GPU Comparison
RADEON
AMD Radeon HD 6770
CORE STATE
Juniper
VRAM
1024 MB
CLOCK SPEED
—
TDP
108 W
BUS WIDTH
128 bit
ARCHITECTURE
TeraScale 2
PROCESS
40 nm
LAUNCH DATE
2011
VS
GEFORCE
H200 NVL
CORE STATE
GH100
VRAM
141 GB
CLOCK SPEED
1785 MHz
TDP
600 W
BUS WIDTH
6144 bit
ARCHITECTURE
Hopper
PROCESS
5 nm
LAUNCH DATE
2024
PERFORMANCE BENCHMARKS
geekbench_opencl
DETAILED SPECIFICATIONS
SPECIFICATION
HD 6770
H200 NVL
Core Specs
Shading Units
800
16,896
+2012.0%
Shaders
800
16,896
+2012.0%
TMUs
40
528
+1220.0%
ROPs
16
24
+50.0%
Compute Units
10
—
SM Count
—
132
Clocks
Base Clock
—
1365 MHz
Boost Clock
—
1785 MHz
GPU Clock
850 MHz
—
Memory Clock
1200 MHz
4.8 Gbps effective
1593 MHz
6.4 Gbps effective
Memory
Memory Size
1024 MB
141 GB
VRAM (MB)
1,024
144,384
+14000.0%
Memory Type
GDDR5
HBM3e
Memory Bus
128 bit
6144 bit
Bandwidth
76.80 GB/s
4.89 TB/s
Cache
L1 Cache
8 KB (per CU)
256 KB (per SM)
L2 Cache
256 KB
50 MB
Performance
Pixel Rate
13.60 GPixel/s
42.84 GPixel/s
Texture Rate
34.00 GTexel/s
942.5 GTexel/s
FP32 (TFLOPS)
1,360.0 GFLOPS
60.32 TFLOPS
FP64 (TFLOPS)
—
30.16 TFLOPS (1:2)
FP16 (TFLOPS)
—
241.3 TFLOPS (4:1)
AI/RT
Tensor Cores
—
528
Power
TDP
108 W
600 W
TDP (W)
108
600
+455.6%
Suggested PSU
300 W
1000 W
Power Connectors
1x 6-pin
8-pin EPS
Architecture
Architecture
TeraScale 2
Hopper
GPU Name
Juniper
GH100
Generation
Northern Islands
(HD 6700)
Server Hopper
(Hxx)
Process Size
40 nm
5 nm
Transistors
1,040 million
80,000 million
Die Size
166 mm²
814 mm²
Foundry
TSMC
TSMC
Density
6.3M / mm²
98.3M / mm²
API Support
DirectX
11.2 (11_0)
—
OpenGL
4.4
—
OpenCL
1.2
3.0
CUDA
—
9.0
Shader Model
5.0
—
Physical
Slot Width
Dual-slot
Dual-slot
Length
198 mm
7.8 inches
267 mm
10.5 inches
Height
—
111 mm
4.4 inches
Outputs
2x DVI1x HDMI 1.3a2x mini-DisplayPort 1.1
No outputs
Bus Interface
PCIe 2.0 x16
PCIe 5.0 x16
Other
Launch Price
129 USD
—
Production
End-of-life
Active
Predecessor
Evergreen
Server Ada
Successor
Southern Islands
Server Blackwell