AMD Radeon R2E Mobile Graphics

Power and Cooling — TDP, PSU recommendation, connector requirements

The AMD Radeon R2E Mobile Graphics is an integrated graphics processor (IGP), which fundamentally shapes its power and cooling profile. Its thermal design power (TDP) is rated at 15 W, a figure that reflects the entire chip’s envelope rather than just the graphics portion, as the R2E shares a die with the CPU in the Beema platform. This low TDP places it firmly in the ultra-portable and entry-level laptop segment, where passive or low-profile active cooling solutions are the norm.

Because the R2E is an IGP, there are no power connectors to speak of. The `powerConnectors` field is null, and the `suggestedPsu` field is also null — there is no standalone power supply requirement. The card draws its power entirely through the motherboard's power delivery system, which is designed around the 15 W TDP of the combined APU. For system integrators, this means no additional PSU headroom is needed beyond what a standard thin-and-light laptop chassis would provide. The slot width is listed as "IGP," confirming that it does not occupy an expansion slot and therefore has no physical footprint for cooling hardware beyond whatever the laptop manufacturer implements for the APU.

The 28 nm process node, fabricated by GlobalFoundries, contributes to the modest power draw. The die size is 107 mm², and the transistor count is 930 million, yielding a transistor density of 8.7 million transistors per square millimeter. These figures indicate a mature, power-efficient design from the GCN 2.0 era, not a high-performance part chasing clock speeds. The production status is "End-of-life," with a release date of January 27, 2015, meaning this is a legacy part that was designed for a specific window of mobile computing where 15 W TDPs were the standard for entry-level notebooks.

Ray Tracing and Feature Set — RT/tensor cores, API support from facts

The R2E Mobile Graphics does not feature dedicated ray tracing cores or tensor cores — both fields are null in the specification data. This is consistent with its GCN 2.0 architecture and its 2015 release timeframe, as hardware-accelerated ray tracing and AI-based tensor operations were not part of the consumer GPU landscape at that time. Instead, the chip relies on its 128 shading units, 8 texture mapping units (TMUs), and 4 render output units (ROPs) for all graphics processing.

The API support tells a more nuanced story. The R2E supports DirectX 12 (specifically feature level 12_0), which means it can run modern DirectX 12 titles, albeit without the advanced features that require higher feature levels. OpenGL 4.6 is supported, which covers a wide range of OpenGL-based applications and games. Vulkan 1.2.170 is also on the list, providing access to modern cross-platform graphics APIs. These API capabilities are notable for a 2015 IGP — they give the R2E a degree of forward compatibility that older integrated graphics lack, even if raw performance is limited.

The pixel rate is 1.200 GPixel/s, and the texture rate is 2.400 GTexel/s. These are modest figures that reflect the 4 ROPs and 8 TMUs working at the chip's clock speeds. The FP32 performance is 76.80 GFLOPS, which is the single-precision compute throughput of the 128 shading units. No FP16 data is available, indicating that half-precision compute was not a focus for this architecture. The bus interface is listed as "IGP," meaning it communicates with the rest of the system via the internal bus of the APU, not through a discrete PCIe connection.

Memory Subsystem — VRAM size/type, bus width, bandwidth and what it means for high resolutions

The memory subsystem of the R2E is entirely system-dependent. The VRAM size is "System Shared," the memory type is "System Shared," and the bus width is "System Shared." This means the GPU does not have its own dedicated video memory; instead, it borrows from the system's main RAM. The memory clock is similarly "System Shared," and the bandwidth is listed as "System Dependent."

This architecture has significant implications for performance, particularly at higher resolutions. Because the R2E must share memory bandwidth with the CPU and other system components, its effective memory bandwidth is a function of the laptop's RAM configuration — its speed, channel count, and whether it's running in dual-channel mode. A dual-channel DDR3 configuration from the 2015 era would provide substantially more bandwidth than a single-channel setup, but even in the best case, the R2E's memory performance is constrained by the system's limitations.

For high-resolution workloads, the system-dependent nature of the memory becomes a bottleneck. At 1080p or higher, the R2E would need to move large amounts of texture and framebuffer data through the shared memory bus, competing with CPU workloads for the same bandwidth. The 4 ROPs also limit fill-rate performance, which manifests as reduced pixel throughput at higher resolutions. Benchmark results indicate that this is a 720p-class solution — at 1080p, frame rates would drop significantly, and at 1440p or above, the memory bandwidth constraint would likely make gaming impractical. The system-dependent bandwidth also means that two laptops with the same R2E chip could perform differently in memory-intensive scenarios based solely on their RAM configurations.

