AMD Radeon Graphics 384SP Mobile

The AMD Radeon Graphics 384SP Mobile is an integrated graphics processor built on the GCN 5.1 architecture, specifically the Vega II IGP generation for Cezanne Mobile platforms. Fabricated on a 7 nm process at TSMC, this chip packs 9,800 million transistors into a 180 mm² die, achieving a transistor density of 54.4M per mm². With a base clock of 300 MHz and a boost clock of 1600 MHz, the GPU delivers a peak FP32 performance of 1,228.8 GFLOPS. Its performance percentile against all GPUs sits at 50, placing it squarely in the middle of the database—a capable integrated solution, but not a gaming powerhouse. The production status is listed as end-of-life, with a release date of April 12, 2021.

Benchmark Performance

The benchmark data for this GPU is sparse, with no direct scores recorded in the database and an average benchmark score of zero. However, its 50th percentile ranking against all GPUs provides a meaningful reference point. This percentile indicates that the Radeon Graphics 384SP Mobile outperforms roughly half of all GPUs ever tracked, which is notable for an integrated part. In practical terms, this places it in the same performance tier as entry-level discrete graphics solutions from previous generations, though the lack of specific rival data means direct percentage comparisons are unavailable. The GPU’s raw compute figures tell a clearer story: 1,228.8 GFLOPS of FP32 performance, supported by a pixel rate of 12.80 GPixel/s and a texture rate of 38.40 GTexel/s. These numbers suggest the GPU can handle light gaming at lower resolutions and settings, but will struggle with demanding modern titles. The FP16 performance of 2.458 TFLOPS (2:1) indicates some compute capability for mixed-precision workloads, though this is not a dedicated AI accelerator. Given the absence of nearest rival data, the performance analysis relies on the architectural specifications: 384 shading units, 24 texture mapping units, and 8 raster output units form a modest configuration that prioritizes efficiency over raw throughput.

How It Compares

The database lists no nearest rivals for this GPU, which limits direct comparative analysis. However, its position as a successor to the Vega IGP and predecessor to the Navi II IGP provides generational context. The Vega II IGP architecture, implemented on the 7 nm node, represents a refinement of the GCN design philosophy. Compared to its predecessor, the Radeon Graphics 384SP Mobile benefits from a more modern manufacturing process, which typically enables higher clock speeds and better power efficiency, though specific performance deltas are not documented. The transition to the Navi II IGP successor would later bring architectural improvements, but this part remains a competent integrated solution for its era. The 384 shading units, while modest by discrete GPU standards, are substantial for an integrated processor, allowing the GPU to handle everyday graphics tasks, video playback, and entry-level gaming. The absence of a dedicated VRAM means performance is inherently linked to system memory, which is a critical factor when considering real-world usage. Without rival scores or delta percentages, the comparison must be framed qualitatively: this GPU sits in the middle of the performance spectrum, suitable for productivity and casual gaming but not for high-refresh-rate or high-detail scenarios.

Who Should Consider It

This GPU is designed for portable devices, as indicated by its "Mobile" designation and "Portable Device Dependent" display outputs. The 45 W TDP suggests it is intended for laptops and similar form factors where power efficiency is paramount. For users with modest gaming expectations—esports titles, older games, or indie releases—the Radeon Graphics 384SP Mobile can deliver playable frame rates at 720p or 1080p with reduced graphical settings. The 1,228.8 GFLOPS of FP32 compute is sufficient for these workloads, though the 8 ROPs and 24 TMUs will limit fill-rate-heavy scenes. Users who prioritize productivity tasks—office applications, web browsing, media consumption—will find this GPU more than adequate. However, for modern AAA games at high settings or 1440p resolution, the integrated nature of this GPU, with system-shared memory, will present significant bottlenecks. The 50th percentile ranking reinforces this assessment: it is a mainstream performer, not a high-end solution. This GPU is best suited for users who need a balanced integrated solution for everyday computing and light gaming, without the power draw or cost of a discrete graphics card.

