Gráfica AMD FirePro 2012 GPU e FirePro A300 Series APUs

Roberto1973

Roberto1973

Power Member
AMD FirePro 2012 Lineup


The FirePro professional graphics lineup for 2012 consists of four members.
Here is a breakdown:
AMD FirePro W5000 (“Megamind”)
Cape Verde GL GPU
2 GB GDDR5 (128-bit), 102.4 GB/s memory bandwidth
2× DisplayPort 1.2, 1× DVI-I
<75W power consumption
Single-slot active fansink
W5000-300x1931.png


AMD FirePro W7000 (“Tighen”)

Pitcairn GL GPU
4 GB GDDR5 (256-bit), 152 GB/s memory bandwidth
4× DisplayPort 1.2
2.4 TFLOPS single-precision, 152 GFLOPS double-precision
Genlock/Framelock
<150W power consumption
1× 6-pin power connector
Single-slot active fansink

W7000-300x1591.png


AMD FirePro W8000 (“Buzz Lightyear”)
Tahiti XT GL GPU
6 GB GDDR5 (384-bit), 176 GB/s memory bandwidth
4× DisplayPort 1.2, 1× 3-pin DIN (Stereoscopic 3D glasses)
3.23 TFLOPS single-precision, 806 GFLOPS double-precision
Memory ECC support
Genlock/Framelock
<225W power consumption
2× 6-pin power connectors
Dual-slot active fansink
W8000-300x1341.png


AMD FirePro W9000 (“Woody”)
Tahiti XT GL GPU
1 GHz GPU frequency
1.95 billion triangles per second
6 GB GDDR5 (384-bit), 264 GB/s memory bandwidth
6× DisplayPort 1.2, 1× 3-pin DIN (Stereoscopic 3D glasses)
4 TFLOPS single-precision, 1 TFLOPS double-precision
Memory ECC support
Genlock/Framelock
<300W power consumption
1× 6-pin power connector + 1× 8-pin power connector
Dual-slot active fansink

W9000-300x1331.png


Update 8/8/12: W8000 changes from 2×8-pin to 2×6-pin. Thanks to Arvid for the correction. Explanation: The train wreck that is AMD PR is to blame for this with seemingly new lows every day.
Same for all GCN-based GPUs, all these professional graphics cards support AMD Eyefinity technology for multi-display workloads, and DirectX 11/OpenGL 4.2 APIs as well as OpenCL 1.2/DirectCompute/C++ AMP. Genlock and framelock functionality will be provided by the FirePro S400 synchronization module, as per usual.
Power efficiency is also important for professional graphics and GPGPU parts as they contribute significantly towards the stability of the product, so the usual AMD PowerTune technology and AMD ZeroCore technology are present in all of the above FirePro offerings, the same for the use of vapor-chamber fansinks.

http://semiaccurate.com/2012/08/07/amd-firepro-2012-lineup/

FirePro A300 Series APUs
  • Trinity GL APU
    • 4 Piledriver CPU Cores
    • AMD TurboCore 3.0 Technology for up to 2 cores
    • 4 MB L2 Cache
    • 384 Radeon Cores (VLIW4 architecture), 24 TMU, 8 ROP
    • Dual-channel DDR3-1866 (128-bit)
  • AMD HD3D Pro Technology, Stereo 3D Support
  • 10-bit display capabilities
  • AMD Eyefinity Technology (up to 4 monitors)
  • Display Connectivity
    • DisplayPort 1.2 (Maximum resolution 4096×2160)
    • Single-link or Dual-link DVI
    • Single-channel or Dual-channel LVDS3
    • Single-link HDMI 1.4a (Maximum resolution 1920×1080)
  • 1/4th double-precision rate
  • UVD 3.2, VCE 1.0, SAMU 1.0, IOMMU v2
  • API Support
    • DirectX 11/Direct3D 11, DirectCompute, C++ AMP
    • OpenGL 4.2, OpenCL 1.1
    • Socket FM2 infrastructure
  • AMD FirePro A320 APU
    • CPU frequency: 3.8 GHz (Base), 4.2 GHz (TurboCore)
    • GPU frequency: 800 MHz
    • Floating-point performance (single/double-precision): 736 GFLOPS/184 GFLOPS
    • Unlocked APU
    • 100W TDP
    • Desktop equivalent: AMD A10-5800K
  • AMD FirePro A300 APU
    • CPU frequency: 3.4 GHz (Base), 4.0 GHz (TurboCore)
    • GPU frequency: 760 MHz
    • Floating-point performance: 693 GFLOPS/173 GFLOPS
    • 65W TDP
    • Desktop equivalent: AMD A10-5700
http://semiaccurate.com/2012/08/07/apus-for-workstations-launching/
 
Última edição:
Adorei os codenames “Woody” :D

Parece-me que pelo menos em termos de performance bruta "TFLOPS" a AMD está a frente, mas ainda há muita gente a não confiar muito na AMD neste mercado.
 
