ARC

Intel H3C XG310

Intel graphics card specifications and benchmark scores

8 GB
VRAM
1100
MHz Boost
300W
TDP
128
Bus Width

At a Glance

Intel
VRAM 8 GB
Boost Clock 1,100 MHz
Shaders 768
Bus Width 128-bit
TDP 300W
Memory Type LPDDR4X
Architecture Generation 12.1
nm
Process 10 nm
Released Nov 2020

Intel H3C XG310 Specifications

H3C XG310 GPU Core

Shader units and compute resources

The Intel H3C XG310 GPU core specifications define its raw processing power for graphics and compute workloads. Shading units (also called CUDA cores, stream processors, or execution units depending on manufacturer) handle the parallel calculations required for rendering. TMUs (Texture Mapping Units) process texture data, while ROPs (Render Output Units) handle final pixel output. Higher shader counts generally translate to better GPU benchmark performance, especially in demanding games and 3D applications.

Shading Units
768
Shaders
768
TMUs
48
ROPs
24
Execution Units
96

H3C XG310 Clock Speeds

GPU and memory frequencies

Clock speeds directly impact the H3C XG310's performance in GPU benchmarks and real-world gaming. The base clock represents the minimum guaranteed frequency, while the boost clock indicates peak performance under optimal thermal conditions. Memory clock speed affects texture loading and frame buffer operations. The H3C XG310 by Intel dynamically adjusts frequencies based on workload, temperature, and power limits to maximize performance while maintaining stability.

Base Clock
1050 MHz
Base Clock
1,050 MHz
Boost Clock
1100 MHz
Boost Clock
1,100 MHz
Memory Clock
2133 MHz 4.3 Gbps effective
GDDR GDDR 6X 6X

Intel's H3C XG310 Memory

VRAM capacity and bandwidth

VRAM (Video RAM) is dedicated memory for storing textures, frame buffers, and shader data. The H3C XG310's memory capacity determines how well it handles high-resolution textures and multiple displays. Memory bandwidth, measured in GB/s, affects how quickly data moves between the GPU and VRAM. Higher bandwidth improves performance in memory-intensive scenarios like 4K gaming. The memory bus width and type (GDDR6, GDDR6X, HBM) significantly influence overall GPU benchmark scores.

Memory Size
8 GB
VRAM
8,192 MB
Memory Type
LPDDR4X
VRAM Type
LPDDR4X
Memory Bus
128 bit
Bus Width
128-bit
Bandwidth
68.26 GB/s

H3C XG310 by Intel Cache

On-chip cache hierarchy

On-chip cache provides ultra-fast data access for the H3C XG310, reducing the need to fetch data from slower VRAM. L1 and L2 caches store frequently accessed data close to the compute units. AMD's Infinity Cache (L3) dramatically increases effective bandwidth, improving GPU benchmark performance without requiring wider memory buses. Larger cache sizes help maintain high frame rates in memory-bound scenarios and reduce power consumption by minimizing VRAM accesses.

L2 Cache
1024 KB
Infinity Cache
16 MB

H3C XG310 Theoretical Performance

Compute and fill rates

Theoretical performance metrics provide a baseline for comparing the Intel H3C XG310 against other graphics cards. FP32 (single-precision) performance, measured in TFLOPS, indicates compute capability for gaming and general GPU workloads. FP64 (double-precision) matters for scientific computing. Pixel and texture fill rates determine how quickly the GPU can render complex scenes. While real-world GPU benchmark results depend on many factors, these specifications help predict relative performance levels.

FP32 (Float)
1.690 TFLOPS
FP64 (Double)
422.4 GFLOPS (1:4)
FP16 (Half)
3.379 TFLOPS (2:1)
Pixel Rate
26.40 GPixel/s
Texture Rate
52.80 GTexel/s

Generation 12.1 Architecture & Process

Manufacturing and design details

The Intel H3C XG310 is built on Intel's Generation 12.1 architecture, which defines how the GPU processes graphics and compute workloads. The manufacturing process node affects power efficiency, thermal characteristics, and maximum clock speeds. Smaller process nodes pack more transistors into the same die area, enabling higher performance per watt. Understanding the architecture helps predict how the H3C XG310 will perform in GPU benchmarks compared to previous generations.

