AMD Radeon R9 M380 vs Intel Iris Xe MAX Graphics Comparison

# AMD Radeon R9 M380 vs Intel Iris Xe MAX Graphics

The AMD Radeon R9 M380 and Intel Iris Xe MAX Graphics represent two very different approaches to mobile graphics, separated by five years of architecture evolution. The data shows a clear overall winner in raw compute, but the story is more nuanced when considering specific workloads and system contexts. The Intel part wins the only shared benchmark, yet the AMD card holds its own in legacy API support and pixel throughput characteristics that matter for certain tasks.

Where Each One Wins

The Intel Iris Xe MAX Graphics wins the only directly comparable benchmark in the dataset. In Geekbench OpenCL, Intel scores 14315 against AMD’s 12565, a 12.2% advantage. This is a substantial margin in general-purpose compute workloads. The Intel GPU’s higher FP32 throughput of 2.534 TFLOPS, compared to 1.536 TFLOPS on the AMD part, explains much of this gap. Intel also doubles the FP16 rate to 5.069 TFLOPS (2:1), a feature AMD lacks entirely in the data. For applications leveraging half-precision math, Intel’s advantage would be even more pronounced.

The AMD Radeon R9 M380 wins in the context of memory bandwidth per compute unit. Its 96.00 GB/s of GDDR5 bandwidth exceeds Intel’s 68.26 GB/s LPDDR4X, giving AMD a 40.6% bandwidth advantage. This matters for texture-heavy workloads and situations where memory access patterns are the bottleneck rather than raw shader throughput. The AMD card also has a higher base clock at 900 MHz versus 300 MHz on Intel, though Intel’s boost clock of 1650 MHz far exceeds AMD’s 1000 MHz ceiling.

In the broader percentile ranking, AMD sits at the 58th percentile among all GPUs, while Intel is at the 56th. This 2-percentile gap suggests that despite losing the head-to-head OpenCL test, AMD’s overall benchmark profile—including its Metal score of 18476—places it slightly higher in the global distribution. AMD’s average benchmark score of 15521 versus Intel’s 14315 reflects this, with AMD leading by 8.4% in aggregate across all recorded tests.

The Verdict

For users prioritizing general compute performance in OpenCL-based applications, the Intel Iris Xe MAX Graphics is the clear choice. Its 12.2% lead in Geekbench OpenCL, combined with modern 10 nm fabrication and higher boost clocks, makes it the stronger candidate for productivity tasks that leverage GPU acceleration. The Intel part also offers PCIe 4.0 x8 connectivity, doubling the per-lane bandwidth of AMD’s PCIe 3.0 x16 interface.

For users who need broader API compatibility and higher memory bandwidth, the AMD Radeon R9 M380 remains relevant. Its Vulkan 1.2.170 support, while older than Intel’s Vulkan 1.4, still covers modern applications. The AMD card’s 96.00 GB/s memory bandwidth is critical for certain rendering workloads that saturate memory subsystems. Its higher pixel rate of 16.00 GPixel/s, however, is actually lower than Intel’s 39.60 GPixel/s—a 147% advantage for Intel in fill-rate-limited scenarios.

The data does not support choosing AMD for pure performance. Intel wins the only direct comparison and offers superior specifications in most measurable categories: FP32 (65% higher), texture rate (65% higher), pixel rate (147% higher), and boost clock (65% higher). AMD’s advantages are limited to memory bandwidth, base clock, and percentile ranking—the latter driven by its Metal benchmark result, which Intel was not tested on.

Head-to-Head Benchmarks

The only direct benchmark comparison available is Geekbench OpenCL. Intel scores 14315, while AMD scores 12565. The deltaPct of -12.2% indicates AMD trails Intel by 12.2% in this test. This is a decisive margin in compute-heavy workloads.

Contextualizing this with the nearest rivals provides additional insight. Intel’s score of 14315 places it within 0.3% of the NVIDIA GeForce GTX 1070 Ti’s average score of 14277, and within 0.5% of the AMD Radeon RX Vega 11’s 14385. Meanwhile, AMD’s R9 M380 score of 12565 is not directly listed among its nearest rivals’ scores, but its average benchmark score of 15521 sits within 0.2% of the NVIDIA GeForce GTX 1080 Ti’s 15548, suggesting the Metal benchmark significantly boosts its aggregate standing.

The texture rate difference is stark: Intel achieves 79.20 GTexel/s versus AMD’s 48.00 GTexel/s. This 65% advantage means Intel processes textured geometry substantially faster. Similarly, pixel rate favors Intel at 39.60 GPixel/s versus 16.00 GPixel/s, a 147% difference that impacts fill-rate-bound rendering. These specification-level differences align with the OpenCL benchmark result, where Intel’s superior compute throughput translates directly into higher scores.

FAQ

Q: Which GPU has higher memory bandwidth?

A: The AMD Radeon R9 M380 has 96.00 GB/s bandwidth from GDDR5 memory, while the Intel Iris Xe MAX Graphics has 68.26 GB/s from LPDDR4X. AMD leads by 40.6% in this metric.

Q: Does the Intel Iris Xe MAX support half-precision floating point?

