AMD Radeon Graphics 384SP
AMD graphics card specifications and benchmark scores
At a Glance
AMDAMD Radeon Graphics 384SP Specifications
Radeon Graphics 384SP GPU Core
Shader units and compute resources
The AMD Radeon Graphics 384SP 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.
Graphics 384SP Clock Speeds
GPU and memory frequencies
Clock speeds directly impact the Radeon Graphics 384SP'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 Radeon Graphics 384SP by AMD dynamically adjusts frequencies based on workload, temperature, and power limits to maximize performance while maintaining stability.
AMD's Radeon Graphics 384SP Memory
VRAM capacity and bandwidth
VRAM (Video RAM) is dedicated memory for storing textures, frame buffers, and shader data. The Radeon Graphics 384SP'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.
Graphics 384SP Theoretical Performance
Compute and fill rates
Theoretical performance metrics provide a baseline for comparing the AMD Radeon Graphics 384SP 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.
GCN 5.1 Architecture & Process
Manufacturing and design details
The AMD Radeon Graphics 384SP is built on AMD's GCN 5.1 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 Graphics 384SP will perform in GPU benchmarks compared to previous generations.
AMD's Radeon Graphics 384SP Power & Thermal
TDP and power requirements
Power specifications for the AMD Radeon Graphics 384SP 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 Radeon Graphics 384SP to maintain boost clocks without throttling.
Radeon Graphics 384SP by AMD Physical & Connectivity
Dimensions and outputs
Physical dimensions of the AMD Radeon Graphics 384SP 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.
AMD API Support
Graphics and compute APIs
API support determines which games and applications can fully utilize the AMD Radeon Graphics 384SP. 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.
Radeon Graphics 384SP Product Information
Release and pricing details
The AMD Radeon Graphics 384SP is manufactured by AMD 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 Radeon Graphics 384SP by AMD represents good value at current market prices. Predecessor and successor information aids in tracking generational improvements and planning future upgrades.
Radeon Graphics 384SP Benchmark Scores
No benchmark data available for this GPU.
About AMD Radeon Graphics 384SP
The AMD Radeon Graphics 384SP is an integrated graphics processor based on the Cezanne chip, using AMD's GCN 5.1 architecture and belonging to the Vega II IGP (Cezanne) generation. TSMC manufactures the chip on a 7 nm process; the die contains 9,800 million transistors on 180 mm², a transistor density of 54.4M / mm². The design has 384 shading units, 24 texture mapping units, and 8 ROPs. Its production status is end-of-life, with a release date of 2021-04-12. The benchmark record is sparse: the benchmarks array is empty, the average benchmark score is 0, and the percentile against all GPUs is 50. Consequently, this analysis is based on the specification fields in the fact pack rather than on measured application scores.
Benchmark Performance
Benchmark data for the AMD Radeon Graphics 384SP is absent from the fact pack. The benchmarks array is empty, and the average benchmark score is 0. The nearestRivals array is also empty, so there are no rival names, rival scores, or deltaPct values to use for direct comparisons. The only percentile field is percentileVsAllGpus with a value of 50; however, because the benchmark list is empty, that percentile is not supported by measured scores in this record.
On raw compute specifications, the part is defined by 384 shading units, a 300 MHz base clock, and a 1700 MHz boost clock. The listed FP32 throughput is 1,305.6 GFLOPS, and the listed FP16 throughput is 2.611 TFLOPS. The FP16 entry is marked with a 2:1 ratio, which means the FP16 peak is double the FP32 peak. No game clock is present in the fact pack, so the boost clock is the highest listed operating point.
Fill-rate figures come from the fixed-function blocks. With 24 TMUs, the texture rate is 40.80 GTexel/s; with 8 ROPs, the pixel rate is 13.60 GPixel/s. These two rates are the only fill-rate data in the pack. The texture rate is higher than the pixel rate because the TMU count is higher than the ROP count, but no rival comparison is available to place these numbers in a competitive context.
The compute and fill-rate figures are internally consistent with the block counts: 384 shaders, 24 TMUs, and 8 ROPs at the listed clock range produce the listed rates. Without benchmark entries, the data cannot indicate how this translates into real application performance. The percentile of 50 against all GPUs remains the only ordinal signal, and it is not accompanied by a measured score.
Memory Subsystem
The memory subsystem is entirely shared with the system. The memory size field is 'System Shared', the memory type field is 'System Shared', and the bus width field is 'System Shared'. Memory bandwidth is listed as 'System Dependent'. There is no dedicated VRAM capacity, no dedicated memory type, no dedicated bus width, and no fixed bandwidth value in the fact pack.
