AMD Radeon R9 M390X vs Intel Arc A750 Comparison

AMD
RADEON

AMD Radeon R9 M390X

CORE STATE Amethyst
VRAM 4 GB
CLOCK SPEED
TDP 75 W
BUS WIDTH 256 bit
ARCHITECTURE GCN 3.0
nm
PROCESS 28 nm
LAUNCH DATE 2015
VS
Intel
GPU

Arc A750

CORE STATE DG2-512
VRAM 8 GB
CLOCK SPEED 2400 MHz
TDP 225 W
BUS WIDTH 256 bit
ARCHITECTURE Xe-HPG
nm
PROCESS 6 nm
LAUNCH DATE 2022

PERFORMANCE BENCHMARKS

geekbench_metal
24,373
N/A
geekbench_vulkan
16,951
85,631
3dmark_3dmark_steel_nomad_dx12
N/A
2,612
geekbench_opencl
N/A
98,554
passmark_directx_10
N/A
65
passmark_directx_11
N/A
72
passmark_directx_12
N/A
70
passmark_directx_9
N/A
181
passmark_g2d
N/A
732
passmark_g3d
N/A
12,534
passmark_gpu_compute
N/A
5,368

Analysis: AMD Radeon R9 M390X vs Intel Arc A750

The AMD Radeon R9 M390X and Intel Arc A750 occupy the same percentile tier in the overall GPU hierarchy, both sitting at the 66th percentile against all GPUs. Their average benchmark scores are remarkably close: the R9 M390X posts a 20662 average, while the Arc A750 posts 20582, a difference of just 0.4 percent. Yet the single head-to-head test available, Geekbench Vulkan, reveals an enormous gulf in raw performance, with the Arc A750 scoring 85631 versus the R9 M390X's 16951, a delta of -80.2 percent. This discrepancy between aggregate averages and the direct comparison underscores that these cards are not peers in actual capability, despite similar percentile placements.

Head-to-Head Benchmarks

The only direct benchmark comparison in the data is Geekbench Vulkan, and it is not close. The Intel Arc A750 delivers 85631 points, while the AMD Radeon R9 M390X manages just 16951 points. That is an 80.2 percent deficit for the AMD part, meaning the Arc A750 is roughly five times faster in this API workload. In practical terms, Vulkan-based games and compute applications will see a massive performance advantage on the Intel card. The R9 M390X's score is so far behind that it effectively places it in a different performance class for modern APIs.

When looking at the nearest rivals list, the R9 M390X sits just 0.2 percent behind the AMD Radeon RX 5600 XT and 0.4 percent ahead of the Arc A750 in average score. This is a statistical tie across all benchmarks aggregated, yet the Vulkan result shows the Arc A750 winning decisively. The explanation lies in the fact that the R9 M390X only has two benchmark entries—Geekbench Metal and Geekbench Vulkan—while the Arc A750 has ten entries spanning DirectX 9 through 12, OpenCL, and compute workloads. The Arc A750's average is dragged down by older DirectX 9 and 10 tests where it scores 181 and 65 respectively, while its modern API scores are far stronger. For example, its Geekbench OpenCL score is 98554, and its Passmark G3D score is 12534. The R9 M390X simply lacks comparable data across those legacy tests.

The Arc A750 also shows a clear win in the head-to-head table with 1 win versus 0 for the R9 M390X. That single win is the Vulkan test, but the margin is so large that it outweighs the absence of other direct comparisons. The data suggests that any modern workload leveraging Vulkan will favor the Intel card overwhelmingly. The R9 M390X's Geekbench Metal score of 24373 is not directly comparable to any Arc A750 result, but Metal is Apple-specific and irrelevant for the typical PC builder comparing these two.

Where Each One Wins

The AMD Radeon R9 M390X wins in the category of thermal and power efficiency. Its TDP is 75 W, compared to the Arc A750's 225 W, meaning it draws one-third the power. This makes it suitable for mobile platforms, as indicated by its MXM Module slot width and lack of power connectors. The Arc A750 requires a dual-slot cooler, a 6-pin plus an 8-pin power connector, and a suggested 550 W PSU. The R9 M390X also has a much smaller die at 366 mm² versus 406 mm², and fewer transistors at 5,000 million versus 21,700 million.

The Intel Arc A750 wins in every measurable performance category. Its FP32 throughput is 17.20 TFLOPS versus 2.961 TFLOPS for the R9 M390X, a 5.8x advantage. Its pixel rate is 268.8 GPixel/s versus 23.14 GPixel/s, and its texture rate is 537.6 GTexel/s versus 92.54 GTexel/s. Memory bandwidth is 512.0 GB/s versus 160.0 GB/s, a 3.2x difference. The Arc A750 also has 8 GB of GDDR6 memory versus 4 GB of GDDR5, double the capacity and a newer type. The Intel card supports PCIe 4.0 x16 while the AMD card is limited to PCIe 3.0 x16.

