008,
|
||||
2.458623886,
|
||||
1.633280039
|
||||
],
|
||||
"kernel_median_ms": 1.633280039,
|
||||
"scan_samples_ms": [
|
||||
1.936459,
|
||||
1.978817,
|
||||
1.943284,
|
||||
2.986426,
|
||||
1.947401
|
||||
],
|
||||
"scan_median_ms": 1.947401
|
||||
},
|
||||
{
|
||||
"mode": 5,
|
||||
"kernel_samples_ms": [
|
||||
2.425856113,
|
||||
2.171904087,
|
||||
2.168832064,
|
||||
2.169856071,
|
||||
2.176000118
|
||||
],
|
||||
"kernel_median_ms": 2.171904087,
|
||||
"scan_samples_ms": [
|
||||
2.821001,
|
||||
2.525468,
|
||||
2.639868,
|
||||
2.538793,
|
||||
2.597401
|
||||
],
|
||||
"scan_median_ms": 2.597401
|
||||
},
|
||||
{
|
||||
"mode": 6,
|
||||
"kernel_samples_ms": [
|
||||
5.011456013,
|
||||
4.367360115,
|
||||
5.564415932,
|
||||
4.3704319,
|
||||
4.3704319
|
||||
],
|
||||
"kernel_median_ms": 4.3704319,
|
||||
"scan_samples_ms": [
|
||||
5.73907,
|
||||
4.964918,
|
||||
6.278786,
|
||||
5.042594,
|
||||
4.929169
|
||||
],
|
||||
"scan_median_ms": 5.042594
|
||||
}
|
||||
],
|
||||
"hits": [
|
||||
[
|
||||
61692151016558,
|
||||
51069,
|
||||
419124
|
||||
]
|
||||
]
|
||||
},
|
||||
"raw": [
|
||||
{
|
||||
"command": [
|
||||
"/mnt/d/dev/slime/show/bin/01_cpu",
|
||||
"--seed",
|
||||
"61692151016558",
|
||||
"--seeds",
|
||||
"1",
|
||||
"--x0",
|
||||
"46973",
|
||||
"--z0",
|
||||
"415028",
|
||||
"--width",
|
||||
"8193",
|
||||
"--height",
|
||||
"8193",
|
||||
"-n",
|
||||
"5",
|
||||
"--repeats",
|
||||
"5",
|
||||
"--cpu-threads",
|
||||
"16"
|
||||
],
|
||||
"process_ms": 3234.2790690017864,
|
||||
"stdout": "{\"seed_start\":61692151016558,\"seeds\":1,\"x0\":46973,\"z0\":415028,\"width\":8193,\"height\":8193,\"n\":5,\"candidate_count\":67125249,\"mode\":\"01_cpu\",\"cpu_threads\":16,\"samples_ms\":[611.078369,917.563899,433.067884,427.50984,419.277371],\"median_ms\":433.067884,\"hits\":[[61692151016558,51069,419124]]}\n",
|
||||
"stderr": ""
|
||||
},
|
||||
{
|
||||
"command": [
|
||||
"/mnt/d/dev/slime/show/bin/cuda_steps",
|
||||
"--seed",
|
||||
"61692151016558",
|
||||
"--seeds",
|
||||
"1",
|
||||
"--x0",
|
||||
"46973",
|
||||
"--z0",
|
||||
"415028",
|
||||
"--width",
|
||||
"8193",
|
||||
"--height",
|
||||
"8193",
|
||||
"-n",
|
||||
"5",
|
||||
"--repeats",
|
||||
"5",
|
||||
"--modes",
|
||||
"31,4,5,6"
|
||||
],
|
||||
"process_ms": 360.2725120144896,
|
||||
"stdout": "{\"seed_start\":61692151016558,\"seeds\":1,\"x0\":46973,\"z0\":415028,\"width\":8193,\"height\":8193,\"n\":5,\"candidate_count\":67125249,\"gpu\":\"NVIDIA GeForce RTX 3060 Laptop GPU\",\"setup_ms\":224.834879,\"comparison_equal\":true,\"rows\":[{\"mode\":31,\"kernel_samples_ms\":[2.184191942,2.183167934,2.189311981,2.189311981,2.188287973],\"kernel_median_ms\":2.188287973,\"scan_samples_ms\":[2.579201,2.564684,2.605201,2.653518,2.550926],\"scan_median_ms\":2.579201},{\"mode\":4,\"kernel_samples_ms\":[1.633280039,1.633280039,1.629184008,2.458623886,1.633280039],\"kernel_median_ms\":1.633280039,\"scan_samples_ms\":[1.936459,1.978817,1.943284,2.986426,1.947401],\"scan_median_ms\":1.947401},{\"mode\":5,\"kernel_samples_ms\":[2.425856113,2.171904087,2.168832064,2.169856071,2.176000118],\"kernel_median_ms\":2.171904087,\"scan_samples_ms\":[2.821001,2.525468,2.639868,2.538793,2.597401],\"scan_median_ms\":2.597401},{\"mode\":6,\"kernel_samples_ms\":[5.011456013,4.367360115,5.564415932,4.3704319,4.3704319],\"kernel_median_ms\":4.3704319,\"scan_samples_ms\":[5.73907,4.964918,6.278786,5.042594,4.929169],\"scan_median_ms\":5.042594}],\"hits\":[[61692151016558,51069,419124]]}\n",
|
||||
"stderr": ""
|
||||
}
|
||||
],
|
||||
"equality": true
|
||||
}
|
||||
],
|
||||
"note": "Original imbalance experiments; diagnostics only, not the main adjacent-version comparison."
