Report an Error

AMD FireStream 9350

Graphics Processor
Cypress
Cores
1440
TMUs
72
ROPs
32
Memory Size
2 GB
Memory Type
GDDR5
Bus Width
256 bit
The FireStream 9350 was a professional graphics card by AMD, launched in June 2010. Built on the 40 nm process, and based on the Cypress graphics processor, in its Cypress PRO GL variant, the card supports DirectX 11.2. The Cypress graphics processor is a large chip with a die area of 334 mm² and 2,154 million transistors. Unlike the fully unlocked Radeon HD 6870 1600SP Edition, which uses the same GPU but has all 1600 shaders enabled, AMD has disabled some shading units on the FireStream 9350 to reach the product's target shader count. It features 1440 shading units, 72 texture mapping units and 32 ROPs. AMD has placed 2,048 MB GDDR5 memory on the card, which are connected using a 256-bit memory interface. The GPU is operating at a frequency of 700 MHz, memory is running at 1000 MHz.
Being a single-slot card, the AMD FireStream 9350 draws power from 1x 6-pin power connectors, with power draw rated at 150 W maximum. Display outputs include: 1x DisplayPort. FireStream 9350 is connected to the rest of the system using a PCI-Express 2.0 x16 interface. The card measures 241 mm in length, and features a single-slot cooling solution.

Graphics Processor

GPU Name
Cypress
GPU Variant
Cypress PRO GL
Architecture
TeraScale 2
Foundry
TSMC
Process Size
40 nm
Transistors
2,154 million
Die Size
334 mm²

Graphics Card

Release Date
Jun 1st, 2010
Generation
FireStream
Production
End-of-life
Bus Interface
PCIe 2.0 x16

Relative Performance

7%
GeForce 210
9%
GeForce 9400 GT
11%
Radeon HD 4550
14%
Radeon HD 5450
17%
Radeon HD 6450
18%
GeForce GT 520
22%
GeForce GT 220
29%
GeForce GT 430
29%
Radeon HD 5570
32%
Radeon HD 4670
33%
GeForce GT 440
34%
GeForce GT 240
39%
GeForce 9600 GT
41%
Radeon HD 5670
44%
GeForce GT 640
46%
GeForce 9800 GT
48%
Radeon HD 6670
49%
Radeon HD 4830
53%
Radeon HD 4770
55%
Radeon HD 4850
57%
GeForce GTS 250
58%
GeForce GTS 450
60%
Radeon HD 5750
69%
Radeon HD 7750
70%
Radeon HD 5770
71%
GeForce GTX 260
72%
Radeon HD 4870
72%
Radeon Vega 8
73%
GeForce GTX 550 Ti
73%
GeForce GTX 650
77%
Radeon HD 5830
81%
Radeon HD 6790
83%
Radeon HD 4890
86%
GeForce GTX 460
87%
Radeon RX Vega 11
87%
GeForce GT 1030
88%
GeForce GTX 275
88%
Radeon HD 7770 GHz Edition
89%
GeForce GTX 280
90%
GeForce GTX 465
95%
Radeon HD 6850
97%
GeForce GTX 285
100%
FireStream 9350
104%
Radeon HD 5850
105%
Radeon HD 7790
105%
GeForce GTX 650 Ti
110%
Radeon RX 550
110%
GeForce GTX 470
114%
Radeon HD 6870
122%
Radeon HD 5870
126%
GeForce GTX 560 Ti
126%
Radeon HD 4870 X2
129%
GeForce GTX 750 Ti
129%
Radeon HD 6950
134%
GeForce GTX 295
135%
GeForce GTX 650 Ti Boost
136%
Radeon HD 7850
139%
GeForce GTX 480
145%
Radeon HD 6970
148%
Radeon R7 265
150%
Radeon RX 460
150%
Radeon R7 370
151%
GeForce GTX 660
151%
GeForce GTX 570
154%
Radeon RX 560
163%
GeForce GTX 950
165%
Radeon HD 7870 GHz Edition
169%
Radeon R9 270X
171%
GeForce GTX 660 Ti
172%
GeForce GTX 580
173%
GeForce GTX 1050
173%
Radeon HD 7950
177%
Radeon HD 5970
182%
GeForce GTX 760
196%
GeForce GTX 670
201%
GeForce GTX 960
206%
Radeon R9 380
207%
Radeon R9 285
209%
Radeon HD 7970
211%
GeForce GTX 680
216%
GeForce GTX 1050 Ti
222%
GeForce GTX 770
227%
Radeon HD 6990
233%
Radeon R9 280X
236%
GeForce GTX 590
236%
Radeon HD 7970 GHz Edition
261%
GeForce GTX 780
271%
GeForce GTX 1650
288%
Radeon RX 470
292%
Radeon R9 290
311%
Radeon R9 390
313%
Radeon R9 290X
317%
GeForce GTX 970
321%
GeForce GTX TITAN
324%
Radeon RX 570
326%
GeForce GTX 780 Ti
330%
Radeon R9 390X
332%
Radeon HD 7990
333%
Radeon RX 480
336%
GeForce GTX 690
354%
Radeon RX 580
361%
GeForce GTX 980
366%
GeForce GTX 1060 6 GB
366%
Radeon R9 FURY
368%
Radeon RX 590
403%
Radeon R9 295X2
410%
Radeon R9 FURY X
417%
GeForce GTX 980 Ti
448%
GeForce GTX TITAN X
470%
GeForce GTX 1660 Ti
472%
GeForce GTX 1070
493%
Radeon RX Vega 56
535%
GeForce GTX 1070 Ti
549%
Radeon RX Vega 64
549%
GeForce RTX 2060
562%
GeForce GTX 1080
646%
Radeon VII
646%
GeForce RTX 2070
677%
TITAN X Pascal
694%
GeForce GTX 1080 Ti
750%
GeForce RTX 2080
868%
GeForce RTX 2080 Ti
Based on TPU review data: "Performance Summary" at 1920x1080
Performance estimated based on architecture, shader count and clocks.

Clock Speeds

GPU Clock
700 MHz
Memory Clock
1000 MHz
4000 MHz effective

Memory

Memory Size
2 GB
Memory Type
GDDR5
Memory Bus
256 bit
Bandwidth
128.0 GB/s

Render Config

Shading Units
1440
TMUs
72
ROPs
32
Compute Units
18
L1 Cache
8 KB (per CU)
L2 Cache
512 KB

Theoretical Performance

Pixel Rate
22.40 GPixel/s
Texture Rate
50.40 GTexel/s
FP32 (float) performance
2.016 TFLOPS
FP64 (double) performance
403.2 GFLOPS (1:5)

Board Design

Slot Width
Single-slot
Length
9.5 inches
241 mm
TDP
150 W
Outputs
1x DisplayPort
Power Connectors
1x 6-pin

Graphics Features

DirectX
11.2 (11_0)
OpenGL
4.4
OpenCL
1.2
Vulkan
N/A
Shader Model
5.0

Cypress GPU Notes

Architecture Codename: Evergreen
Graphics/Compute: GFX4
Display Core Engine: 4.0
Unified Video Decoder: 2.3