Architecture
Generation 12.1
GPU Name
DG1
Process Node
10 nm
Foundry
Intel
Die Size
95 mm²

Intel's H3C XG310 Power & Thermal

TDP and power requirements

Power specifications for the Intel H3C XG310 determine PSU requirements and thermal management needs. TDP (Thermal Design Power) indicates the heat output under typical loads, guiding cooler selection. Power connector requirements ensure adequate power delivery for stable operation during demanding GPU benchmarks. The suggested PSU wattage accounts for the entire system, not just the graphics card. Efficient power delivery enables the H3C XG310 to maintain boost clocks without throttling.

TDP
300 W
TDP
300W
Power Connectors
1x 8-pin
Suggested PSU
700 W

H3C XG310 by Intel Physical & Connectivity

Dimensions and outputs

Physical dimensions of the Intel H3C XG310 are critical for case compatibility. Card length, height, and slot width determine whether it fits in your chassis. The PCIe interface version affects bandwidth for communication with the CPU. Display outputs define monitor connectivity options, with modern cards supporting multiple high-resolution displays simultaneously. Verify these specifications against your case and motherboard before purchasing to ensure a proper fit.

Slot Width
Single-slot
Bus Interface
PCIe 3.0 x16
Display Outputs
No outputs
Display Outputs
No outputs

Intel API Support

Graphics and compute APIs

API support determines which games and applications can fully utilize the Intel H3C XG310. DirectX 12 Ultimate enables advanced features like ray tracing and variable rate shading. Vulkan provides cross-platform graphics capabilities with low-level hardware access. OpenGL remains important for professional applications and older games. CUDA (NVIDIA) and OpenCL enable GPU compute for video editing, 3D rendering, and scientific applications. Higher API versions unlock newer graphical features in GPU benchmarks and games.

DirectX
12 (12_1)
DirectX
12 (12_1)
OpenGL
4.6
OpenGL
4.6
Vulkan
1.4
Vulkan
1.4
OpenCL
3.0
Shader Model
6.6

H3C XG310 Product Information

Release and pricing details

The Intel H3C XG310 is manufactured by Intel as part of their graphics card lineup. Release date and launch pricing provide context for comparing GPU benchmark results with competing products from the same era. Understanding the product lifecycle helps evaluate whether the H3C XG310 by Intel represents good value at current market prices. Predecessor and successor information aids in tracking generational improvements and planning future upgrades.

Manufacturer
Intel
Release Date
Nov 2020
Production
End-of-life
Predecessor
Knights Corner
Successor
Data Center GPU

H3C XG310 Benchmark Scores

No benchmark data available for this GPU.

About Intel H3C XG310

The Intel H3C XG310 is a curious entry in the hardware landscape, a single-slot accelerator built on Intel’s Generation 12.1 architecture and the DG1 chip, fabricated on a 10 nm process with a die size of 95 mm². It was released on 2020-11-10 and is now marked as end-of-life, positioning it as a transitional product between the Knights Corner predecessor and the Data Center GPU successor. The data shows a device with no display outputs, no benchmark scores, and no nearest rivals listed, which makes its analysis purely architectural and feature-based rather than performance-driven.

Benchmark Performance

The benchmark data for the Intel H3C XG310 is conspicuously empty; the FACT PACK lists an average benchmark score of 0 and no entries in the benchmarks array. The percentile versus all GPUs is 50, which suggests a median standing in the overall distribution, but without actual scores, this percentile is more of a placeholder than a measured result. The shading units total 768, with 48 texture mapping units and 24 raster operations pipelines, yielding a pixel rate of 26.40 GPixel/s and a texture rate of 52.80 GTexel/s. The FP32 compute is 1.690 TFLOPS, while FP16 reaches 3.379 TFLOPS with a 2:1 ratio, indicating that the hardware can double throughput on half-precision workloads, a common feature for certain compute tasks.