Power and Cooling

The Radeon Graphics 384SP Mobile has a TDP of 45 W, which is a moderate power envelope for an integrated GPU. This figure represents the maximum thermal design power the cooling solution must dissipate under sustained load. As an IGP (integrated graphics processor), it does not require a discrete power supply recommendation, and the power connectors are listed as "None." The slot width is also designated as "IGP," confirming it is soldered to the motherboard or integrated into the APU package. The 7 nm manufacturing process contributes to power efficiency, allowing the GPU to achieve its 1,600 MHz boost clock within the 45 W envelope. For system builders, the lack of a suggested PSU rating means this GPU will not add significant power draw beyond the host processor’s requirements. Cooling requirements are typically handled by the laptop’s existing thermal solution, which must be designed to accommodate the combined TDP of the CPU and GPU. The end-of-life status suggests this GPU is being phased out, but for systems still using it, the 45 W TDP is manageable within standard mobile chassis designs. Thermal management should be straightforward, as integrated GPUs generally do not require exotic cooling solutions.

FAQ

Q: What is the manufacturing process for this GPU?

A: The Radeon Graphics 384SP Mobile is fabricated on a 7 nm process at TSMC, with a die size of 180 mm² and 9,800 million transistors.

Q: How much dedicated VRAM does this GPU have?

A: It has no dedicated VRAM; the memory size, type, and bus width are all "System Shared," meaning it uses the host system’s RAM, and bandwidth is "System Dependent."

Q: What is the boost clock speed?

A: The GPU has a base clock of 300 MHz and a boost clock of 1600 MHz, delivering 1,228.8 GFLOPS of FP32 performance.

Q: Does this GPU support hardware ray tracing?

A: No, the RT cores field is null, indicating no dedicated ray tracing hardware. Ray tracing would be handled via compute shaders, if at all.

Q: What is the TDP and connector requirement?

A: The TDP is 45 W, and it requires no power connectors, as it is an integrated GPU (IGP) with a slot width also designated as "IGP."

Q: When was this GPU released and what is its status?

A: It was released on April 12, 2021, and is currently listed as end-of-life, succeeding the Vega IGP and preceding the Navi II IGP.

Memory Subsystem

The memory configuration is entirely system-shared, with no dedicated VRAM. The size, type, and bus width are all listed as "System Shared," and bandwidth is "System Dependent," meaning it relies on the host system’s memory controller and RAM configuration. This design has significant implications for performance, especially at higher resolutions. The GPU’s 8 ROPs and 24 TMUs are responsible for pixel and texture processing, and their efficiency is directly tied to memory bandwidth. In dual-channel memory configurations, the available bandwidth can be sufficient for 1080p gaming at low to medium settings. However, at 1440p or higher resolutions, the memory subsystem can become a bottleneck, as the shared bandwidth is also consumed by the CPU and other system processes. The pixel rate of 12.80 GPixel/s and texture rate of 38.40 GTexel/s are theoretical maximums that assume optimal memory conditions. In practice, single-channel memory configurations could severely limit performance, potentially halving effective bandwidth. For users seeking the best performance from this GPU, a dual-channel memory setup is essential, though specific memory speeds are not documented in the fact pack. The system-dependent nature of memory bandwidth makes it difficult to predict exact performance without knowing the host system’s specifications.

Ray Tracing and Feature Set

The Radeon Graphics 384SP Mobile does not include dedicated ray tracing cores or tensor cores, as both fields are null. This means hardware-accelerated ray tracing is not supported, and any ray tracing effects would need to be computed via traditional shader workloads, which would be impractical given the 1,228.8 GFLOPS of FP32 performance. The GPU does offer solid API support, including DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.3. This API compatibility ensures broad software support across modern games and applications. The DirectX 12_1 feature level indicates support for advanced rendering features like conservative rasterization and rasterizer-ordered views, though these are not commonly utilized in mainstream titles. The Vulkan 1.3 support provides low-overhead access to the GPU, which can be beneficial for developers and in Vulkan-based games. The absence of tensor cores means no dedicated AI acceleration for features like DLSS, but the FP16 performance of 2.458 TFLOPS (2:1) does allow some mixed-precision compute, which could be leveraged for light AI workloads. The GPU’s GCN 5.1 architecture is mature and well-supported, but it lacks the modern feature set of newer architectures, particularly in terms of hardware-accelerated ray tracing and AI-based upscaling. For users, this means the GPU is best suited for traditional rasterization-based rendering, with performance in ray-traced titles likely being prohibitively slow.