Ada, AD102, 16384 shaders, PCIe 4.0 x16

Thanks to @MysteryDove

• processor clock @ 2520 MHz
• driver 551.86
• Windows 10 21H2 (19044.1415)
• Python 3.11.3
• vapoursynth-classic R57.A8
• vapoursynth-plugin v0.96g3

1920x1080 rgbs, CUDA graphs enabled, fp16, max_aux_streams=0

Measurements: FPS / Device Memory (MB)

model	1 stream	2 streams	3 streams
dpir gray	22.05 / 1818.796	25.30 / 3111.114	25.33 / 4403.488
dpir color	18.30 / 1851.632	25.13 / 3176.808	25.17 / 4501.984
waifu2x upconv_7_{anime_style_art_rgb, photo}	20.45 / 2148.716	41.22 / 3867.240	61.21 / 5585.764
waifu2x upresnet10	17.91 / 1716.588	34.53 / 2941.540	42.33 / 4166.492
waifu2x cunet / cugan	13.89 / 4391.292	25.74 / 8346.248	25.96 / 12301.202
waifu2x swin_unet	4.62 / 7436.692	5.43 / 14426.812	5.43 / 21412.840
real-esrgan (v2/v3, xsx2)	17.06 / 1087.844	33.41 / 1778.264	38.26 / 2468.684
scunet gray	5.29 / 3590.320	5.40 / 6678.768	5.40 / 9767.208
scunet color	5.13 / 3555.568	5.48 / 6611.308	5.47 / 9667.048
swinir-s (2x, color)	1.63 / 15897.048	N/A	N/A
swinir-m* (2x, color, 720p)	1.05 / 11305.268	N/A	N/A
swinir-l* (4x, color, 720p)	0.61 / 15391.316	N/A	N/A

*: swinir-m and swinir-l models exhibit overflow issues.

v2, fp16 i/o

version	1 stream	2 streams	3 streams	4 streams	5 streams
v4.4-v4.5	136.92/778.432	273.80/1149.204	414.80/1522.028	553.70/1892.796	574.31/2263.568
v4.6	136.01/800.960	275.26/1192.212	411.01/1585.516	544.30/1979.764	550.01/2368.020
v4.7-v4.9	98.20/1302.724	195.78/2187.548	210.12/3074.420	210.45/3957.196	210.66/4844.068
v4.10-v4.15	84.41/1595.592	160.93/2773.280	161.96/3953.020	162.04/5132.760	162.07/6310.448
{v4.12, v4.13, v4.15, v4.16}_lite	93.39/1333.444	187.32/2255.132	197.71/3178.872	198.01/4098.508	197.95/5022.248
v4.14 lite	81.83/1595.292	153.40/2779.424	154.19/3963.260	154.28/5149.140	154.30/6332.980

• processor clock @ 2520 MHz
• driver 551.86
• Windows 10 21H2 (19044.1415)
• Python 3.11.3
• vapoursynth-classic R57.A8
• vapoursynth-plugin v0.96g3

1920x1080 rgbs, CUDA graphs enabled, fp16

Measurements: FPS / Device Memory (MB)

model	1 stream	2 streams	3 streams
dpir gray	21.93/1757.352	25.48/3049.696	25.31/4342.044
dpir color	18.24/1790.184	25.11/3115.360	25.22/4440.540
waifu2x upconv_7_{anime_style_art_rgb, photo}	19.58/2148.716	39.87/3867.240	59.94/5585.768
waifu2x upresnet10	17.40/1655.144	34.22/2880.096	42.78/4105.048
waifu2x cunet / cugan	13.64/4391.292	25.09/8346.248	25.19/12301.208
waifu2x swin_unet	4.62/14989.772	OOM	OOM
real-esrgan (v2/v3, xsx2)	16.77/1136.996	33.99/1876.568	41.44/2616.140

v2, fp16 i/o

version	1 stream	2 streams	3 streams	4 streams	5 streams
v4.4-v4.5	150.20/622.784	301.05/835.860	448.90/1053.024	615.84/1268.152	787.57/1481.224
v4.6	147.63/624.832	294.53/837.904	452.26/1055.072	603.63/1270.200	764.31/1485.320
v4.7-v4.9	132.06/747.712	268.63/1075.476	403.54/1405.284	494.98/1737.152	496.41/2064.908
v4.10-v4.15	119.09/862.400	238.68/1304.852	346.98/1749.352	349.48/2195.904	349.80/2638.356
{v4.12, v4.13, v4.15, v4.16}_lite	123.72/782.528	250.81/1151.252	377.27/1522.020	403.14/1894.844	403.79/2263.568
v4.14 lite	117.97/839.872	234.67/1265.940	320.23/1696.104	321.88/2124.224	321.18/2552.340

• processor clock @ 2860 MHz
• memory clock @ 1406.25 MHz
• driver 527.56
• Windows 11 21H2
• VapourSynth R57

1920x1080 rgbs

Measurements: FPS / Device Memory (MB)

model	ORT_CUDA 1 stream	TRT 1 stream	TRT 2 streams
dpir gray	9.093 / 1845	23.95 / 975	24.527 / 1297
dpir color	8.688 / 1749	21.92 / 1073	24.212 / 1413
waifu2x upconv7	20.15 / 5905	39.035 / 2354	53.406 / 4029
waifu2x upresnet10	13.445 / 2814	29.411 / 2147	37.001 / 3439
waifu2x cunet	6.981 / 8532
cugan	6.869 / 8719	20.511 / 5490	24.018 / 9579
realesrgan	14.188 / 2346	28.518 / 2080	35.771 / 2970
rife (1920x1088, model=44)	95.52 / 1609	138.513 / 1319	208.345 / 1653

• driver 545.84
• Windows 10 22H2
• VapourSynth-classic R57.A8

1920x1080 rgbs

PSNR is tested on a private set of samples compared to FP32.

Measurements: FPS / Device Memory (MB)

precision	TRT 1 stream	TRT 2 streams	PSNR
fp16	4.91 / 7399.8	5.40 / 14351	65.3
bf16	4.70 / 7797.1	5.10 / 15142	53.7