How It Compares — position vs each nearest rival

The nearest rivals list for the R2E is empty, which means the benchmark database does not have direct comparative data from other GPUs at the same performance tier. This is common for integrated graphics from this era, as they were often not benchmarked against discrete parts or even against each other in a standardized manner. The `percentileVsAllGpus` field is set to 50, which places it at the exact median of all GPUs in the database — a middle-of-the-road position that suggests it outperforms half of the recorded GPUs and underperforms the other half. However, this percentile is based on an `avgBenchmarkScore` of 0, which indicates that no actual benchmark scores are recorded for this part, so the percentile may be a default or estimated value rather than a computed one.

Without rival data, comparisons must be framed qualitatively based on the architecture and specifications. The R2E's predecessor is the TeraScale 3 IGP, and its successor is the GCN 3.0 IGP. This lineage places it in the middle of AMD's integrated graphics evolution, where each generation brought incremental improvements in feature support and efficiency. The 128 shading units and GCN 2.0 architecture represent a significant step up from the older TeraScale 3 design in terms of compute capabilities and API support, but the successor GCN 3.0 IGP would offer further refinements. The R2E sits in the gap between these two generations, offering GCN 2.0's feature set without the performance or efficiency gains of later iterations.

Benchmark Performance — analyze scores vs rivals with exact % deltas

The benchmark data for the R2E is sparse. The `benchmarks` array is empty, and the `avgBenchmarkScore` is 0. This means there are no recorded scores to analyze, no exact percentage deltas to report, and no comparative performance figures against rivals. The `nearestRivals` array is also empty, so there are no deltaPct values to cite.

What can be analyzed is the theoretical performance based on the raw specifications. The FP32 throughput of 76.80 GFLOPS, combined with the pixel rate of 1.200 GPixel/s and texture rate of 2.400 GTexel/s, paints a picture of a very low-end part. For context, a typical discrete GPU from the same era would have FP32 performance in the hundreds or thousands of GFLOPS. The R2E's 128 shading units are organized in a configuration that yields these specific rates, and the 4 ROPs are the minimum practical number for any GPU, limiting pixel output.

The percentile rank of 50 against all GPUs is the only relative metric available. Given the empty benchmark array, this percentile should be interpreted with caution — it may reflect the part's position in the database's hierarchy based on specifications rather than measured performance. In practical terms, the R2E would be suitable for basic desktop productivity, video playback, and very light gaming at low resolutions and settings. The absence of benchmark data suggests that this part was not widely tested or that its performance was considered too low to warrant standardized benchmarking.

FAQ

Q: Does the AMD Radeon R2E Mobile Graphics support DirectX 12?

A: Yes, it supports DirectX 12 with feature level 12_0, along with OpenGL 4.6 and Vulkan 1.2.170.

Q: How much dedicated video memory does the R2E have?

A: It has no dedicated video memory. The VRAM size, type, and bus width are all "System Shared," meaning it uses the system's main RAM.

Q: What is the TDP of this integrated GPU?

A: The TDP is 15 W, which covers the graphics portion of the Beema APU. There are no power connectors or PSU requirements since it is an IGP.

Q: Does the R2E have ray tracing capabilities?

A: No, it does not. The `rtCores` and `tensorCores` fields are null, and the GCN 2.0 architecture predates hardware ray tracing.

Q: When was this GPU released, and is it still in production?

A: It was released on January 27, 2015, and its production status is "End-of-life."

Q: What is the pixel and texture throughput of the R2E?

A: The pixel rate is 1.200 GPixel/s, and the texture rate is 2.400 GTexel/s, based on its 4 ROPs and 8 TMUs.

Q: How does the R2E compare to its predecessor and successor?

A: Its predecessor is the TeraScale 3 IGP, and its successor is the GCN 3.0 IGP. The R2E sits between these generations, offering GCN 2.0 features.

Q: What is the manufacturing process for this chip?

A: It is fabricated on a 28 nm process node by GlobalFoundries, with a die size of 107 mm² and 930 million transistors.