For use cases, the R9 M390X is a legacy mobile part from 2015, suited for older laptops or embedded systems where power draw is critical. The Arc A750, released in 2022, targets desktop gamers and content creators who need modern API support, ray tracing, and high-bandwidth memory. The Arc A750's DirectX 12 Ultimate support and 28 ray tracing cores place it firmly in the current generation, while the R9 M390X's DirectX 12 (12_0) support is a baseline feature set without ray tracing.

Architecture Differences

The two GPUs come from different eras and design philosophies. The R9 M390X uses AMD's GCN 3.0 architecture, built on a 28 nm process at TSMC. It packs 5,000 million transistors on a 366 mm² die, yielding a transistor density of 13.7M per mm². The chip is codenamed Amethyst and belongs to the Gem System generation (R9 M300 series). Its predecessor was Solar System, and its successor is Polaris Mobile. The architecture uses 2048 shading units, 128 TMUs, and 32 ROPs. It has no dedicated ray tracing or tensor cores. Its FP16 performance is identical to FP32 at 2.961 TFLOPS, indicating a 1:1 ratio.

The Arc A750 uses Intel's Xe-HPG architecture, built on a 6 nm process also at TSMC. It has 21,700 million transistors on a 406 mm² die, a density of 53.4M per mm². The chip is DG2-512 and belongs to the Alchemist generation (Arc 7). Its predecessor was Xe Graphics, and its successor is Battlemage. It has 3584 shading units, 224 TMUs, and 112 ROPs, plus 28 ray tracing cores. Its FP16 performance is 34.41 TFLOPS, exactly double its FP32 figure of 17.20 TFLOPS, indicating a 2:1 ratio. The process node advantage is stark: 6 nm versus 28 nm, allowing over four times the transistor density.

Architecturally, the R9 M390X is a compute-oriented design from the GCN era, while the Arc A750 is a gaming-first design with dedicated ray tracing hardware. The Arc A750 supports Vulkan 1.4 and DirectX 12 Ultimate, whereas the R9 M390X supports Vulkan 1.2.170 and DirectX 12 (12_0). Both support OpenGL 4.6. The R9 M390X's memory runs at 1250 MHz (5 Gbps effective) while the Arc A750's runs at 2000 MHz (16 Gbps effective), a 3.2x bandwidth difference. The R9 M390X has no base or boost clock listed, but the Arc A750 has a base of 2050 MHz and a boost of 2400 MHz.

FAQ

Q: Which GPU has a higher average benchmark score?

A: The AMD Radeon R9 M390X has an average benchmark score of 20662, which is 0.4 percent higher than the Intel Arc A750's 20582. However, this is based on different benchmark sets; the R9 M390X has only two benchmarks listed, while the Arc A750 has ten.

Q: How does the Geekbench Vulkan score compare between the two?

A: The Intel Arc A750 scores 85631 in Geekbench Vulkan, while the AMD Radeon R9 M390X scores 16951. This gives the Arc A750 an 80.2 percent advantage, making it roughly five times faster in Vulkan workloads.

Q: What is the memory capacity and type of each GPU?

A: The AMD Radeon R9 M390X has 4 GB of GDDR5 memory on a 256-bit bus with 160.0 GB/s bandwidth. The Intel Arc A750 has 8 GB of GDDR6 memory on a 256-bit bus with 512.0 GB/s bandwidth.

Q: Which GPU supports ray tracing?

A: Only the Intel Arc A750 supports ray tracing, with 28 dedicated ray tracing cores. The AMD Radeon R9 M390X has no ray tracing hardware and uses a DirectX 12 (12_0) feature set without ray tracing support.

Q: What are the power requirements for each card?

A: The AMD Radeon R9 M390X has a 75 W TDP and requires no power connectors, using an MXM Module slot. The Intel Arc A750 has a 225 W TDP, requires a dual-slot cooler, one 6-pin and one 8-pin power connector, and a suggested 550 W PSU.

Q: Which GPU has a more recent release date?

A: The Intel Arc A750 was released on 2022-10-11, while the AMD Radeon R9 M390X was released on 2015-05-04. The Arc A750 is over seven years newer and uses a 6 nm process compared to the R9 M390X's 28 nm process.

The Verdict

The data is unambiguous: the Intel Arc A750 is the superior performer for any modern workload. Its 17.20 TFLOPS FP32 throughput, 512.0 GB/s memory bandwidth, and 28 ray tracing cores put it in a completely different class from the R9 M390X's 2.961 TFLOPS and 160.0 GB/s. The 80.2 percent Vulkan deficit for the R9 M390X confirms this gap in practice.

The R9 M390X's only advantages are power consumption and form factor. At 75 W with no auxiliary power connectors, it fits into compact mobile systems where the Arc A750's 225 W TDP and dual-slot cooler would be impossible. If you are upgrading a legacy laptop with an MXM slot, the R9 M390X is a drop-in replacement. For any desktop build, the Arc A750 is the only rational choice.

