AMD Radeon RX Vega M GL vs Intel Arc A750 Comparison

AMD
RADEON

AMD Radeon RX Vega M GL

CORE STATE Polaris 22
VRAM 4 GB
CLOCK SPEED 1011 MHz
TDP 65 W
BUS WIDTH 1024 bit
ARCHITECTURE GCN 4.0
nm
PROCESS 14 nm
LAUNCH DATE 2018
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_opencl
19,549
98,554
geekbench_vulkan
22,757
85,631
3dmark_3dmark_steel_nomad_dx12
N/A
2,612
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 RX Vega M GL vs Intel Arc A750

AMD Radeon RX Vega M GL and Intel Arc A750 occupy very different corners of the GPU landscape, and the benchmark data reflects that gulf. The Arc A750 wins both shared head-to-head tests decisively, while the Vega M GL is an older, integrated part with far lower absolute scores. The data shows a clear performance hierarchy, but the two cards serve distinct purposes based on their physical design and the systems they were built for.

Where Each One Wins

The Intel Arc A750 wins every shared benchmark in the data set, and it wins by enormous margins. In the Geekbench OpenCL test, the Arc A750 scores 98,554 against the Vega M GL’s 19,549, a difference of roughly 80%. In the Geekbench Vulkan test, the Arc A750 scores 85,631 against 22,757, a gap of about 73%. There is no benchmark in the head-to-head data where the AMD part comes out ahead. The wins for the Arc A750 are not marginal; they are category-level differences in raw compute throughput.

The AMD Radeon RX Vega M GL does not win any head-to-head test in the provided data. Its wins, if any, would have to come from use cases not captured by these two benchmarks. The Vega M GL is an integrated graphics processor (IGP) with a 65 W TDP, designed for portable devices. Its advantage is not in benchmark scores but in its form factor: it requires no slot width, no power connectors, and no suggested PSU, making it suitable for compact systems where the Arc A750’s dual-slot, 225 W design would be impractical. The Arc A750, by contrast, is a discrete, dual-slot card with a 6-pin and 8-pin power connector requirement.

The data also shows both GPUs sit at the 66th percentile among all GPUs, which is a curious alignment. Despite the Arc A750’s massive lead in raw scores, its average benchmark score (20,582) is actually slightly lower than the Vega M GL’s average (21,153). This is because the Arc A750’s average is pulled down by low scores in several Passmark tests, particularly the DirectX 9 test (181) and the DirectX 10 test (65), while the Vega M GL only has two high Geekbench scores. The percentile ranking reflects a broader set of benchmarks, not just the head-to-head ones.

Architecture Differences

The two GPUs are built on entirely different architectures from different foundries. The AMD Radeon RX Vega M GL uses the GCN 4.0 architecture on a chip called Polaris 22, manufactured on a 14 nm process at GlobalFoundries. The Intel Arc A750 uses the Xe-HPG architecture on a chip called DG2-512, manufactured on a 6 nm process at TSMC. The process node difference is stark: 14 nm versus 6 nm, which contributes to the Arc A750’s much higher transistor density.

The transistor counts reflect the generational leap. The Vega M GL has 5,000 million transistors on a 208 mm² die, giving a density of 24.0 million transistors per square millimeter. The Arc A750 has 21,700 million transistors on a 406 mm² die, with a density of 53.4 million per square millimeter. That is over four times the transistor count on a die that is only about twice the size, and the density is more than double. The Arc A750 also features 28 dedicated ray tracing cores, a capability entirely absent from the Vega M GL, which lists no RT cores. The architectures also differ in their FP16 support: the Vega M GL has a 1:1 ratio for FP16 to FP32, while the Arc A750 has a 2:1 ratio, meaning it can process half-precision floating point at twice the rate of single-precision.

The API support also differs. The Vega M GL supports DirectX 12 (12_0) and Vulkan 1.3, while the Arc A750 supports DirectX 12 Ultimate (12_2) and Vulkan 1.4. The Arc A750’s DirectX 12 Ultimate designation indicates support for features like ray tracing and mesh shaders, which the Vega M GL’s 12_0 level does not include.

Head-to-Head Benchmarks

The Geekbench OpenCL test is the largest single win for the Intel Arc A750. The Arc A750 scores 98,554, while the AMD Vega M GL scores 19,549. The delta is -80.2% from the Arc A750’s perspective, meaning the Vega M GL achieves less than 20% of the Arc A750’s score. This is a massive gap, reflecting the difference in shading units (3,584 on the Arc A750 versus 1,280 on the Vega M GL), texture mapping units (224 versus 80), and raw FP32 throughput (17.20 TFLOPS versus 2.588 TFLOPS).

The Geekbench Vulkan test shows a similar but slightly smaller gap. The Arc A750 scores 85,631 against the Vega M GL’s 22,757, a delta of -73.4%. While the margin is still enormous, the Vega M GL performs relatively better in Vulkan than in OpenCL; its Vulkan score is about 16% higher than its OpenCL score, while the Arc A750’s Vulkan score is about 13% lower than its OpenCL score. This suggests the Vega M GL’s GCN architecture is comparatively stronger in Vulkan workloads, though it remains far behind in absolute terms.

