Home / NVIDIA / NVIDIA GeForce RTX 3060 3840SP: Performance and Specs

NVIDIA GeForce RTX 3060 3840SP

Name: NVIDIA GeForce RTX 3060 3840SP
Brand: NVIDIA

NVIDIA GeForce RTX 3060 3840SP graphics card review

NVIDIA GeForce RTX 3060 3840SP: A Rare OEM Version with a Fully Active GA106

The GeForce RTX 3060 3840SP is one of the most unusual versions of the RTX 3060 family. It did not receive a separate full retail launch and was predominantly found in pre-built OEM systems. The main difference from the standard RTX 3060 is the fully active GA106 die with 3840 CUDA cores instead of 3584.

How It Differs from the Standard RTX 3060

The standard RTX 3060 uses 28 active SMs, while the 3840SP version has all 30 enabled. Additionally, the number of Tensor cores has been increased to 120, RT cores to 30, and texture units to 120.

Version	CUDA	SM	RT Cores	Tensor Cores
RTX 3060	3584	28	28	112
RTX 3060 3840SP	3840	30	30	120

The clock speeds of the rare version are also higher: the Boost reaches about 1852 MHz, resulting in a theoretical FP32 performance of around 14.2 TFLOPS compared to approximately 12.7 TFLOPS for the standard RTX 3060.

Why It Only Has 6 GB of Memory

The base OEM configuration of the RTX 3060 3840SP features 6 GB of GDDR6, a 192-bit bus, and a bandwidth of around 336 GB/s.

This makes the model quite peculiar: it has more computing units than the standard RTX 3060 but half the memory. There were also separate variants with 12 GB, so the specifications of a particular OEM card may vary.

How Much Faster It Is

The additional CUDA cores and higher clock speeds provide a slight performance boost over the standard RTX 3060, but there is no revolution here. The 3840SP version remains a representative of the Ampere architecture and its performance level is significantly below that of the RTX 3060 Ti.

In practical terms, it’s more interesting to view it not as a standalone product, but as a rare hardware revision of the RTX 3060.

Conclusion

The GeForce RTX 3060 3840SP is a rare OEM version with a fully active GA106.

It features more CUDA, RT, and Tensor cores than the standard RTX 3060, but was most often equipped with only 6 GB of memory. It did not have a separate mass launch, so today such a card is primarily interesting as an unusual variant of Ampere and a rare specimen in the RTX 3060 family.

Basic

Label Name

NVIDIA

Platform

Desktop

Launch Date

January 2021

Model Name

GeForce RTX 3060 3840SP

Generation

GeForce 30

Base Clock

1627MHz

Boost Clock

1852MHz

Bus Interface

PCIe 4.0 x16

Transistors

12,000 million

RT Cores

Tensor Cores

Tensor Cores are specialized processing units designed specifically for deep learning, providing higher training and inference performance compared to FP32 training. They enable rapid computations in areas such as computer vision, natural language processing, speech recognition, text-to-speech conversion, and personalized recommendations. The two most notable applications of Tensor Cores are DLSS (Deep Learning Super Sampling) and AI Denoiser for noise reduction.

120

TMUs

Texture Mapping Units (TMUs) serve as components of the GPU, which are capable of rotating, scaling, and distorting binary images, and then placing them as textures onto any plane of a given 3D model. This process is called texture mapping.

120

Foundry

Samsung

Process Size

8 nm

Architecture

Ampere

Memory Specifications

Memory Size

6GB

Memory Type

GDDR6

Memory Bus

The memory bus width refers to the number of bits of data that the video memory can transfer within a single clock cycle. The larger the bus width, the greater the amount of data that can be transmitted instantaneously, making it one of the crucial parameters of video memory. The memory bandwidth is calculated as: Memory Bandwidth = Memory Frequency x Memory Bus Width / 8. Therefore, when the memory frequencies are similar, the memory bus width will determine the size of the memory bandwidth.

192bit

Memory Clock

1750MHz

Bandwidth

Memory bandwidth refers to the data transfer rate between the graphics chip and the video memory. It is measured in bytes per second, and the formula to calculate it is: memory bandwidth = working frequency × memory bus width / 8 bits.

336.0 GB/s

Display and Media

Outputs

1x HDMI 2.1
3x DisplayPort 1.4a

Theoretical Performance

Pixel Rate

Pixel fill rate refers to the number of pixels a graphics processing unit (GPU) can render per second, measured in MPixels/s (million pixels per second) or GPixels/s (billion pixels per second). It is the most commonly used metric to evaluate the pixel processing performance of a graphics card.

88.90 GPixel/s

Texture Rate

Texture fill rate refers to the number of texture map elements (texels) that a GPU can map to pixels in a single second.

222.2 GTexel/s

FP16 (half)

An important metric for measuring GPU performance is floating-point computing capability. Half-precision floating-point numbers (16-bit) are used for applications like machine learning, where lower precision is acceptable. Single-precision floating-point numbers (32-bit) are used for common multimedia and graphics processing tasks, while double-precision floating-point numbers (64-bit) are required for scientific computing that demands a wide numeric range and high accuracy.

14.22 TFLOPS

FP64 (double)

An important metric for measuring GPU performance is floating-point computing capability. Double-precision floating-point numbers (64-bit) are required for scientific computing that demands a wide numeric range and high accuracy, while single-precision floating-point numbers (32-bit) are used for common multimedia and graphics processing tasks. Half-precision floating-point numbers (16-bit) are used for applications like machine learning, where lower precision is acceptable.

222.2 GFLOPS

FP32 (float)

An important metric for measuring GPU performance is floating-point computing capability. Single-precision floating-point numbers (32-bit) are used for common multimedia and graphics processing tasks, while double-precision floating-point numbers (64-bit) are required for scientific computing that demands a wide numeric range and high accuracy. Half-precision floating-point numbers (16-bit) are used for applications like machine learning, where lower precision is acceptable.

14.504 TFLOPS

Miscellaneous

SM Count

Multiple Streaming Processors (SPs), along with other resources, form a Streaming Multiprocessor (SM), which is also referred to as a GPU's major core. These additional resources include components such as warp schedulers, registers, and shared memory. The SM can be considered the heart of the GPU, similar to a CPU core, with registers and shared memory being scarce resources within the SM.

Shading Units

The most fundamental processing unit is the Streaming Processor (SP), where specific instructions and tasks are executed. GPUs perform parallel computing, which means multiple SPs work simultaneously to process tasks.

3840

L1 Cache

128 KB (per SM)

L2 Cache

3MB

TDP

185W

Vulkan Version

Vulkan is a cross-platform graphics and compute API by Khronos Group, offering high performance and low CPU overhead. It lets developers control the GPU directly, reduces rendering overhead, and supports multi-threading and multi-core processors.

1.3

OpenCL Version

3.0

OpenGL

4.6

CUDA

8.6

DirectX

12 Ultimate (12_2)

Power Connectors

1x 12-pin

ROPs

The Raster Operations Pipeline (ROPs) is primarily responsible for handling lighting and reflection calculations in games, as well as managing effects like anti-aliasing (AA), high resolution, smoke, and fire. The more demanding the anti-aliasing and lighting effects in a game, the higher the performance requirements for the ROPs; otherwise, it may result in a sharp drop in frame rate.

Shader Model

6.7

Suggested PSU

450W

Benchmarks

FP32 (float)

Score

14.504 TFLOPS

Compared to Other GPU

FP32 (float) / TFLOPS

GeForce RTX 3070 Mobile

15.651 +7.9%

Arctic Sound M

15.045 +3.7%