The Arc A750's average benchmark score is statistically tied with the R9 M390X, but this is misleading because the R9 M390X lacks scores for DirectX 9, 10, 11, and 12 tests, OpenCL, and compute workloads. The Arc A750's Passmark G3D score of 12534 and OpenCL score of 98554 demonstrate real-world capability, while the R9 M390X's two scores are narrow in scope. The Intel card also has double the memory (8 GB vs 4 GB) and a newer memory type (GDDR6 vs GDDR5), which matters for texture-heavy games and larger datasets.

Specification Differences

| Specification | AMD Radeon R9 M390X | Intel Arc A750 |

|---|---|---|

| Architecture | GCN 3.0 | Xe-HPG |

| Process Node | 28 nm | 6 nm |

| Transistors | 5,000 million | 21,700 million |

| Die Size | 366 mm² | 406 mm² |

| Transistor Density | 13.7M / mm² | 53.4M / mm² |

| Base Clock | None listed | 2050 MHz |

| Boost Clock | None listed | 2400 MHz |

| Memory Clock | 1250 MHz (5 Gbps effective) | 2000 MHz (16 Gbps effective) |

| Memory Size | 4 GB | 8 GB |

| Memory Type | GDDR5 | GDDR6 |

| Memory Bandwidth | 160.0 GB/s | 512.0 GB/s |

| Shading Units | 2048 | 3584 |

| TMUs | 128 | 224 |

| ROPs | 32 | 112 |

| Ray Tracing Cores | None | 28 |

| Pixel Rate | 23.14 GPixel/s | 268.8 GPixel/s |

| Texture Rate | 92.54 GTexel/s | 537.6 GTexel/s |

| FP32 Performance | 2.961 TFLOPS | 17.20 TFLOPS |

| FP16 Performance | 2.961 TFLOPS (1:1) | 34.41 TFLOPS (2:1) |

| TDP | 75 W | 225 W |

| Slot Width | MXM Module | Dual-slot |

| Power Connectors | None | 1x 6-pin + 1x 8-pin |

| Suggested PSU | None listed | 550 W |

| Bus Interface | PCIe 3.0 x16 | PCIe 4.0 x16 |

| Display Outputs | Portable Device Dependent | 1x HDMI 2.1, 3x DisplayPort 2.0 |

| DirectX Support | 12 (12_0) | 12 Ultimate (12_2) |

| Vulkan Support | 1.2.170 | 1.4 |

| Release Date | 2015-05-04 | 2022-10-11 |

| Launch MSRP | None listed | 289 USD |

DETAILED SPECIFICATIONS

SPECIFICATION
R9 M390X
A750
Core Specs
Shading Units
2,048
3,584 +75.0%
Shaders
2,048
3,584 +75.0%
TMUs
128
224 +75.0%
ROPs
32
112 +250.0%
Compute Units
32
Execution Units
448
Clocks
Base Clock
2050 MHz
Boost Clock
2400 MHz
GPU Clock
723 MHz
Memory Clock
1250 MHz 5 Gbps effective
2000 MHz 16 Gbps effective
Memory
Memory Size
4 GB
8 GB
VRAM (MB)
4,096
8,192 +100.0%
Memory Type
GDDR5
GDDR6
Memory Bus
256 bit
256 bit
Bandwidth
160.0 GB/s
512.0 GB/s
Cache
L1 Cache
16 KB (per CU)
L2 Cache
512 KB
16 MB
Performance
Pixel Rate
23.14 GPixel/s
268.8 GPixel/s
Texture Rate
92.54 GTexel/s
537.6 GTexel/s
FP32 (TFLOPS)
2.961 TFLOPS
17.20 TFLOPS
FP64 (TFLOPS)
185.1 GFLOPS (1:16)
2.150 TFLOPS (1:8)
FP16 (TFLOPS)
2.961 TFLOPS (1:1)
34.41 TFLOPS (2:1)
AI/RT
RT Cores
28
XMX Cores
448
Power
TDP
75 W
225 W
TDP (W)
75
225 +200.0%
Suggested PSU
550 W
Power Connectors
None
1x 6-pin + 1x 8-pin
Architecture
Architecture
GCN 3.0
Xe-HPG
GPU Name
Amethyst
DG2-512
Generation
Gem System (R9 M300)
Alchemist (Arc 7)
Process Size
28 nm
6 nm
Transistors
5,000 million
21,700 million
Die Size
366 mm²
406 mm²
Foundry
TSMC
TSMC
Density
13.7M / mm²
53.4M / mm²
API Support
DirectX
12 (12_0)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.2.170
1.4
OpenCL
2.1
3.0
Shader Model
6.5
6.6
Physical
Slot Width
MXM Module
Dual-slot
Outputs
Portable Device Dependent
1x HDMI 2.13x DisplayPort 2.0
Bus Interface
PCIe 3.0 x16
PCIe 4.0 x16
Other
Launch Price
289 USD
Production
End-of-life
End-of-life
Predecessor
Solar System
Xe Graphics
Successor
Polaris Mobile
Battlemage
View Radeon R9 M390X Details View Arc A750 Details