Posts by Centro de Computacion de Fotometria Estelar

1) (Message 8979)
Posted 16 May 2025 by Profile Centro de Computacion de Fotometria Estelar
Post:
I disagree, I think it's software, given that the computing power of the RX9070XT is much higher than the RTX4060, and they get exactly the same score.


Estoy en desacuerdo, creo que es software, dado que la potencia de calculo de la RX9070XT es muy superior a RTX4060, y sacan exactamente la misma puntuacion



Yes, i using the rtx4060 on folding at home, and i obtain 4.000.000 ponts per day, but i now i using the rtx5070ti, and obtain 25.000.000 points per day.


In asteroids the rtx4060 work 1 unit 6-8 minute /wu = 50points
Buy the rx9070xt work 1unit 6-5 min /wu 50 points

I think is the software of application on asteroids
2) (Message 8978)
Posted 16 May 2025 by Profile Centro de Computacion de Fotometria Estelar
Post:
I disagree, I think it's software, given that the computing power of the RX9070XT is much higher than the RTX4060, and they get exactly the same score.


Estoy en desacuerdo, creo que es software, dado que la potencia de calculo de la RX9070XT es muy superior a RTX4060, y sacan exactamente la misma puntuacion
3) (Message 8974)
Posted 9 May 2025 by Profile Centro de Computacion de Fotometria Estelar
Post:
He empezado las pruebas con el equipo AMD 7950x RX9070XT, esta 5 minutos procesando la tarea con la frecuencia de la memoria de la tarjeta entre 1200mhz u 1538mhz,, totalmente fria consumiendo 83wats, y despues , pasados los 5 minutos comienza a procesar, procesa 3 minutos y 18 segundos empieza a calientarse hasta los 2786mhz de memoria consumiendo 220-236wats, haciendo un total de 8minutos y 14 segundos, definitivamente hay algo mal en las tareas ps_250507_input_29478_69 (221603 bytes). porque solo trabaja a alta frecuencia la memoria los ultimos 3 minutos Las tareas tardan lo mismo que una rtx4060.

Los amd 7950x son especialmente calientes, sin overclok los 32 hilos al 75% de tiempo llegan 70ºC a 75ºC. suelen tardar 40 minutos cada tarea, una pequeña o ligera diferencia frente a los 45 minutos de loa amd ryzen 9 5900x.

Los amd7950x con ddr5 es la peor inversion que he realizado, rinden casi lo mismo que amd 5900x con ddr4, voy a dejarlo trabajando unos dias para ver los datos, creo que los tiempos se estan reduciendo.

Una cosa curiosa de rx9070xt , es que la temperatura de la memoria es 10 grados superior 71ºC, a hot spot 64ºC , cuando la gpu solo tiene 43ºC
4) (Message 8966)
Posted 28 Apr 2025 by Profile Centro de Computacion de Fotometria Estelar
Post:
https://www.eldiario.es/economia/grafico-tiempo-real-muestra-apagon-electrico-espana_1_12253737.html

All is off
5) (Message 8965)
Posted 26 Apr 2025 by Profile Centro de Computacion de Fotometria Estelar
Post:
> Can you use the IA tensor cores of nvidia to program ASIC of asteroids at home?

No, tensor cores do support low-precision data types like FP16, they're specifically built for AI workloads. The Asteroids app depends on FP64, and lower precisions aren't good enough. That’s also why none of the existing BOINC projects make use of tensor cores (or NPUs); they're not suitable for scientific computing. Like ASICs, tensor cores are highly specialized, great for AI, but pretty much useless for most scientific applications.