Since no rival scores or deltaPct values exist, the data cannot be compared with percentage deltas. The lack of benchmarks means that any interpretation of real-world speed is speculative; the raw numbers suggest a modest compute capability, but without measured results, a definitive ranking is impossible. The FP32 figure of 1.690 TFLOPS is low by modern standards, but the FP16 rate of 3.379 TFLOPS hints at a design leaning toward specific workloads where half-precision is acceptable. The 50th percentile placement, however, implies that if benchmarks were run, it would sit in the middle of the pack, but that is an inference from the percentile field, not a tested outcome. The absence of any rivals in the nearestRivals array further complicates any comparative analysis, leaving the XG310 as a theoretical entity with no validated performance anchor.

How It Compares

Without any nearest rivals listed in the FACT PACK, there is no direct competitor to position against. The data provides no names, scores, or deltaPct values, so a comparative paragraph per rival is impossible. The only relational data points are the predecessor (Knights Corner) and successor (Data Center GPU), which are architectural lineage markers rather than performance benchmarks. Knights Corner was a different era of Intel computing, while the Data Center GPU successor implies a more refined or capable product, but no scores quantify that gap.

The XG310’s position is thus isolated; it does not compete with any listed GPU in the benchmark database for this entry. The percentile of 50 versus all GPUs is a global reference, but without specific rivals, the reader cannot gauge whether it beats or loses to any particular card. This absence of comparative data forces a neutral stance: the XG310 exists as a hardware definition, but its market or performance standing remains unquantified. The fact that it has no display outputs further narrows its role — it is not a consumer graphics card in the traditional sense, but rather a compute-oriented accelerator, which may explain why no typical gaming rivals are listed.

Power and Cooling

The thermal design power (TDP) is listed as 300 W, which is a substantial power draw for a single-slot card. The suggested power supply unit is 700 W, indicating that the system builder must account for a robust PSU to handle not just the card but the rest of the platform. The power connector requirement is a single 8-pin, which is relatively simple given the 300 W TDP; this suggests that the card is designed to draw most of its power from the PCIe slot and the one connector, though the exact distribution is not specified. The slot width is single-slot, which is notable because dissipating 300 W of heat in a single-slot form factor requires an efficient cooling solution, but the FACT PACK does not detail the cooler type or its effectiveness.

The bus interface is PCIe 3.0 x16, which is a standard connection, but the power draw of 300 W with a 700 W PSU recommendation implies that the card is not meant for low-power systems. The lack of display outputs reinforces that this is not a typical graphics card for monitors, so the power is directed entirely toward compute tasks. The single 8-pin connector is a minimal requirement for 300 W, which may indicate that the card has strict power limits or that the board design is optimized for a specific server or workstation environment. The data shows no additional power details, so any discussion of efficiency or thermal behavior is qualitative; the numbers only provide the TDP, PSU suggestion, and connector type.

FAQ

Q: What is the TDP of the Intel H3C XG310?

A: The TDP is 300 W, and the suggested power supply is 700 W, with a single 8-pin power connector required.

Q: Does the XG310 support modern graphics APIs?

A: Yes, it supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4, according to the FACT PACK.

Q: What is the memory configuration of this card?

A: It has 8 GB of LPDDR4X memory with a 128-bit bus width, providing a bandwidth of 68.26 GB/s, and memory clocked at 2133 MHz with 4.3 Gbps effective.

Q: Are there any display outputs on the XG310?

A: No, the FACT PACK lists "No outputs" for display outputs, meaning it is not intended for direct monitor connection.

Q: What is the compute performance in FP32 and FP16?

A: The FP32 performance is 1.690 TFLOPS, while FP16 reaches 3.379 TFLOPS with a 2:1 ratio.

Q: What is the production status of this product?

A: It is end-of-life, released on 2020-11-10, with a predecessor of Knights Corner and a successor of Data Center GPU.

