slime/show/results/mapping_diagnostics.json

704 lines
23 KiB
JSON
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"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."
}