Technically the chip GB203 of rtx5070ti have tensor cores in FP64

When i received the chips AMD, i wil make the computers, about final of month may, in my country the transport is bad, and very slow.
6) (Message 8964)
Posted 25 Apr 2025 by Profile Centro de Computacion de Fotometria Estelar
Post:
PCIe bandwidth is mostly important for SSD performance or when games exceed available GPU memory. In typical scenarios, it's primarily used during data transfers to the GPU, like when loading a game level. Compute tasks, on the other hand, spend minimal time on data loading. Most of their time is spent processing data that's already resident in GPU memory. Faster is always better in theory, but if data transfers only account for 1% of the total workload, speeding them up even 10 times won’t make a noticeable difference.

what doesn't matter:
* pcie bandwidth
* tensor / AI / wmma - no boinc app utilize them
* FP16, INT4... - despite great perf numbers, no boinc app utilize them
* TMUs (TMU * clock speed = Texture Rate) - only relevant for games
* ROPs (ROP * clock speed = Pixel Rate) - only relevant for games
* VRAM capacity - A larger size won’t improve performance, and most GPUs have more than enough capacity to handle BOINC projects.

what matters:
* GPU vendor / architecture in general
* cores - but meaningful comparisons can only be made within the same architecture and vendor
* FP32
* FP64
* INT32
* cache
* memory bandwidth
* clock speed

Those are attributes you should be looking for, but just like with games, performance can vary. Some projects see greater gains from high clock speeds, while others rely more on memory bandwidth. It depends on the type of computations and how well the application is optimized.




The RTX5070Ti have 336 tensore cores on FP64 , chip GB203 Blackwell architecture

https://asteroidsathome.net/boinc/forum_thread.php?id=1125
7) (Message 8963)
Posted 25 Apr 2025 by Profile Centro de Computacion de Fotometria Estelar
Post:
Information for developers

RDNA4.0 Architecture

https://www.amd.com/content/dam/amd/en/documents/radeon-tech-docs/instruction-set-architectures/rdna4-instruction-set-architecture.pdf

Blackwell Architecture

https://images.nvidia.com/aem-dam/Solutions/geforce/blackwell/nvidia-rtx-blackwell-gpu-architecture.pdf

https://developer.nvidia.com/blog/cuda-toolkit-12-8-delivers-nvidia-blackwell-support/

https://docs.nvidia.com/cuda/cuda-toolkit-release-notes/index.html#deprecated-or-dropped-features

https://nvdam.widen.net/s/xqt56dflgh/nvidia-blackwell-architecture-technical-brief

In the last technical brief, the tensor cores are FP64 in GB200 superchip 90TeraFLOPS rtx5000 series.

The next generation of rtx 5000, the rtx6000,

https://www.techpowerup.com/gpu-specs/rtx-pro-6000-blackwell.c4272


FP16 (half)
126.0 TFLOPS (1:1)

FP32 (float)
126.0 TFLOPS

FP64 (double)
1.968 TFLOPS (1:64)
8) (Message 8959)
Posted 21 Apr 2025 by Profile Centro de Computacion de Fotometria Estelar
Post:
Este sitio es lo único que me ancla con la realidad, es todo lo que puedo hacer por la ciencia, es la única magnitud verdadera, nuestro mundo esta lleno de mentiras necesarias para mantener vuestro imperio del derecho, teórico, superficial y materialista nos aleja de la realidad, para confrontarnos en guerras por la ambición de dicho imperio, siempre son unos pocos hombres quienes donan sus pocos recursos humildemente, máxime, en los periodos de mas necesidad, que terrible ambición la que describa la maldad del hombre cuando mas desarrollo tecnológico suscitan las guerras. Pues es ese preciso instante donde el imperio del derecho da la libertad a la ciencia, la muerte. Por el contrario, para la vida, el amor el deseo del progreso de una vida en armonía estan los hombre solos y pobres que dan lo que tienen, resolviendo una vez mas, "el pueblo salva el pueblo" ni los reyes ni la incompetencia de los políticos pueden ayudar, no saben gestionar las emergencias de una DANA ni los alimentos donados a los mas necesitados, sin embargo parecen muy hábiles en desviar los fondos para favorecer a sus empresas. Dicha y encontrada la esencia de la corrupción Española, podemos analizar porque no hay ningún documental que dignifique los preámbulos de la transición de los colaboradores del régimen dictatorial, que sepultados por el CNI y la CIA han dado unas falsas bases por la que no se cultiva ningún respeto hacia el servidor publico ni hacia el servicio publico, sino que por el contrario, la corrupción sociológica de los funcionarios deja una profunda apatía del pueblo, y nos recuerda que no tenemos el suficiente nivel cultural para asimilar un Estado de Derecho con interpretaciones llenas de odio y rencor en un mar ideológico sin resolver por esa a la que llaman profusamente desgastada Justicia.
9) (Message 8939)
Posted 9 Apr 2025 by Profile Centro de Computacion de Fotometria Estelar
Post:
> Can you use the IA tensor cores of nvidia to program ASIC of asteroids at home?

