AMD Radeon RX 470
AMD graphics card specifications and benchmark scores
At a Glance
AMDAMD Radeon RX 470 Specifications
Radeon RX 470 GPU Core
Shader units and compute resources
The AMD Radeon RX 470 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.
RX 470 Clock Speeds
GPU and memory frequencies
Clock speeds directly impact the Radeon RX 470'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 RX 470 by AMD dynamically adjusts frequencies based on workload, temperature, and power limits to maximize performance while maintaining stability.
AMD's Radeon RX 470 Memory
VRAM capacity and bandwidth
VRAM (Video RAM) is dedicated memory for storing textures, frame buffers, and shader data. The Radeon RX 470'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.
Radeon RX 470 by AMD Cache
On-chip cache hierarchy
On-chip cache provides ultra-fast data access for the RX 470, reducing the need to fetch data from slower VRAM. L1 and L2 caches store frequently accessed data close to the compute units. AMD's Infinity Cache (L3) dramatically increases effective bandwidth, improving GPU benchmark performance without requiring wider memory buses. Larger cache sizes help maintain high frame rates in memory-bound scenarios and reduce power consumption by minimizing VRAM accesses.
RX 470 Theoretical Performance
Compute and fill rates
Theoretical performance metrics provide a baseline for comparing the AMD Radeon RX 470 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 4.0 Architecture & Process
Manufacturing and design details
The AMD Radeon RX 470 is built on AMD's GCN 4.0 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 RX 470 will perform in GPU benchmarks compared to previous generations.
AMD's Radeon RX 470 Power & Thermal
TDP and power requirements
Power specifications for the AMD Radeon RX 470 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 RX 470 to maintain boost clocks without throttling.
Radeon RX 470 by AMD Physical & Connectivity
Dimensions and outputs
Physical dimensions of the AMD Radeon RX 470 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 RX 470. 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 RX 470 Product Information
Release and pricing details
The AMD Radeon RX 470 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 RX 470 by AMD represents good value at current market prices. Predecessor and successor information aids in tracking generational improvements and planning future upgrades.
Radeon RX 470 Benchmark Scores
3dmark_3dmark_steel_nomad_dx12Source
3DMark Steel Nomad is the latest GPU benchmark running at native 4K with DirectX 12. It's roughly 3x more demanding than Time Spy, testing AMD Radeon RX 470 with cutting-edge rendering techniques.
Top 5 Performers
Top 5 PerformersNearby Performers
Nearby Performersgeekbench_metalSource
Geekbench Metal tests GPU compute using Apple's Metal API. This shows how AMD Radeon RX 470 performs in macOS and iOS applications that leverage GPU acceleration. Metal provides low-overhead access to Apple silicon GPUs.
Top 5 Performers
Nearby Performers
geekbench_openclSource
Geekbench OpenCL tests GPU compute performance using the cross-platform OpenCL API. This shows how AMD Radeon RX 470 handles parallel computing tasks like video encoding and scientific simulations.
Top 5 Performers
Nearby Performers
geekbench_vulkanSource
Geekbench Vulkan tests GPU compute using the modern low-overhead Vulkan API. This shows how AMD Radeon RX 470 performs with next-generation graphics and compute workloads. Vulkan offers better CPU efficiency than older APIs like OpenGL.
Top 5 Performers
Nearby Performers
About AMD Radeon RX 470
The AMD Radeon RX 470, built on the 14 nm process at GlobalFoundries with the Ellesmere chip and GCN 4.0 architecture, occupies a distinct position in the database. It carries an average benchmark score of 28996, placing it in the 72nd percentile of all GPUs, a figure that suggests it remains relevant for specific workloads despite its 2016 release and end-of-life status. The data presents a card that is defined by its memory configuration, its closeness to a cluster of modern rivals, and a feature set that anchors it to a particular generation of graphics technology.
Memory Subsystem
The RX 470 comes equipped with 4 GB of GDDR5 memory, which is a modest capacity by modern standards. This is paired with a 256-bit bus width, a specification that remains a strong point for the card, as it allows for substantial memory bandwidth. The memory operates at 1650 MHz, translating to 6.6 Gbps effective and yielding a total bandwidth of 211.2 GB/s. For high-resolution gaming, this configuration tells a specific story. The 256-bit bus and the resulting bandwidth are sufficient to feed the card's 2048 shading units and 128 TMUs at 1080p, but the 4 GB frame buffer is the limiting factor at higher resolutions like 1440p or 4K. Textures and geometry data for modern titles can easily exceed 4 GB, causing the card to rely on slower system memory over the PCIe 3.0 x16 interface. The data indicates that the memory subsystem is balanced for its era, but the capacity creates a hard ceiling for future-proofing at high resolutions. The pixel rate of 38.59 GPixel/s and texture rate of 154.4 GTexel/s are in line with this memory configuration, suggesting a coherent design where the frame buffer size, not bandwidth, is the primary bottleneck for demanding scenarios.
