AMD Radeon 880M vs AMD Radeon HD 8870M Comparison

The AMD Radeon HD 8870M and the AMD Radeon 880M sit at the same overall percentile rank (43rd) among all GPUs, yet they represent two entirely different eras of mobile graphics. The HD 8870M is a discrete part from the Solar System generation, built on a 28 nm process, while the 880M is a modern integrated graphics processor (IGP) from the Navi III IGP family, fabricated on a 4 nm node. The single head-to-head benchmark available shows a dramatic gap, but the story is more nuanced than a simple score comparison.

Head-to-Head Benchmarks

The only direct benchmark result between these two parts is the Geekbench OpenCL test, and the outcome is lopsided. The AMD Radeon 880M scores 31,285 points, while the AMD Radeon HD 8870M manages 8,462 points. The deltaPct from the perspective of the HD 8870M is -73%, meaning the 880M is roughly 3.7 times faster in this compute workload. This is not a marginal improvement; it is a generational leap. The 880M’s score is so much higher that it completely redefines what an integrated solution can achieve against a dedicated mobile GPU from a decade prior.

However, the HD 8870M’s own nearestRivals list puts its 8,462 score within 0.1% of the NVIDIA GeForce MX330 (8,458) and 0.3% of the AMD Radeon 880M itself (8,436 in that rival list context). Interestingly, the rival list for the 880M shows an average score of 8,436, which is lower than the 31,285 it scored in the head-to-head test. This discrepancy suggests the average includes a broader set of workloads, some of which may not favor the 880M as strongly. The 880M’s nearestRivals also include the NVIDIA GeForce GTX 675MX (8,427, deltaPct 0.1%) and the AMD Radeon R9 M375X (8,325, deltaPct 1.3%). In those comparisons, the 880M is essentially tied or slightly ahead, which is remarkable for an IGP.

The HD 8870M’s rival list also includes the Intel Arc A380, which scores 8,558 and shows a deltaPct of -1.1% relative to the HD 8870M. That means the Arc A380 is about 1.1% faster than the HD 8870M in this aggregated metric. None of these rival comparisons approach the 73% gap seen in the head-to-head Geekbench test, indicating that the OpenCL workload is particularly well-suited to the 880M’s architecture.

Where Each One Wins

Based on the data, the AMD Radeon 880M wins the only direct benchmark, taking the single win (winsB: 1) in the head-to-head comparison. The HD 8870M has zero wins (winsA: 0). Beyond that, the 880M shows a much broader benchmark suite. It has results across Passmark DX9 (97), DX10 (31), DX11 (73), DX12 (32), G2D (969), G3D (7,615), and GPU Compute (3,719), plus a Vulkan score of 40,006 and a 3DMark Steel Nomad DX12 score of 535. The HD 8870M only has the single Geekbench OpenCL result.

The 880M’s Passmark G3D score of 7,615 is substantial for an integrated part, and its GPU Compute score of 3,719 indicates strong general-purpose processing. The Vulkan score of 40,006 is notably higher than the OpenCL score, suggesting the 880M excels under modern API loads. For the HD 8870M, its only data point is the OpenCL score, which places it in the 43rd percentile—same as the 880M—but without additional tests, it is impossible to claim wins in any other category. The data clearly favors the 880M across every measurable metric.

Architecture Differences

The architectural divide between these two GPUs is vast. The HD 8870M uses the Venus chip based on GCN 1.0 architecture, manufactured on a 28 nm process at TSMC. It packs 1,500 million transistors on a 123 mm² die, yielding a transistor density of 12.2M per mm². The 880M, by contrast, uses the Strix Point chip with RDNA 3.5 architecture, built on a 4 nm process at the same foundry. It contains 34,000 million transistors on a 233 mm² die, achieving a density of 145.9M per mm²—about 12 times denser. This density jump explains how the 880M can offer more compute units in a smaller relative footprint despite the larger absolute die.

The HD 8870M has 640 shading units, 40 texture mapping units (TMUs), and 16 raster output units (ROPs). The 880M increases shading units to 768, TMUs to 48, and keeps ROPs at 16. More importantly, the 880M adds 12 ray tracing cores, a feature entirely absent from the GCN 1.0 part. The clock speeds tell a similar story: the HD 8870M runs at a base of 725 MHz and boosts to 775 MHz, while the 880M has a base of 400 MHz but boosts to 2,900 MHz—a massive boost headroom that drives its performance.