|
||||
}
|
||||
13
show/results/mapping_progress.txt
Normal file
13
show/results/mapping_progress.txt
Normal file
|
|
@ -0,0 +1,13 @@
|
|||
测量线程映射:A:CPU → 按 seed 的 CUDA,65536 seed × 257×257
|
||||
CPU 对照完成;开始 CUDA 预热与计时
|
||||
完成该组完整命中对照
|
||||
测量线程映射:B:大坐标范围的固定坐标策略,65536 seed × 4097×4097
|
||||
CPU 对照完成;开始 CUDA 预热与计时
|
||||
完成该组完整命中对照
|
||||
测量线程映射:C:固定 seed 的坐标扫描与后续优化,1 seed × 8193×8193
|
||||
CPU 对照完成;开始 CUDA 预热与计时
|
||||
完成该组完整命中对照
|
||||
坐标范围趋势:65536 seed × 513×513
|
||||
坐标范围趋势:65536 seed × 1025×1025
|
||||
坐标范围趋势:65536 seed × 2049×2049
|
||||
完成分段改测:show/BENCHMARK.md 和 show/results/latest.json
|
||||
175
show/results/stage3_polynomial_reuse.json
Normal file
175
show/results/stage3_polynomial_reuse.json
Normal file
|
|
@ -0,0 +1,175 @@
|
|||
{
|
||||
"date": "2026-10-08T23:09:51.361807+08:00",
|
||||
"case": {
|
||||
"seed": 61692151016558,
|
||||
"seeds": 65536,
|
||||
"x0": 50557,
|
||||
"z0": 418612,
|
||||
"width": 1025,
|
||||
"height": 1025,
|
||||
"n": 5
|
||||
},
|
||||
"comparison_equal": true,
|
||||
"before_source_sha256": {
|
||||
"01_cpu.cpp": "b7fc5d25b32050bd3defdb3934e6bb4f1dd8b5d83d529bef8b8a90d719d17e8b",
|
||||
"08_seed_cpu.cpp": "b9722cc52e46eb720fb78ea1d3f0531249cf656d274771fd8c2bad9f06f27800",
|
||||
"07_residue.cu": "873bea97faec42ce87620ea8b6bea3ffdb329ba2cf7924ab2d11719a91347b38",
|
||||
"08_seed_cuda.cu": "e4e95df388e572c21fed0e87b81299265ed66221f7d37b90d5c8feb7839a1ed7",
|
||||
"08_upper_compare.cu": "f20dc272ebc821230c83d22ca5c9819e8b658b1b994025b2c31b1928f067335f",
|
||||
"cuda_steps.cu": "b81d7c85f96c1e1f36fa6cb6907e17f62955606821e86959b038095e10f4957a",
|
||||
"02_cuda_seed.cuh": "1f6a8bf1d780f569c1a685c67edd8242db9d658fb919247b0197c3b450854455",
|
||||
"03_cuda_position.cuh": "69ceeb76a9954b073826a613fe9b343bc3cbb106f47546b3af2bd00df589e34c",
|
||||
"04_cuda_outer_sum.cuh": "a316d3a4845351be996bee4930d817aa9d37edec05cbcf8e1869c086533a477d",
|
||||
"common.hpp": "686d1964fe2fd5cb17709d9c5de7cbfbf0530a7a5622604a138a65194f100a13",
|
||||
"../research/slime_solver_core.hpp": "feb1200518716b4d796fb60f60a83b6b798155bbd4e795531793181a5c7f9eba"
|
||||
},
|
||||
"after_source_sha256": {
|
||||
"03_cuda_position.cuh": "44f49a7db73e52ec87ac632a2cee2f7938a2241a356780e151b3ab0de5d9a506",
|
||||
"cuda_steps.cu": "a5c639dafcdf581c35f4551195cf28e5ec82eac9b642631a6845fbfc6fa48cfb"
|
||||
},
|
||||
"note": "Both versions use fixed-coordinate threads; new version precomputes private axis terms and uses compile-time pattern sizes. Each version has one full warmup and five samples. Versions run sequentially, unlike the rotating main 02/03 comparison.",
|
||||
"results": [
|
||||
{
|
||||
"label": "before",
|
||||
"binary_sha256": "95f417172b7de49271edc1dd20c791fe2834cdcbb0ad7367204e0431dd29a896",
