Intel HD Graphics P630 Mobile

Intel HD Graphics P630 Mobile is an integrated graphics processor (IGP) from Intel, built on the Kaby Lake GT2 chip using the Generation 9.5 architecture and a 14 nm++ process node. Released on 2016-08-04, it is now end-of-life. The data places it at the 50th percentile of all GPUs, though no nearest rival comparisons are provided, meaning its position is defined by its absolute specifications. With 192 shading units, 24 TMUs, and 3 ROPs, it delivers 422.4 GFLOPS of FP32 compute, which is modest for modern workloads.

How It Compares

The FACT PACK provides no nearestRivals entries, so direct percentage deltas against competitor products are unavailable. However, the percentileVsAllGpus field places it at the 50th percentile, indicating a median standing across the entire GPU landscape. This suggests that while it is not a low-end outlier, it is also far from a performance leader. Its integrated nature (IGP) and system-shared memory mean its real-world standing is heavily dependent on the host platform's memory configuration, which the data lists as "System Dependent" for bandwidth. Without rival scores, the comparison must rely on its raw throughput figures: 422.4 GFLOPS FP32 and 844.8 GFLOPS FP16, which are indicative of a basic entry-level part. The 3 ROPs are a particularly telling constraint, as this is an exceptionally low count that will limit fill-rate-bound scenarios. The 50th percentile ranking, combined with the absence of any rival data, implies that this IGP sits squarely in the middle of the historical GPU distribution, but that median position is achieved through its integration into a broad range of systems rather than through competitive performance.

Who Should Consider It

Given its modest compute capabilities, this IGP is suited for basic desktop productivity, video playback, and light 2D workloads. The 3 ROPs and 3.300 GPixel/s pixel rate limit its ability to handle high-resolution rendering; users should expect to operate at low resolutions and minimal graphics settings for any 3D application. The system-shared memory architecture means that performance scales with the host system's RAM speed and capacity, but the lack of dedicated VRAM caps its potential at higher resolutions. The 192 shading units and 24 TMUs provide enough throughput for simple shader effects and basic texturing, but they are insufficient for modern game engines or GPU-accelerated content creation. It is not a candidate for gaming or GPU-accelerated rendering beyond the most basic tasks. The 15 W TDP and IGP slot width indicate it is intended for power-constrained, portable devices, where the primary use case is web browsing, office applications, and streaming video rather than any form of high-fidelity graphics.

Memory Subsystem

The memory subsystem is entirely system-shared: size, type, and bus width are all listed as "System Shared," with bandwidth noted as "System Dependent." This means the GPU has no dedicated VRAM; it borrows from the host system's main memory. Consequently, memory bandwidth is not a fixed specification but varies with the system's memory configuration, such as the number of channels and the memory clock speed. This design inherently limits performance at high resolutions because the shared bus must contend with CPU memory traffic, and the available bandwidth is not guaranteed. For users aiming for high resolutions, the data indicates that the memory subsystem is a bottleneck, as the bandwidth is not a fixed number but is dependent on external factors. The lack of a dedicated bus width means that the GPU cannot sustain the high data rates required for large framebuffers, making it unsuitable for 4K or even 1440p workloads. The "System Dependent" label is a critical caveat: two systems with the same IGP could exhibit significantly different memory performance based solely on their RAM configuration.

FAQ

Q: What is the architecture of the Intel HD Graphics P630 Mobile?

A: It is based on the Generation 9.5 architecture, built on a 14 nm++ process node, with the Kaby Lake GT2 chip.

Q: What is the TDP of this GPU?

A: The TDP is 15 W, and it is an integrated graphics processor (IGP) with a slot width of IGP.

Q: What API support does it offer?

A: It supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.3.

Q: What is the base and boost clock speed?

A: The base clock is 350 MHz, and the boost clock is 1100 MHz.

Q: What is the production status?

A: The production status is end-of-life, with a release date of 2016-08-04.

Q: Does it have dedicated VRAM?

A: No, its memory size, type, and bus width are all "System Shared," and bandwidth is "System Dependent."

Benchmark Performance

The FACT PACK lists an average benchmark score of 0 and no individual benchmark entries, so performance analysis relies on theoretical throughput. The FP32 compute is 422.4 GFLOPS, while FP16 is 844.8 GFLOPS at a 2:1 ratio, indicating that the hardware supports fast FP16 but FP32 is the primary precision for most workloads. The texture rate is 26.40 GTexel/s, and the pixel rate is 3.300 GPixel/s. With 192 shading units, 24 TMUs, and 3 ROPs, the data shows a configuration that is heavily skewed toward shading and texturing but has very few ROPs, which will bottleneck pixel output. Relative to the 50th percentile standing, these numbers suggest a mid-pack position among all GPUs, but without rival deltas, it is impossible to quantify a percentage lead or deficit. The FP16 output of 844.8 GFLOPS is exactly double the FP32 figure, which is a typical ratio for this generation. The pixel rate of 3.300 GPixel/s, when compared to the texture rate of 26.40 GTexel/s, reveals an 8:1 ratio between texturing and pixel throughput, meaning that scenes with heavy overdraw or complex fragment shading will quickly become fill-rate limited. The 0 average benchmark score is a data artifact indicating that no standardized benchmark results have been recorded, so all assessments must be derived from the theoretical specifications.

Power and Cooling

The TDP is 15 W, which is very low, indicating that cooling requirements are minimal. The slot width is "IGP," meaning it is integrated onto the motherboard and does not occupy a discrete expansion slot. No power connectors are listed (null), and no suggested PSU is provided (null). Because it is an IGP, it draws power from the motherboard's integrated power delivery, not from a separate PSU rail. The 15 W TDP makes it suitable for thin-and-light laptops or compact devices where heat dissipation is constrained. The lack of a discrete power connector means no additional cabling is needed, and the cooling solution can be a simple passive heatsink or a low-profile fan. The absence of a suggested PSU rating further confirms that this part is not intended for systems with a discrete power supply, as it operates entirely within the host platform's power budget.

Ray Tracing and Feature Set

The FACT PACK lists rtCores as null and tensorCores as null, indicating that this GPU has no dedicated ray tracing or tensor core hardware. It relies on the Generation 9.5 architecture's standard shader units for all graphics processing. For API support, it offers DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.3, which means it can run modern graphics APIs but without hardware-accelerated ray tracing. The display outputs are "Portable Device Dependent," meaning the available connectors vary by the device it is integrated into. The bus interface is "Ring Bus," which is the internal interconnect for Intel integrated graphics. The absence of RT and tensor cores means any ray tracing workloads would fall back to compute shaders, but the modest 422.4 GFLOPS FP32 compute makes such workloads impractical. The feature set is thus limited to conventional rasterization, with the API support ensuring compatibility with contemporary software but providing no acceleration for AI-based features like DLSS or ray-traced effects. The DirectX 12 (12_1) support is notable for a 2016 part, but the lack of dedicated hardware for these advanced features means they will run at reduced efficiency.