No, tensor cores do support low-precision data types like FP16, they're specifically built for AI workloads. The Asteroids app depends on FP64, and lower precisions aren't good enough. That’s also why none of the existing BOINC projects make use of tensor cores (or NPUs); they're not suitable for scientific computing. Like ASICs, tensor cores are highly specialized, great for AI, but pretty much useless for most scientific applications.


Lo probaré

¿Do you recommend crossfire/SLI or not,?
10) (Message 8935)
Posted 8 Apr 2025 by Profile Centro de Computacion de Fotometria Estelar
Post:
Note that FP32 represents peak performance under ideal (unrealistic) conditions. Real-world applications are more complex than simply multiplying two numbers. As a result, newer architectures can outperform older GPUs in certain applications, even if their FP32 performance is lower because they can utilize available resources more efficiently.
The numbers can give you a rough performance estimate, but it's always best to test with the specific application you plan to run.



I buy 2 rx7900xt 2x789€ motherboard B840 and 1 nvidia rtx5070ti OC 949€ motherboards B850

In 1 month will recibe the cpus Ryzen 9 7950x :)


¿Can you use the IA tensor cores of nvidia to program ASIC of asteroids at home?
11) (Message 8934)
Posted 8 Apr 2025 by Profile Centro de Computacion de Fotometria Estelar
Post:
Please refrain from insulting others. We're here to help, but we have no control over how the work is distributed. We're just volunteers like you.
Some other projects, such as PrimeGrid, provide more consistent workloads. They can generate tasks that run for years with ease, making them a good choice if you want to keep your PC continuously occupied. On the other hand, GPUGrid has been out of work for a month. Are you suggesting they have "poor management" as well?


Considero a Asteroids at home el proyecto mas interesante desde el punto de vista de la visibilidad de los resultados directa y publica, los datos computados tiene un numero que puede ser consultado en la base DAMINT, por ejemplo el resultado ps_250404_input_3731_490_0_r1562681491_0 , ofrece una referencia 3731 segun el damint https://astro.troja.mff.cuni.cz/projects/damit/ (todavia no hay referencias de renderizado para su visualizacion por ser una tarea reciente, pero hay otras como 1382 que es una de las tareas me llevo 1h y 42min que hace referencia un asteroide llamado "Gerti" , las imagenes imagino que son obtenidas en distintos tiempos para saber su eje de rotacion, pero ignoro si los calculos sirven también para conocer su trayectoria o posicion, pero si sirven para saber su eje de rotacion.

A partir de esta semana y la anterior, ya estoy recibiendo cargas de trabajo constantes, sin quedar desprovisto de tareas como las semanas anteriores, al no poder adquirir mas de 500 tareas en progreso, cuando los servidores dejan de enviar los viernes a medio dia, el Sabado a las 22:00h tengo que apagar el ordenador mas potente, dado que ya no tiene tareas que computar. Sin embargo, debo decir que a partir de el viernes de la semana anterior, estoy recibiendo tareas que a diferencias de las anteriores semanas tardan el doble de tiempo en resolverse. ahora llegan casi a los 50 minutos, y esporadicamente hay tareas de 1h y 45 minutos por ejemplo input 1382.

El problema de GPUgrid, son que las investigaciones que publican son breves resumenes, y no se puede acceder al contenido completo de la misma, quedando restringido solo para personal PDI investigador, ademas, antes, al igual que asteroids at home, publicaban los nombres de los colaboradores en esta pagina https://asteroidsathome.net/scientific_results.html, ahora ya no, considero que se debiera retomar esta iniciativa para ser compensado de alguna forma

Desconocía que la gestion, administracion o asignacion de tareas se asignaba a mano. Tampoco he sabido valorar el altruismo con el cual se mantienen, programan o desarrollan el contenido motor del proyecto, me disculpo por ello. Reconozco que he sido maleducado al no ver el esfuerzo que hay detras de estos proyectos gratuitos.