How It Compares
vs AMD Radeon RX 6800M: The RX 470’s average score of 28996 is nearly identical to the RX 6800M’s 29011, a difference of only -0.1%. This is a striking result, as the RX 6800M is a mobile part from a much later generation. The benchmark data suggests that in synthetic aggregate workloads, the older desktop card holds its own against a premium mobile solution, implying that the RX 470’s raw compute capabilities, particularly its 4.940 TFLOPS FP32 performance, are not easily surpassed by a mobile chip with different power constraints.
vs AMD Radeon RX 6650 XT: The comparison with the RX 6650 XT shows a similar pattern, with the rival posting an average score of 29024. The RX 470 trails by a mere -0.1%. This is surprising given the generational gap; the RX 6650 XT is a newer, more efficient architecture. The data implies that the RX 470’s high shader count and memory bandwidth allow it to remain competitive in these specific benchmark tests, even if it lacks the newer features and efficiency of its successor.
vs Intel Arc A370M: The Intel Arc A370M, with an average score of 29175, sits just 0.6% ahead of the RX 470. This is a marginal lead for the Intel discrete mobile GPU. The benchmark results indicate a performance parity that defies the age difference between the two products. The RX 470’s mature drivers and consistent GCN architecture likely contribute to its ability to match a newer, entry-level mobile part, though the Arc A370M may offer advantages in newer API-specific workloads that the aggregate score does not fully capture.
vs AMD Radeon RX Vega M GH: The RX Vega M GH, another mobile-class part, scores 29197, which is 0.7% higher than the RX 470. This is the largest delta among the nearest rivals, yet it remains within a single percentage point. The data suggests that the RX 470 is positioned in a performance tier where several disparate architectures converge. The Vega M GH’s integrated HBM2 memory may give it a slight edge in bandwidth-sensitive tasks, but the RX 470’s overall score shows it is not outclassed, maintaining a near-identical level of performance in these aggregate metrics.
Benchmark Performance
The benchmark performance of the RX 470 is characterized by its consistency across different testing frameworks. In Geekbench OpenCL, it scores 33568, while in Geekbench Vulkan, it achieves 39884, and in Geekbench Metal, it reaches 41690. This progression indicates a strong scaling with the API, with the Vulkan and Metal scores being 18.8% and 24.2% higher than the OpenCL result, respectively. This suggests that the GCN architecture responds well to lower-level access and modern driver optimizations. In contrast, the 3DMark Steel Nomad DX12 test yields a score of 842, which is dramatically lower than the Geekbench results. This is not a direct comparison of APIs but rather reflects the different nature of the workloads: Steel Nomad is a demanding, modern DX12 gaming test, while Geekbench compute tests are more synthetic. The data implies that the RX 470’s raw compute power, as measured by Geekbench, is substantial, but its gaming-specific performance in a heavy DX12 title is more limited. Relative to its nearest rivals, the deltas are minuscule. Being 0.1% behind the RX 6800M and RX 6650 XT, and 0.6-0.7% behind the Intel Arc A370M and RX Vega M GH, the RX 470 effectively trades blows with all four. This tight clustering suggests that for the average user, these GPUs offer indistinguishable performance in the aggregate, and the choice between them would come down to other factors like features, power consumption, and driver support rather than raw score.
FAQ
Q: How does the RX 470’s performance compare to its closest rivals?
A: The average benchmark score of 28996 places it within 0.7% of all four nearest rivals. It is 0.1% behind the AMD Radeon RX 6800M and RX 6650 XT, and 0.6% and 0.7% behind the Intel Arc A370M and RX Vega M GH, respectively.
Q: What is the card’s memory bandwidth and how does it affect performance?
A: The memory bandwidth is 211.2 GB/s, derived from a 256-bit bus and 6.6 Gbps effective GDDR5 memory. This bandwidth is substantial for the card’s compute capabilities, but the 4 GB VRAM capacity is the limiting factor for high-resolution textures.