Ray Tracing and Feature Set

The Intel H3C XG310 does not have any listed ray tracing cores or tensor cores in the FACT PACK; the fields for rtCores and tensorCores are both null. This absence is significant because it means the hardware has no dedicated acceleration for ray-traced workloads or AI tensor operations, which are common in modern graphics and compute cards. The API support includes DirectX 12 (12_1), which can theoretically handle ray tracing at a software level, but without hardware RT cores, performance would rely on the shader units, which number 768. The FP16 capability at 3.379 TFLOPS (2:1) suggests some compute versatility, but without tensor cores, machine learning tasks would be limited to general shader compute.

The feature set is otherwise defined by the shading units, TMUs, and ROPs, with a pixel rate of 26.40 GPixel/s and a texture rate of 52.80 GTexel/s. The DirectX 12 (12_1) support indicates a feature level that includes some advanced rasterization, but the lack of RT and tensor cores positions this card as a basic compute unit rather than a graphics or AI accelerator. The Vulkan 1.4 support is recent, but again, without dedicated cores, any ray tracing would be emulated via compute shaders, which is inefficient. The data shows no ray tracing performance metrics, so the only conclusion is that the card is not designed for such workloads, and its feature set is limited to traditional rasterization and generic compute.

Who Should Consider It

Given the absence of benchmark scores and rival comparisons, the recommendation must be grounded in the raw specifications. The FP32 compute of 1.690 TFLOPS is modest, so the XG310 is not suited for high-end gaming at 4K or even 1440p with demanding settings; the pixel rate of 26.40 GPixel/s and texture rate of 52.80 GTexel/s suggest that it could handle lower resolutions like 1080p with lighter settings, but the lack of display outputs means it cannot drive a monitor directly. This card is therefore not for a typical gamer building a desktop PC; it is a compute accelerator for server or workstation environments where processing happens headlessly.

The 8 GB of LPDDR4X memory with 68.26 GB/s bandwidth is adequate for moderate data sets, but the 128-bit bus width limits memory-intensive workloads. The 300 W TDP and 700 W PSU requirement indicate it is for a system with a robust power supply, likely in a rack or tower server. The single-slot form factor is advantageous for dense configurations, but the cooling solution must handle 300 W, which is a challenge. The end-of-life status means it is not a future-proof investment, so only those with legacy compute needs or specific compatibility requirements should consider it, and even then, the lack of RT and tensor cores limits its use to basic FP32/FP16 tasks.

Memory Subsystem

The memory subsystem of the Intel H3C XG310 consists of 8 GB of LPDDR4X type memory, which is a low-power variant typically used in mobile devices, but here it is deployed on a 128-bit bus. The bus width of 128 bit is relatively narrow for a card with 8 GB, and the resulting bandwidth is 68.26 GB/s, which is the product of the memory clock at 2133 MHz with an effective data rate of 4.3 Gbps. This bandwidth is modest compared to high-end GPUs that often exceed 500 GB/s, but for a compute card with a 1.690 TFLOPS FP32 throughput, it is proportionate. The memory clock of 2133 MHz is the base frequency, and the effective rate of 4.3 Gbps accounts for the double data rate nature of LPDDR4X.

For high resolutions or large textures, 68.26 GB/s would be a bottleneck if the card were used for graphics, but since it has no display outputs, this is moot. In compute workloads, the bandwidth limits how fast data can be fed to the 768 shaders, so memory-bound tasks would see reduced performance. The 8 GB capacity is sufficient for many datasets, but the 128-bit bus means that memory access patterns must be efficient to avoid stalls. The lack of a larger bus or higher bandwidth is a clear design constraint, and the data shows no indication of a memory overclock or alternative configurations. The LPDDR4X type is also notable for its lower power consumption, which might offset some of the 300 W TDP, but the exact power split is not provided.

The NVIDIA Equivalent of H3C XG310

Looking for a similar graphics card from NVIDIA? The NVIDIA GeForce GTX 1650 TU116 offers comparable performance and features in the NVIDIA lineup.

NVIDIA GeForce GTX 1650 TU116

NVIDIA • 4 GB VRAM

View Specs Compare

Popular Intel H3C XG310 Comparisons

See how the H3C XG310 stacks up against similar graphics cards from the same generation and competing brands.

Compare H3C XG310 with Other GPUs

Select another GPU to compare specifications and benchmarks side-by-side.

Browse GPUs