Seria bueno en el caso de no poderse visualizar la simulación de la tarea ejecutándose ( en la sección propiedades), tener en un listado de nombre de colaboradores.

Por otro lado alguien deberia tambien publicar con mas frecuencia el fantastico trabajo que haceis, desde aqui parece todo muy cerrado,
12) (Message 8933)
Posted 8 Apr 2025 by Profile Centro de Computacion de Fotometria Estelar
Post:
Note that FP32 represents peak performance under ideal (unrealistic) conditions. Real-world applications are more complex than simply multiplying two numbers. As a result, newer architectures can outperform older GPUs in certain applications, even if their FP32 performance is lower because they can utilize available resources more efficiently.
The numbers can give you a rough performance estimate, but it's always best to test with the specific application you plan to run.



I buy 2 rx7900xt 2x789€ motherboard B840 and 1 nvidia rtx5070ti OC 949€ motherboards B850

In 1 month will recibe the cpus Ryzen 9 7950x :)
13) (Message 8927)
Posted 7 Apr 2025 by Profile Centro de Computacion de Fotometria Estelar
Post:
ok, thx, but its the same x8 than x1? because the motherboard its turn to x1 if you connect two graphic cards
14) (Message 8924)
Posted 7 Apr 2025 by Profile Centro de Computacion de Fotometria Estelar
Post:
My mother board Placa Base ASUS PRIME B550M-A WIFI II . have

PCI Express x1 (Gen 3.x) ranuras: 2
PCI Express x16 Gen (3.x) ranuras: 1
Ranuras PCI Express x16 (Gen 4.x): 1



For example, using the HWINFO64 , i see Bus PCIe 4.0 X8 16GT/s and x8.

The velocity of RAM are 4.6Gb/s

https://ibb.co/Ps5jjscc

theoretical gigatrasnfers per second rx7900xt

Pixel Rate
459.6 GPixel/s

Texture Rate
804.4 GTexel/s
15) (Message 8923)
Posted 7 Apr 2025 by Profile Centro de Computacion de Fotometria Estelar
Post:
I have Psi-e 4 set in BIOS because the motherboard supports the fourth version. I myself am unpleasantly surprised by such performance.

I think, i cant run at 100% rx7900xt because the second slot works at x8 if conect first slot, and works two cards in Asus prime x870p. I cant pay motherboard workstation with epyc cpu.


¿In this tasks of BOINC are really relevant obtain 5.0 to 4.0 or, x16 or x8? , much motherboards only works at 8x when are two graphic cards connected at motherboard, ¿this is relevan in this type of tasks?

Example actually have motherboard asus prime B550 whit RTX4060 OC 8GB Eagle, and...the motherboard have 1 PCIe 4.0 at x16, and actually en 2 weeks have 20.000 promedio, in fact, i make less more than 30.000
16) (Message 8922)
Posted 7 Apr 2025 by Profile Centro de Computacion de Fotometria Estelar
Post:
I have Psi-e 4 set in BIOS because the motherboard supports the fourth version. I myself am unpleasantly surprised by such performance.

I think, i cant run at 100% rx7900xt because the second slot works at x8 if conect first slot, and works two cards in Asus prime x870p. I cant pay motherboard workstation with epyc cpu.
17) (Message 8921)
Posted 6 Apr 2025 by Profile Centro de Computacion de Fotometria Estelar
Post:
Since it's an OpenCL app, the Radeon RX 9070 XT (RDNA 4) should work fine. However, for the card to be listed among the TOP GPUs, there must be at least 10 active hosts. This requirement ensures that the statistics remain meaningful.
It looks like you don’t have the card and are just interested in its performance. Is that right?

Unlike AMD, the official CUDA application doesn’t yet support Blackwell (GeForce RTX 5000 series), but the next version will.



Yes im interesting in rx7900xt because have a, more TFLOPS than RX9070XT, but difference is little.

