AMD Radeon R4E Mobile Graphics

Power and Cooling — TDP, PSU recommendation, connector requirements

The AMD Radeon R4E Mobile Graphics is an integrated graphics processor (IGP) built on the Stoney chip, fabricated on a 28 nm process at GlobalFoundries. Its thermal design power is rated at 15 W, which places it firmly in the low-power segment typical of mobile IGPs. This 15 W figure represents the total board power envelope, encompassing both the GPU and its associated logic, but since this is an IGP, the actual thermal load is shared with the host processor's package.

Because the R4E is an IGP, it does not require any dedicated power connectors — the slot width is listed as "IGP" and the power connectors field is null. The bus interface is likewise "IGP," meaning it draws its power through the motherboard's socket rather than through a PCIe slot or auxiliary cabling. Consequently, there is no suggested PSU rating provided in the data, as the power delivery is entirely dependent on the host laptop or mobile platform's design. For a system builder or user considering this part, the only relevant power consideration is whether the laptop's existing thermal solution can handle the combined CPU and GPU load within the 15 W envelope.

The process node is 28 nm, and the die size measures 125 mm², containing 1,200 million transistors. This yields a transistor density of 9.6 million transistors per square millimeter. The 28 nm node is a mature manufacturing process, and the relatively modest transistor count reflects the entry-level positioning of this IGP. The production status is listed as "End-of-life," with a release date of May 31, 2016, meaning this is a legacy part that has been superseded in AMD's mobile lineup.

Who Should Consider It

Benchmark results indicate that the R4E occupies the 50th percentile among all GPUs, which positions it as a strictly entry-level solution. The average benchmark score is zero, and there are no specific benchmark entries in the dataset, which means quantitative performance data is sparse. However, the hardware specifications — 192 shading units, 12 texture mapping units, and 8 ROPs — provide a basis for expectations.

At its base clock of 400 MHz and boost clock of 600 MHz, the R4E delivers 230.4 GFLOPS of FP32 compute and 230.4 GFLOPS of FP16 compute at a 1:1 ratio. This level of compute throughput is suitable for basic desktop productivity, web browsing, and video playback. For gaming, the data suggests this IGP is not intended for high-resolution or high-settings workloads. The pixel rate is 4.800 GPixel/s, and the texture rate is 7.200 GTexel/s, which are modest figures that would struggle with modern 3D titles at 1080p beyond minimum settings.

Given the lack of benchmark scores, recommendations must be inferred from the raw specifications. The R4E would be appropriate for users who primarily need integrated graphics for office applications, streaming video, and light casual gaming at 720p or lower resolutions with reduced graphical settings. It is not suitable for 1440p or 4K gaming, nor for any workload requiring sustained GPU compute. The memory subsystem being system-dependent further reinforces that this is a basic IGP aimed at budget laptops and low-power devices.

Memory Subsystem

The memory configuration of the R4E is entirely system-dependent. The VRAM size is listed as "System Shared," the memory type is "System Shared," the bus width is "System Shared," and the bandwidth is "System Dependent." This means the GPU does not have its own dedicated video memory but instead borrows from the host system's main memory. The clock speed for memory is also listed as "System Shared," indicating that the memory frequency is tied to the system's RAM configuration.

This shared memory architecture has significant implications for high-resolution workloads. Because the GPU must access main memory through the system bus, bandwidth is inherently limited by the platform's memory controller and the speed of the installed RAM. The "System Dependent" bandwidth figure means that performance can vary widely depending on whether the host system uses single-channel or dual-channel memory, and whether the RAM is DDR3 or DDR4 at various speeds. For a GPU with only 192 shading units and 8 ROPs, the memory bandwidth is unlikely to be the primary bottleneck at typical use cases, but it does constrain performance at higher resolutions where texture fetches and frame buffer reads become more demanding.

In practical terms, the shared memory configuration means that the R4E will perform better in systems with faster dual-channel memory, as this effectively increases the available bandwidth to the GPU. However, even with optimal system memory, the compute capabilities of the R4E are limited by its clock speeds and shader count, so the memory subsystem is a secondary consideration rather than a performance differentiator.