Memory configurations differ fundamentally. The HD 8870M uses 2 GB of GDDR5 on a 128-bit bus, delivering 72.00 GB/s of bandwidth. The 880M uses system shared memory, with no dedicated VRAM; its bus width and bandwidth are listed as "System Shared" and "System Dependent," respectively. This means the 880M’s performance will vary with the host system’s memory, whereas the HD 8870M has fixed dedicated bandwidth. Pixel and texture rates reflect the 880M’s advantage: it achieves 46.40 GPixel/s and 139.2 GTexel/s, versus the HD 8870M’s 12.40 GPixel/s and 31.00 GTexel/s. FP32 compute is 4.454 TFLOPS for the 880M versus 992.0 GFLOPS for the HD 8870M—a 4.5-fold difference. The 880M also supports FP16 at 4.454 TFLOPS (1:1), while the HD 8870M has no listed FP16 capability.

FAQ

Q: Which GPU is faster in the Geekbench OpenCL test?

A: The AMD Radeon 880M scores 31,285, while the AMD Radeon HD 8870M scores 8,462. The 880M wins with a deltaPct of -73% from the HD 8870M’s perspective.

Q: Do these two GPUs have the same overall performance percentile?

A: Yes, both are listed at the 43rd percentile among all GPUs, despite the large difference in their OpenCL scores.

Q: What memory type does each GPU use?

A: The HD 8870M uses 2 GB of GDDR5 on a 128-bit bus with 72.00 GB/s bandwidth. The 880M uses system shared memory with system-dependent bandwidth.

Q: Does the 880M support ray tracing?

A: Yes, the 880M has 12 ray tracing cores. The HD 8870M has no ray tracing cores listed.

Q: What is the process node difference?

A: The HD 8870M is built on a 28 nm process, while the 880M uses a 4 nm process, both from TSMC.

Q: Which GPU has a higher boost clock?

A: The 880M boosts to 2,900 MHz, whereas the HD 8870M boosts to 775 MHz.

The Verdict

The data points to a clear choice for anyone deciding between these two. The AMD Radeon 880M is superior in every benchmark category where scores exist. Its Geekbench OpenCL score is 73% higher than the HD 8870M’s, and it offers additional Vulkan, Passmark, and 3DMark results that the HD 8870M cannot match. The 880M also brings modern features like ray tracing, DirectX 12 Ultimate support, and a 1:1 FP16 rate, all while being an integrated part with a 15 W TDP. The HD 8870M, being end-of-life and from 2013, has no path to competitiveness in this comparison. That said, the HD 8870M does have dedicated GDDR5 memory, which could theoretically offer consistent bandwidth, but its 72.00 GB/s is far below what the 880M can achieve with system memory in a modern platform. For raw compute, gaming, or API support, the 880M is the only logical pick. The HD 8870M’s sole advantage is its discrete form factor, but the benchmark data shows that advantage is irrelevant against the 880M’s architectural lead.

Specification Differences

• Chip: Venus vs Strix Point
• Architecture: GCN 1.0 vs RDNA 3.5
• Generation: Solar System (HD 8800M) vs Navi III IGP (Strix Point Mobile)
• Process Node: 28 nm vs 4 nm
• Transistors: 1,500 million vs 34,000 million
• Die Size: 123 mm² vs 233 mm²
• Transistor Density: 12.2M / mm² vs 145.9M / mm²
• Base Clock: 725 MHz vs 400 MHz
• Boost Clock: 775 MHz vs 2,900 MHz
• Memory Size: 2 GB vs System Shared
• Memory Type: GDDR5 vs System Shared
• Memory Bus Width: 128 bit vs System Shared
• Memory Bandwidth: 72.00 GB/s vs System Dependent
• Shading Units: 640 vs 768
• TMUs: 40 vs 48
• ROPs: 16 vs 16
• Ray Tracing Cores: None vs 12
• Pixel Rate: 12.40 GPixel/s vs 46.40 GPixel/s
• Texture Rate: 31.00 GTexel/s vs 139.2 GTexel/s
• FP32: 992.0 GFLOPS vs 4.454 TFLOPS
• FP16: None vs 4.454 TFLOPS (1:1)
• TDP: Not listed vs 15 W
• Slot Width: Not listed vs IGP
• Power Connectors: Not listed vs None
• Bus Interface: PCIe 3.0 x16 vs PCIe 4.0 x8
• Display Outputs: Not listed vs Portable Device Dependent
• DirectX Support: 12 (11_1) vs 12 Ultimate (12_2)
• Vulkan Support: 1.2.170 vs 1.4
• Production Status: End-of-life vs Active
• Release Date: 2013-03-31 vs 2024-07-14
• Predecessor: London vs Navi II IGP
• Successor: Gem System vs None listed