Acctually im seeing the acctual work on a user with rx9070xt, mmm, the time is very similar than the rtx4060 295-500seg/wu


But i see, the rtx5070TI have RAY TRACING 4ª generación, 133 TFLOPS!!!!!
18) (Message 8919)
Posted 5 Apr 2025 by Profile Centro de Computacion de Fotometria Estelar
Post:
I see the code in git hub https://github.com/AsteroidsAtHome/PeriodSearch last modificacion 3 years ago

in period searchmain
in the period_searh_optimization_cpu
input_period_search
period_searh_in_2263

only for visualize one of the task

2 0.5 1000 1 period_start period_step period_end fixed/free
0.0 initial epoch
0.0 initial rotation angle
0.1 convexity weight
3 3 degree and order of spherical harmonics
6 number of rows
0.5 1 scattering parameters
0.1 1
-0.5 1
0.1 0 LS coeff
50 iteration stop condidion
10 minimum number of iterations (only if the above value < 1)
5 Alamda multiplicative factor
0.1 Alamda initial value
19
66 0 0.012 2008-09-01.4 R Oey
2454710.033030 9.526465e-01 -2.23590051 -0.00900072 0.39304262 -1.29772251 -0.38119762 0.39304159
...... a lot of numbres i think probably matrix and derivades calculations of Two methods are outlined for estimating the attitude and rotation of an object with a known shape and orbit using only light curve measurements :/ bayesian inference?, this methods, ...

i remember when use newthon rhapson and gauss seidel when system converge for caluclation of nodes electrical systems of power. ( in spanish) (calculaba los incrementos de los resultados de las matrices inversas, y si no convergía en el error hacia otra iteracion hasta que el sistema pasaba el error minimo fijado)

this is my work of system iterations (start page 64 of pdf) 4 nodes by hand, yes, BY HAND muahahaha one iteration of nwethon rhapson its toooo crazy

https://www.transfernow.net/dl/20250405eSViW6HK

Its no have manual for understand how works the period search application,, but, i think, i can use deep seek R1 IA, (R1) for code , for understand.

i think this IA can write the code c... in python?

¿How works in the cpu this code? Can i see the code run with asembler or xdbg debugger , and see , the diagram fluxes?

I think what the IA can generate code for visulize the simulation (light curve) in boinc?, because only can see propierties of task
19) (Message 8918)
Posted 5 Apr 2025 by Profile Centro de Computacion de Fotometria Estelar
Post:
Since it's an OpenCL app, the Radeon RX 9070 XT (RDNA 4) should work fine. However, for the card to be listed among the TOP GPUs, there must be at least 10 active hosts. This requirement ensures that the statistics remain meaningful.
It looks like you don’t have the card and are just interested in its performance. Is that right?

Unlike AMD, the official CUDA application doesn’t yet support Blackwell (GeForce RTX 5000 series), but the next version will.



Yes im interesting in rx7900xt because have a, more TFLOPS than RX9070XT, but difference is little.

Acctually im seeing the acctual work on a user with rx9070xt, mmm, the time is very similar than the rtx4060 295-500seg/wu
20) (Message 8917)
Posted 5 Apr 2025 by Profile Centro de Computacion de Fotometria Estelar
Post:
https://asteroidsathome.net/boinc/show_host_detail.php?hostid=773485

host with rx 9070хт. If you are interested in evaluating the operating time.


¿how can evaluate?, is off ¿no?, its a few points, ¿its run 24h/day?

the rx9070xt make task in 200 to 400seg, same as RTX4060, mmm, this is not possible! OMG

I have another quuestion, ¿what is grc pool?, is asteroids?

I have another question, What does it affect, for the processing of the tasks of the graphics card that?
is 5x PCI-E x16 slot

PCI_E1 Gen PCIe 4.0 supports up to x16 (From CPU)
PCI_E2 Gen PCIe 3.0 supports up to x1 (From Chipset)
PCI_E3 Gen PCIe 3.0 supports up to x1 (From Chipset)
PCI_E4 Gen PCIe 3.0 supports up to x4 (From Chipset)
PCI_E5 Gen PCIe 3.0 supports up to x1 (From Chipset)

if you have PCIe 3.0 is slow, thna 4.0, but, internally, the graphic works on his memory, that is important, obtain PCIe5.0?

¿Its important de velocity of PCIex16 on 3.0 vs 5.0 in asteroids at home with rx7900xt?


Next 20