Q: What modern APIs does the RX 470 support?
A: The card supports DirectX 12 (12_0), OpenGL 4.6, and Vulkan 1.3. Its Vulkan performance is strong, with a Geekbench Vulkan score of 39884, which is higher than its OpenCL score.
Q: What is the card’s position in the overall GPU landscape?
A: The RX 470 is in the 72nd percentile of all GPUs, indicating it outperforms a majority of the database entries. Its average score of 28996 is competitive with several much newer mobile GPUs.
Q: Does the RX 470 have dedicated ray tracing or tensor cores?
A: No. The FACT PACK lists null values for both `rtCores` and `tensorCores`. This indicates it lacks dedicated hardware for ray tracing and AI acceleration, relying instead on its general-purpose 2048 shading units.
Q: What is the effective memory clock speed?
A: The memory clock is listed as 1650 MHz, which translates to 6.6 Gbps effective. This is the data point used to calculate the 211.2 GB/s bandwidth.
Ray Tracing and Feature Set
The RX 470’s feature set is defined by what it lacks. The data explicitly lists null values for both ray tracing cores and tensor cores. This means the card has no dedicated hardware for hardware-accelerated ray tracing or AI-based features like DLSS. Any ray tracing effects would have to be computed on the standard shader units, which would severely impact performance, and the FP16 performance is 4.940 TFLOPS, identical to its FP32 rate (1:1), indicating no special half-precision acceleration. The card does support DirectX 12 (12_0), which is a baseline feature level, but it does not include the newer features often associated with DX12 Ultimate. On the software side, it supports Vulkan 1.3 and OpenGL 4.6, providing a modern API foundation for many current titles. The display outputs are 1x HDMI 2.0b and 3x DisplayPort 1.4a, which allow for high refresh rate monitors, though the card’s performance ceiling may limit its ability to drive them in demanding games. The architecture is GCN 4.0, a design that predates the current focus on hybrid rendering, and the data suggests its strength lies in traditional rasterization and compute workloads rather than cutting-edge graphics features.
Who Should Consider It
Given its 72nd percentile ranking and benchmark scores, the RX 470 is a card for a specific user. The data indicates it is well-suited for 1080p gaming, where its 4 GB of VRAM and 211.2 GB/s bandwidth are adequate for most titles. Users playing esports or older games at high settings will find the performance acceptable, with the card’s raw compute power providing a smooth experience. However, for 1440p or 4K gaming, the 4 GB frame buffer becomes a critical limitation. The data suggests it is not a viable option for modern AAA titles at those resolutions without significantly reducing texture quality and other settings. The near-identical scores to its rivals imply that a user considering an RX 470 should not expect a performance advantage over a RX 6650 XT or RX 6800M, but rather a similar level of aggregate performance. This card is best for a secondary system, a budget 1080p build, or a user who primarily plays less demanding titles. Gamers who prioritize high-resolution textures or want to enable the latest graphical features like ray tracing should look elsewhere, as the lack of dedicated RT cores and the VRAM capacity will be immediate bottlenecks.
Power and Cooling
The RX 470 has a TDP of 120 W, a figure that is modest by modern standards. The system requirements are equally restrained, with a suggested PSU of just 300 W and a single 1x 6-pin power connector. This makes it an easy drop-in replacement for older systems with limited power supply headroom. The card is a dual-slot design, measuring 240 mm in length (9.4 inches), 95 mm in height (3.7 inches), and 35 mm in width (1.4 inches), which should fit in most standard mid-tower cases. The cooling solution is not specified in the data, but the 120 W TDP suggests that a capable air cooler is sufficient to manage thermals. The 14 nm process node from GlobalFoundries is a factor in this power efficiency. The combination of a 300 W PSU recommendation and a single 6-pin connector indicates that the card is designed to be power-frugal, making it a practical choice for systems where power delivery is a concern. The data shows a straightforward power profile that does not require extensive PSU upgrades or complex cabling, contributing to its ease of installation in a wide range of builds.
The NVIDIA Equivalent of Radeon RX 470
Looking for a similar graphics card from NVIDIA? The NVIDIA GeForce RTX 2080 offers comparable performance and features in the NVIDIA lineup.
Popular AMD Radeon RX 470 Comparisons
See how the Radeon RX 470 stacks up against similar graphics cards from the same generation and competing brands.
Compare Radeon RX 470 with Other GPUs
Select another GPU to compare specifications and benchmarks side-by-side.
Browse GPUs