Não é só o facto de ter ficado sem suporte, mas o facto da velocidade no Adobe CS com gráficas que tenham CUDA, ser assustadoramente superior a qualquer outra tecnologia. São compatibilidades, contratos e negócios, mas o cliente não tem culpa nem quer saber disso, quer fazer as coisas rápido.

Notar, no entanto, que a nvidia aproveitou isso (entre outros factores) e as gráficas da série 6xx não são grande coisa para essas tarefas. As quadro sim, ainda dominam largamente o mercado.
 
SubCode disse:
Não é só o facto de ter ficado sem suporte, mas o facto da velocidade no Adobe CS com gráficas que tenham CUDA, ser assustadoramente superior a qualquer outra tecnologia. São compatibilidades, contratos e negócios, mas o cliente não tem culpa nem quer saber disso, quer fazer as coisas rápido.
Clicar para expandir...

Embora as coisas estejam a caminhar para o lado do OpenCL mesmo na Adobe, ainda existem coisas com o MPE no Premiere que em Windows só funciona com CUDA.
 
Eu fico espantado com os coolers que metem nestas gráficas, parece que querem provocar sobre-aquecimentos em pouco tempo!
 
 
Última edição:
Ja existe review e comparativos entre os high ends. W8000 / 9000 contra as quadro 6000.
http://www.tomshardware.com/reviews/firepro-w8000-w9000-benchmark,3265.html


Sao placas muito interessantes de acordo com a finalidade que se pretende. Eu por exemplo tenho uma firepro V4800 e aquilo apra a finalidade que é bomba nas horas (Solidworks e Acad).
Ja no trabalho tenho uma Quadro 2000, e sendo a firepro 1 terço do preço, tem (para mim) melhor performance e qualidade d imagem.

agora é um facto que existe placas com drivers optimizados para determinados programas e vice versa, da mesma forma como é com os jogos. HA uns optimizados para uns, e outras para outros jogos. E tudo muito relativo.. na verdade é que conforme a utilização que se pretende, uma pessoa pode ter melhor ideia e comparaçao e ai sim, puder escolher o que procura.

A titulo de curiosidade, no meu caso, inicialmente estava a ir para a Quadro 600, mas depois vi os testes e comparativos, e acabei de ir para a Firepro, pois tem melhor performance para a finalidade que procuro.
 
AMD FirePro APUs and Motherboards Start Selling

AMD's FirePro APUs built on the "Trinity" silicon, with the GPU feature-set of AMD's FirePro professional GPUs and durability of Opteron enterprise CPUs; and compatible motherboards made by PC Partner (Sapphire) have started selling in Japan. Among the new products on sale are the FirePro A300 (3.40 GHz CPU core, 4.00 GHz CPU TurboCore, 760 MHz GPU, quad-core, 65W), and FirePro A320 (3.80 GHz CPU core, 4.20 GHz CPU TurboCore, 800 MHz GPU, quad-core, 100W), and the AMD reference design micro-ATX motherboard, manufactured by PC Partner.

The motherboard features socket FM2, powered by an 8-phase digital PWM power supply to the APU socket, four DDR3 DIMM slots supporting 64 GB of dual-channel DDR3-1866 MHz memory, expansion slots that include PCI-Express 2.0 x16, PCI-Express 2.0 x4, x1, and legacy PCI; eight SATA 6 Gb/s ports, display outputs that include dual-link DVI, dual-link DisplayPort, and D-Sub. HD audio and gigabit Ethernet make for the rest of it.
Clicar para expandir...
http://www.techpowerup.com/174676/AMD-FirePro-APUs-and-Motherboards-Start-Selling.html
 
