GPU Comparison

NVIDIA
GEFORCE

NVIDIA CMP 90HX

CORE STATE GA102
VRAM 10 GB
CLOCK SPEED 1710 MHz
TDP 320 W
BUS WIDTH 320 bit
ARCHITECTURE Ampere
nm
PROCESS 8 nm
LAUNCH DATE 2021
VS
NVIDIA
GEFORCE

L40S

CORE STATE AD102
VRAM 48 GB
CLOCK SPEED 2520 MHz
TDP 300 W
BUS WIDTH 384 bit
ARCHITECTURE Ada Lovelace
nm
PROCESS 5 nm
LAUNCH DATE 2022

PERFORMANCE BENCHMARKS

geekbench_opencl
69,000
330,727
geekbench_vulkan
N/A
260,799

Analysis: NVIDIA CMP 90HX vs NVIDIA L40S

NVIDIA L40S (NVIDIA) and the NVIDIA CMP 90HX achieve almost equivalent rendering performance in our head-to-head test. Any frame rate differences between them generally land below 5-10%, rendering any a good selection. The equality renders the decision nuanced. Other variables turn more relevant. Price frequently influences the scales.

Over focusing on slight frame rate gains, prospective builders could examine alternative factors. Power efficiency, acoustics, build quality, and after-sales quality often play a role greater than minor frame rate differences. These variables might influence the decision. Evaluate past only performance. This entire package counts.

Game performance performance also indicate close results between NVIDIA L40S (NVIDIA) and the NVIDIA CMP 90HX. Smoothness variations typically fall inside single digits. Such slight differences are hardly perceptible during everyday gaming. Each GPUs provide capable experiences. Those who game could choose confidently between both cards.

Finally, buyers could decide based on price instead of pure frame rates exclusively. Each NVIDIA L40S (NVIDIA) and the NVIDIA CMP 90HX offer solid gaming capability for the target price points. The choice rests on particular requirements. Either option is valid. You won't go badly with these options.

DETAILED SPECIFICATIONS

SPECIFICATION
CMP 90HX
L40S
Core Specs
Shading Units
6,400
18,176 +184.0%
Shaders
6,400
18,176 +184.0%
TMUs
200
568 +184.0%
ROPs
80
192 +140.0%
SM Count
50
142 +184.0%
Clocks
Base Clock
1500 MHz
1110 MHz
Boost Clock
1710 MHz
2520 MHz
Memory Clock
1188 MHz 19 Gbps effective
2250 MHz 18 Gbps effective
Memory
Memory Size
10 GB
48 GB
VRAM (MB)
10,240
49,152 +380.0%
Memory Type
GDDR6X
GDDR6
Memory Bus
320 bit
384 bit
Bandwidth
760.3 GB/s
864.0 GB/s
Cache
L1 Cache
128 KB (per SM)
128 KB (per SM)
L2 Cache
5 MB
48 MB
Performance
Pixel Rate
136.8 GPixel/s
483.8 GPixel/s
Texture Rate
342.0 GTexel/s
1,431.4 GTexel/s
FP32 (TFLOPS)
21.89 TFLOPS
91.61 TFLOPS
FP64 (TFLOPS)
342.0 GFLOPS (1:64)
1,431.4 GFLOPS (1:64)
FP16 (TFLOPS)
21.89 TFLOPS (1:1)
91.61 TFLOPS (1:1)
AI/RT
RT Cores
50
142 +184.0%
Tensor Cores
200
568 +184.0%
Power
TDP
320 W
300 W
TDP (W)
320
300 -6.3%
Suggested PSU
700 W
700 W
Power Connectors
2x 8-pin
1x 16-pin
Architecture
Architecture
Ampere
Ada Lovelace
GPU Name
GA102
AD102
Generation
Mining GPUs
Server Ada (Lxx)
Process Size
8 nm
5 nm
Transistors
28,300 million
76,300 million
Die Size
628 mm²
609 mm²
Foundry
Samsung
TSMC
Density
45.1M / mm²
125.3M / mm²
API Support
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
3.0
3.0
CUDA
8.6
8.9
Shader Model
6.8
6.8
Physical
Slot Width
Dual-slot
Dual-slot
Length
285 mm 11.2 inches
267 mm 10.5 inches
Height
112 mm 4.4 inches
111 mm 4.4 inches
Outputs
No outputs
1x HDMI 2.13x DisplayPort 1.4a
Bus Interface
PCIe 1.0 x4
PCIe 4.0 x16
Other
Production
End-of-life
End-of-life
Predecessor
Server Ampere
Successor
Server Hopper
View CMP 90HX Details View L40S Details