|
||||
"raw": {
|
||||
"command": [
|
||||
"/tmp/slime_show_before_stage3",
|
||||
"--seed",
|
||||
"61692151016558",
|
||||
"--seeds",
|
||||
"65536",
|
||||
"--x0",
|
||||
"50557",
|
||||
"--z0",
|
||||
"418612",
|
||||
"--width",
|
||||
"1025",
|
||||
"--height",
|
||||
"1025",
|
||||
"-n",
|
||||
"5",
|
||||
"--repeats",
|
||||
"5",
|
||||
"--modes",
|
||||
"3"
|
||||
],
|
||||
"process_ms": 10323.46587500001,
|
||||
"stdout": "{\"seed_start\":61692151016558,\"seeds\":65536,\"x0\":50557,\"z0\":418612,\"width\":1025,\"height\":1025,\"n\":5,\"candidate_count\":68853760000,\"gpu\":\"NVIDIA GeForce RTX 3060 Laptop GPU\",\"setup_ms\":227.442475,\"comparison_equal\":true,\"rows\":[{\"mode\":3,\"kernel_samples_ms\":[1532.477417,1534.586914,1555.032104,1549.421509,1537.888306],\"kernel_median_ms\":1537.888306,\"scan_samples_ms\":[1660.816641,1662.997808,1685.21925,1678.91165,1666.479642],\"scan_median_ms\":1666.479642}],\"hits\":[[61692151016558,51069,419124]]}\n",
|
||||
"stderr": ""
|
||||
},
|
||||
"data": {
|
||||
"seed_start": 61692151016558,
|
||||
"seeds": 65536,
|
||||
"x0": 50557,
|
||||
"z0": 418612,
|
||||
"width": 1025,
|
||||
"height": 1025,
|
||||
"n": 5,
|
||||
"candidate_count": 68853760000,
|
||||
"gpu": "NVIDIA GeForce RTX 3060 Laptop GPU",
|
||||
"setup_ms": 227.442475,
|
||||
"comparison_equal": true,
|
||||
"rows": [
|
||||
{
|
||||
"mode": 3,
|
||||
"kernel_samples_ms": [
|
||||
1532.477417,
|
||||
1534.586914,
|
||||
1555.032104,
|
||||
1549.421509,
|
||||
1537.888306
|
||||
],
|
||||
"kernel_median_ms": 1537.888306,
|
||||
"scan_samples_ms": [
|
||||
1660.816641,
|
||||
1662.997808,
|
||||
1685.21925,
|
||||
1678.91165,
|
||||
1666.479642
|
||||
],
|
||||
"scan_median_ms": 1666.479642
|
||||
}
|
||||
],
|
||||
"hits": [
|
||||
[
|
||||
61692151016558,
|
||||
51069,
|
||||
419124
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"label": "after",
|
||||
"binary_sha256": "8668056a28c672a2fc12c1f2046a4be3d72201c8da17d2de30c27462372e64ce",
|
||||
"raw": {
|
||||
"command": [
|
||||
"/mnt/d/dev/slime/show/bin/cuda_steps",
|
||||
"--seed",
|
||||
"61692151016558",
|
||||
"--seeds",
|
||||
"65536",
|
||||
"--x0",
|
||||
"50557",
|
||||
"--z0",
|
||||
"418612",
|
||||
"--width",
|
||||
"1025",
|
||||
"--height",
|
||||
"1025",
|
||||
"-n",
|
||||
"5",
|
||||
"--repeats",
|
||||
"5",
|
||||
"--modes",
|
||||
"3"
|
||||
],
|
||||
"process_ms": 6253.339395000012,
|
||||
"stdout": "{\"seed_start\":61692151016558,\"seeds\":65536,\"x0\":50557,\"z0\":418612,\"width\":1025,\"height\":1025,\"n\":5,\"candidate_count\":68853760000,\"gpu\":\"NVIDIA GeForce RTX 3060 Laptop GPU\",\"setup_ms\":254.046325,\"comparison_equal\":true,\"rows\":[{\"mode\":3,\"kernel_samples_ms\":[912.5765381,920.5626831,915.3710327,905.3746948,917.3391113],\"kernel_median_ms\":915.3710327,\"scan_samples_ms\":[989.005658,997.631591,992.011583,981.183558,994.174567],\"scan_median_ms\":992.011583}],\"hits\":[[61692151016558,51069,419124]]}\n",