A: Yes, Intel lists FP16 at 5.069 TFLOPS (2:1), indicating half-rate FP16 execution. The AMD Radeon R9 M380 has no FP16 field specified in the data.

Q: What is the average benchmark score difference between the two?

A: AMD’s average benchmark score is 15521, while Intel’s is 14315. AMD leads by 8.4% in aggregate, though this includes AMD’s Geekbench Metal score of 18476, which Intel was not tested on.

Q: Which GPU has better Vulkan API support?

A: Intel supports Vulkan 1.4, while AMD supports Vulkan 1.2.170. Intel’s newer API version indicates better forward compatibility with modern applications.

Q: Are both GPUs the same size in terms of die area?

A: No. AMD’s die size is 160 mm², while Intel’s is 95 mm². Intel’s die is 40.6% smaller despite offering higher compute performance.

Q: Which GPU has more ROPs?

A: Intel has 24 ROPs versus AMD’s 16 ROPs. This contributes to Intel’s higher pixel rate of 39.60 GPixel/s versus AMD’s 16.00 GPixel/s.

Architecture Differences

The architectural gap between these two GPUs spans five years of evolution. AMD uses the GCN 2.0 architecture on a 28 nm TSMC process, codenamed Strato, part of the Gem System generation. Intel uses Generation 12.1 architecture on a 10 nm Intel process, with the DG1 chip from the Xe Graphics generation. The process node difference is significant: 28 nm versus 10 nm, representing a full two-generation fabrication jump.

Transistor counts reflect this difference. AMD packs 2,080 million transistors into a 160 mm² die, yielding a density of 13.0M / mm². Intel does not list transistor count or density, but its die size is 95 mm²—40.6% smaller than AMD’s. The smaller die with higher performance suggests Intel’s 10 nm process achieves superior transistor density.

Both GPUs have 768 shading units and 48 TMUs, an identical compute core configuration. The differences emerge in fixed-function hardware: AMD has 16 ROPs, while Intel has 24 ROPs (50% more). This explains Intel’s higher pixel rate despite similar shader counts. Intel also doubles FP16 throughput via 2:1 ratio, a feature absent from AMD’s specification.

The memory architectures differ fundamentally. AMD uses GDDR5 with 1500 MHz base clock (6 Gbps effective), while Intel uses LPDDR4X at 2133 MHz (4.3 Gbps effective). Both have 4 GB capacity and 128-bit bus width, but AMD’s higher memory clock yields 96.00 GB/s versus Intel’s 68.26 GB/s. The bus interface also differs: AMD uses PCIe 3.0 x16, while Intel uses PCIe 4.0 x8. Despite having fewer lanes, Intel’s PCIe 4.0 provides comparable or better bandwidth per lane.

Production status differs as well. AMD’s R9 M380 is end-of-life, released on 2015-05-04, with its predecessor being Solar System and successor Polaris Mobile. Intel’s Iris Xe MAX is also end-of-life, released on 2020-10-30, with predecessor Graphics and successor Alchemist. Neither GPU has a launch MSRP listed in the data.

Specification Differences

The two GPUs differ across nearly every measurable specification, reflecting their generational gap. AMD’s base clock is 900 MHz, while Intel’s is 300 MHz—AMD leads by 200% at idle. However, Intel’s boost clock of 1650 MHz exceeds AMD’s 1000 MHz by 65%. This implies Intel’s power management allows for aggressive boosting under load, while AMD runs closer to a fixed clock.

Memory specifications show AMD’s advantage in bandwidth: 96.00 GB/s versus 68.26 GB/s (40.6% higher), with GDDR5 versus LPDDR4X memory types. Both have 4 GB capacity and 128-bit bus, but AMD’s 1500 MHz memory clock versus Intel’s 2133 MHz reflects different memory technologies. AMD’s 6 Gbps effective rate versus Intel’s 4.3 Gbps effective rate further illustrates the bandwidth gap.

Compute throughput significantly favors Intel. FP32 performance is 2.534 TFLOPS versus 1.536 TFLOPS (65% higher). Texture rate is 79.20 GTexel/s versus 48.00 GTexel/s (65% higher). Pixel rate is 39.60 GPixel/s versus 16.00 GPixel/s (147% higher). Intel also lists FP16 at 5.069 TFLOPS, which AMD does not specify.

Power specifications are only listed for Intel: 25 W TDP and 200 W suggested PSU. AMD has no TDP or PSU recommendation in the data. Intel is classified as IGP (integrated graphics) with no display outputs, while AMD’s display outputs are unspecified. API support differs with Intel supporting DirectX 12_1 versus AMD’s 12_0, and Vulkan 1.4 versus 1.2.170. Both support OpenGL 4.6.

The ROP count differs (24 versus 16), while shading units and TMUs are identical at 768 and 48 respectively. Die size favors Intel at 95 mm² versus 160 mm², though AMD’s transistor count of 2,080 million is listed while Intel’s is absent. The bus interface differs: PCIe 4.0 x8 for Intel versus PCIe 3.0 x16 for AMD, with Intel’s newer standard providing higher per-lane bandwidth.