For high-resolution rendering, the absence of dedicated video memory means all frame-buffer traffic uses the host's memory channels. Because the bandwidth field is system dependent, actual performance will change with the platform's memory configuration rather than being a fixed property of the GPU. The record does not list a memory clock; the only clock values are the GPU base clock of 300 MHz and boost clock of 1700 MHz.
Without a fixed bandwidth number, it is not possible to calculate a memory-to-compute ratio or determine whether the 384 shaders can be fully utilized. The memory subsystem is the primary platform-dependent variable for this integrated part, and its effect on high-resolution workloads is not quantified in the fact pack.
The shared memory type also means that capacity is not a fixed attribute of the GPU. Any allocation for the frame buffer or rendering resources is drawn from the system memory pool, and the 'System Dependent' bandwidth applies to all such traffic. The memory subsystem is therefore not characterized by any fixed capacity or bandwidth number in this record.
Ray Tracing and Feature Set
The fact pack lists no RT cores and no tensor cores; both fields are null. This means no dedicated hardware ray tracing blocks or tensor/matrix acceleration blocks are documented. The API feature set is given by DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.3. The DirectX entry specifies feature level 12_1, and no other DirectX details are listed.
Display outputs are listed as 'Motherboard Dependent', so physical connector support depends on the host motherboard. The architecture is GCN 5.1 and the generation is Vega II IGP (Cezanne), but without RT core or tensor core counts, the data set cannot confirm dedicated ray tracing or AI acceleration hardware. The API versions are the only software interface details provided; no ray tracing extensions or compute API capabilities are listed.
The absence of RT and tensor counts is separate from API support. DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.3 are listed as supported APIs, but the fact pack does not describe which optional API features or extensions are present. Dedicated hardware acceleration is not part of the recorded feature set.
Power and Cooling
The power specification is a TDP of 45 W. The slot width is IGP, the bus interface is IGP, and power connectors are listed as 'None'. No suggested PSU is listed, so no PSU recommendation can be stated. These fields indicate an integrated part that does not require auxiliary power connectors.
The absence of a suggested PSU does not mean no system power is needed; it means the fact pack does not define a PSU requirement for this GPU. Since the bus interface is IGP, power is delivered through the motherboard rather than through PCIe power cables. The power connectors field is 'None', consistent with an integrated design.
No cooling details are present in the fact pack. There is no cooler size, no length, no height, no width, and no heatsink specification. For an IGP, the thermal solution is integrated into the host system. The 45 W TDP is the only thermal/power figure available.
The 45 W TDP figure describes the integrated part's thermal envelope in the data set. Because no suggested PSU is listed and no connector requirements are given, all power supply and cooling decisions are delegated to the platform design. This is a minimal power profile, but the fact pack offers no further power measurements.
How It Compares
The nearestRivals array is empty in the fact pack, so this GPU cannot be compared with any named rival using the required data. There are no rival scores and no deltaPct values. Therefore, no statement can be made about this part being ahead of or behind another GPU by a percentage.
The lineage fields provide a different kind of context. The predecessor is recorded as Vega IGP, and the successor is recorded as Navi II IGP. These are generation labels, not nearestRivals, and no benchmark scores are attached to either one. The performance gap between this part and its predecessor or successor is therefore not quantified.
The only remaining position is percentileVsAllGpus, which is 50. With avgBenchmarkScore of 0 and an empty benchmarks array, that percentile is not anchored by measured data. In summary, the comparison section is limited to the specification profile: GCN 5.1, 384 shading units, 7 nm TSMC process, 45 W TDP, system-shared memory, and a place in the Vega II IGP generation between Vega IGP and Navi II IGP.
Because the nearestRivals list contains no entries, no paragraph can be written for each rival. The empty nearestRivals field is the definitive comparison result in this data set.
The NVIDIA Equivalent of Radeon Graphics 384SP
Looking for a similar graphics card from NVIDIA? The NVIDIA GeForce RTX 3050 Ti Mobile offers comparable performance and features in the NVIDIA lineup.
Popular AMD Radeon Graphics 384SP Comparisons
See how the Radeon Graphics 384SP stacks up against similar graphics cards from the same generation and competing brands.
Compare Radeon Graphics 384SP with Other GPUs
Select another GPU to compare specifications and benchmarks side-by-side.
Browse GPUs