2q09klf.jpg

15gfjbo.jpg

http://www.anandtech.com/show/6445/amd-announces-firepro-s10000


Key Features of AMD FirePro S10000 Server Graphics

● Compute Performance: The AMD FirePro S10000 is the most powerful dual-GPU server graphics card ever created, delivering up to 1.3 times the single precision and up to 7.8 times peak double-precision floating-point performance of the competition's comparable dual-GPU product. It also boasts an unprecedented 1.48 TFLOPS of peak double-precision floating-point performance;
● Increased Performance-Per-Watt: The AMD FirePro S10000 delivers the highest peak double-precision performance-per-watt -- 3.94 gigaFLOPS -- up to 4.7 times more than the competition's comparable dual-GPU product;
● High Memory Bandwidth: Equipped with a 6GB GDDR5 frame buffer and a 384-bit interface, the AMD FirePro S10000 delivers up to 1.5 times the memory bandwidth of the comparable competing dual-GPU solution;
● DirectGMA Support: This feature removes CPU bandwidth and latency bottlenecks, optimizing communication between both GPUs. This also enables P2P data transfers between devices on the bus and the GPU, completely bypassing any need to traverse the host's main memory, utilize the CPU, or incur additional redundant transfers over PCI Express, resulting in high throughput low-latency transfers which allow for quick compute of complex calculations requiring high accuracy;
● OpenCL Support: OpenCL has become the compute programming language of choice among developers looking to take full advantage of the combined parallel processing capabilities of the FirePro S10000. This has accelerated computer-aided design (CAD), computer-aided engineering (CAE), and media and entertainment (M&E) software, changing the way professionals work thanks to performance and functionality improvements.
Clicar para expandir...
http://www.techpowerup.com/175362/AMD-Introduces-the-FirePro-S10000-Server-Graphics-Card.html


23kdshg.png


If you look at the specs of the S10000 compared to the Nvidia Tesla M2090, the S10000 crushes the M2090 on DP FP performance per watt by about 33%, and the K10 fares far far worse due to it’s abysmal DP performance. On SP FP the S10000 about doubles the M2090 on performance per watt, but loses to the K10 on that count fairly comprehensively. If the K20 comes out with the specs that C’t discovered, it should trounce the S10000 on DP performance per watt, and be a little ahead on SP performance per watt.
Clicar para expandir...
 
Bem já venderam 420 unidades da FirePro S10000.

Powered by 420 AMD FirePro S10000 dual-GPU server graphics cards based on AMD Graphics Core Next Architecture, the SANAM supercomputer redefines supercomputing with its incredible power efficiency.
Capable of sustaining 420 TFLOPS, providing a system energy efficiency of over 2.3 GFLOPS per watt and performing 2,351 million calculations per second per watt, the SANAM supercomputer is shifting the industry mindset of determining performance through FLOPS to focusing on eco-conscious measurements like performance-per-watt.

SANAM is a joint project of Frankfurt Institute for Advanced Studies and King Abdulaziz City for Science and Technology (KACST) in Riyadh, Saudi Arabia. As an integral part of the high-speed cluster (HSC) project, Adtech Global provided technical research to identify a systems solution that would not only work for the high-speed cluster HSC application, but could also provide long-term development and modifications opportunities.

Four Maturing Tools for HPC Developers


● Accelereyes ArrayFire: Accelereyes is dedicated to delivering fast, simple GPU software. The general availability release of ArrayFire, a GPU software acceleration library that provides hundreds of functions already optimized for speed by top GPU computing experts, allows for easy integration into C, C++, Fortran and Python applications;


● Portland Group (PGI) Accelerator compilers: PGI Accelerator Fortran, C and C++ compilers target the AMD line of APUs as well as the AMD line of discrete GPU accelerators. PGI continues to work closely with AMD to extend its PGI Accelerator directive-based compilers. The goal is to generate code directly for AMD GPU accelerators, and to generate heterogeneous x64+GPU executable files that automatically use both the CPU and GPU compute capabilities of AMD APUs;


● CAPS Entreprise HMPP compiler: CAPS Entreprise is a leading provider of solutions for deploying applications on "many-core" systems. CAPS source-to-source HMPP compiler is based on C, C++, and Fortran directives and supports OpenACC and OpenHMPP standards. With help from AMD, the compiler incorporates a powerful OpenCL parallel data generator;


● AMD CodeXL: AMD CodeXL is a comprehensive tool suite that enables developers to harness the benefits of AMD CPUs, GPUs and APUs. It includes powerful GPU debugging, comprehensive GPU and CPU profiling, and static OpenCL kernel analysis capabilities, enhancing accessibility for software developers to enter the era of heterogeneous computing. AMD CodeXL is available as both a Visual Studio extension and as a standalone user interface application for Windows and Linux.
Clicar para expandir...
http://www.techpowerup.com/175565/A...cs-Redefining-Supercomputing-Performance.html

Não contando com algo semelhante ao CUDA que já tem algum tempo no mercado, e tendo estado de algum modo "afastada" durante uns anos deste mercado, até é de estranhar tão rápida adopção.
 
Inicie sessão ou registe-se para poder participar.
Back
Topo