How It Compares

The dataset for the R4E lists no nearest rivals, which means there are no direct comparison points in the benchmark database. The "nearestRivals" field is empty, and there are no specific scores or delta percentages provided for comparison with other GPUs. This absence of comparative data makes it challenging to position the R4E against contemporary or competing parts.

However, the predecessor and successor information provides some context. The R4E is preceded by the "GCN 2.0 IGP" and succeeded by "Vega IGP." This indicates that the R4E belongs to the GCN 3.0 architecture generation, which is a minor revision over GCN 2.0, focusing on power efficiency and minor architectural refinements. The successor, Vega IGP, represents a more significant architectural leap with the Vega architecture's improved memory management and compute capabilities.

In the absence of direct rival comparisons, the percentile ranking of 50 serves as a general indicator. Being at the 50th percentile means that the R4E performs better than half of all GPUs in the database and worse than the other half. This is a surprisingly high percentile for such a low-power IGP, which may reflect the fact that the database includes many older or even less capable integrated and entry-level discrete GPUs. The average benchmark score of zero is more telling, suggesting that the R4E has not been subjected to any standardized benchmark tests or has failed to register meaningful scores.

Benchmark Performance

The benchmark performance section must rely on the available data points, which are limited to the raw specifications and the percentile ranking. The FP32 performance of 230.4 GFLOPS is the primary compute metric, derived from the 192 shading units operating at a boost clock of 600 MHz. To put this in perspective, this is approximately half the compute throughput of a low-end discrete GPU from the same era, but it is a reasonable figure for an IGP with a 15 W TDP.

The pixel rate of 4.800 GPixel/s and texture rate of 7.200 GTexel/s are derived from the 8 ROPs and 12 TMUs at the boost clock. These rates indicate that the R4E can handle basic 2D rendering and video decode tasks without issue, but 3D gaming at 1080p would likely result in frame rates below 30 FPS for most modern titles. The FP16 performance being equal to FP32 (1:1 ratio) is notable, as it suggests the GPU does not have dedicated FP16 hardware or that the architecture processes both at the same rate — this is typical for GCN 3.0 IGPs.

Since there are no benchmark scores or rival deltas in the dataset, a quantitative comparison against specific competitors is not possible. The percentile rank of 50 is the only relative performance indicator, and it should be interpreted cautiously given the zero average benchmark score. In the absence of measured data, the specifications suggest that the R4E is comparable to other entry-level IGPs of its era, such as those found in budget laptops from 2016, but without confirmed benchmark results, this remains an inference from the hardware configuration.

FAQ

Q: What is the TDP of the AMD Radeon R4E Mobile Graphics?

A: The R4E has a thermal design power of 15 W, which is typical for an integrated graphics processor designed for mobile platforms.

Q: Does the R4E have its own dedicated video memory?

A: No, the memory size, type, and bus width are all listed as "System Shared," meaning the GPU uses the host system's main memory. The bandwidth is "System Dependent," varying with the platform's memory configuration.

Q: What is the maximum FP32 compute performance of the R4E?

A: The R4E delivers 230.4 GFLOPS of FP32 compute at its boost clock of 600 MHz, based on its 192 shading units. Its FP16 performance is identical at 230.4 GFLOPS with a 1:1 ratio.

Q: Is the R4E suitable for modern gaming at 1080p resolution?

A: The data indicates that the R4E is an entry-level IGP with a pixel rate of 4.800 GPixel/s and a texture rate of 7.200 GTexel/s. These figures suggest it would struggle with modern 3D games at 1080p, making it more suitable for 720p gaming at reduced settings or non-gaming workloads.

Q: What process node is the R4E manufactured on?

A: The R4E is fabricated on a 28 nm process at GlobalFoundries, with a die size of 125 mm² containing 1,200 million transistors.

Q: What is the production status and release date of the R4E?

A: The R4E is listed as "End-of-life" with a release date of May 31, 2016. It is part of the GCN 3.0 architecture generation, succeeding GCN 2.0 IGP and preceding Vega IGP.