|
||||
"stderr": ""
|
||||
},
|
||||
"data": {
|
||||
"seed_start": 61692151016558,
|
||||
"seeds": 65536,
|
||||
"x0": 50557,
|
||||
"z0": 418612,
|
||||
"width": 1025,
|
||||
"height": 1025,
|
||||
"n": 5,
|
||||
"candidate_count": 68853760000,
|
||||
"gpu": "NVIDIA GeForce RTX 3060 Laptop GPU",
|
||||
"setup_ms": 254.046325,
|
||||
"comparison_equal": true,
|
||||
"rows": [
|
||||
{
|
||||
"mode": 3,
|
||||
"kernel_samples_ms": [
|
||||
912.5765381,
|
||||
920.5626831,
|
||||
915.3710327,
|
||||
905.3746948,
|
||||
917.3391113
|
||||
],
|
||||
"kernel_median_ms": 915.3710327,
|
||||
"scan_samples_ms": [
|
||||
989.005658,
|
||||
997.631591,
|
||||
992.011583,
|
||||
981.183558,
|
||||
994.174567
|
||||
],
|
||||
"scan_median_ms": 992.011583
|
||||
}
|
||||
],
|
||||
"hits": [
|
||||
[
|
||||
61692151016558,
|
||||
51069,
|
||||
419124
|
||||
]
|
||||
]
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
19
show/results/tests.txt
Normal file
19
show/results/tests.txt
Normal file
|
|
@ -0,0 +1,19 @@
|
|||
历史 GPU 验证日志;不表示此次清理重新运行 GPU 测试。
|
||||
|
||||
test_all_pattern_sizes (__main__.Steps.test_all_pattern_sizes) ... ok
|
||||
test_complete_fixed_position_pipeline (__main__.Steps.test_complete_fixed_position_pipeline) ... ok
|
||||
test_high16_equivalence_and_seed48_wrap (__main__.Steps.test_high16_equivalence_and_seed48_wrap) ... ok
|
||||
test_int32_edges (__main__.Steps.test_int32_edges) ... ok
|
||||
test_invalid_ranges_and_truncation (__main__.Steps.test_invalid_ranges_and_truncation) ... ok
|
||||
test_known_hit_and_partial_tiles (__main__.Steps.test_known_hit_and_partial_tiles) ... ok
|
||||
test_negative_and_overflow_coordinates (__main__.Steps.test_negative_and_overflow_coordinates) ... ok
|
||||
test_nonzero_seed_and_nonblock_dimensions (__main__.Steps.test_nonzero_seed_and_nonblock_dimensions) ... ok
|
||||
test_outer_tall_rectangle_fallback (__main__.Steps.test_outer_tall_rectangle_fallback) ... ok
|
||||
test_rejection_tail (__main__.Steps.test_rejection_tail) ... ok
|
||||
test_residue_expansion_against_direct_window (__main__.Steps.test_residue_expansion_against_direct_window) ... ok
|
||||
test_upper13_against_enumeration (__main__.Steps.test_upper13_against_enumeration) ... ok
|
||||
|
||||
----------------------------------------------------------------------
|
||||
Historical suite completed in 10.792s; retired X/Z test entry removed on 2026-10-11.
|
||||
|
||||
OK
|
||||
Loading…
Add table
Add a link
Reference in a new issue