The Arc A750’s Passmark scores provide additional context. Its G3D score is 12,534, and its GPU compute score is 5,368. Its DirectX 9 score of 181 is notably higher than its DirectX 10 (65), DirectX 11 (72), and DirectX 12 (70) scores, which is an unusual pattern likely reflecting driver optimization or the benchmark’s workload characteristics. The 3DMark Steel Nomad DX12 score of 2,612 is the only other modern benchmark listed for the Arc A750, and it is not compared against the Vega M GL in the head-to-head data.

Specification Differences

The memory subsystem is one of the clearest differentiators. The Vega M GL has 4 GB of HBM2 memory on a 1024-bit bus, with a bandwidth of 179.2 GB/s. The Arc A750 has 8 GB of GDDR6 memory on a 256-bit bus, with a bandwidth of 512.0 GB/s. The Arc A750 has more than double the memory capacity and nearly three times the bandwidth, despite having a narrower bus. The memory clock rates also differ: the Vega M GL runs at 700 MHz (1400 Mbps effective), while the Arc A750 runs at 2000 MHz (16 Gbps effective).

The compute units scale accordingly. The Vega M GL has 1,280 shading units, 80 TMUs, and 32 ROPs. The Arc A750 has 3,584 shading units, 224 TMUs, and 112 ROPs. The pixel rate and texture rate reflect these differences: the Vega M GL manages 32.35 GPixel/s and 80.88 GTexel/s, while the Arc A750 achieves 268.8 GPixel/s and 537.6 GTexel/s. The FP32 performance is 2.588 TFLOPS versus 17.20 TFLOPS, a factor of about 6.6.

The power and form factor differences are critical for system design. The Vega M GL is rated at 65 W TDP and is an IGP, meaning it is integrated onto a substrate or motherboard. The Arc A750 is rated at 225 W TDP, is dual-slot, requires a 1x 6-pin and 1x 8-pin power connector, and needs a 550 W suggested PSU. The bus interface also differs: the Vega M GL uses IGP, while the Arc A750 uses PCIe 4.0 x16. The display outputs differ, with the Vega M GL described as "Portable Device Dependent" and the Arc A750 offering 1x HDMI 2.1 and 3x DisplayPort 2.0.

FAQ

Q: Which GPU has higher raw compute performance?

A: The Intel Arc A750 is substantially ahead, with 17.20 TFLOPS FP32 versus the AMD Radeon RX Vega M GL’s 2.588 TFLOPS. In Geekbench OpenCL, the Arc A750 scores 98,554 versus 19,549, a gap of -80.2%.

Q: Can the AMD Radeon RX Vega M GL be used in a desktop tower?

A: The Vega M GL is an integrated GPU (IGP) with a 65 W TDP and no slot width, power connectors, or suggested PSU. Its display outputs are listed as "Portable Device Dependent," indicating it is designed for portable devices rather than desktop expansion slots.

Q: Does the Intel Arc A750 support ray tracing?

A: Yes, the Arc A750 has 28 ray tracing cores and supports DirectX 12 Ultimate (12_2), which includes hardware-accelerated ray tracing features. The AMD Radeon RX Vega M GL lists no RT cores and supports only DirectX 12 (12_0).

Q: How do their memory bandwidths compare?

A: The Arc A750 has 512.0 GB/s bandwidth from 8 GB of GDDR6 on a 256-bit bus. The Vega M GL has 179.2 GB/s from 4 GB of HBM2 on a 1024-bit bus. The Arc A750 has nearly triple the bandwidth.

Q: What is the transistor density difference?

A: The Arc A750, built on TSMC’s 6 nm process, has a density of 53.4 million transistors per mm² (21,700 million total on 406 mm²). The Vega M GL, on GlobalFoundries’ 14 nm process, has 24.0 million per mm² (5,000 million on 208 mm²).

Q: Which GPU has a higher average benchmark score?

A: The AMD Radeon RX Vega M GL has a higher average score of 21,153, compared to the Intel Arc A750’s 20,582. However, this average is based on different benchmark sets; the Arc A750 includes multiple Passmark tests where it scores low, while the Vega M GL only has two Geekbench entries.

The Verdict

The Intel Arc A750 is the clear performance winner in every shared benchmark, and the data is unambiguous on this point. If raw compute, memory bandwidth, or modern API support are the criteria, the Arc A750 dominates. It offers 8 GB of memory versus 4 GB, over three times the bandwidth, and roughly 6.6 times the FP32 throughput. For any workload that leverages these resources, the Arc A750 is the only rational choice. Its 28 RT cores and DirectX 12 Ultimate support also make it the only option for ray-traced content, though no ray tracing benchmark is included in the data to quantify this advantage.

The AMD Radeon RX Vega M GL, however, is not without a rationale. It is an integrated part with a 65 W TDP, no external power connectors, and no slot width requirements. For a portable device or a compact system where a 225 W dual-slot card cannot fit, the Vega M GL is the only viable option between the two. Its average benchmark score of 21,153 is actually higher than the Arc A750’s 20,582, though this is an artifact of the benchmark sets used. The data shows the Vega M GL is competitive with older mobile GPUs like the AMD Radeon HD 8970M (delta -0.4%) and the NVIDIA RTX A4000 Mobile (delta -1.1%), placing it in a mid-range mobile class.

The verdict is straightforward: the Arc A750 for anyone who can accommodate a discrete, power-hungry card, and the Vega M GL for integrated, low-power portable systems. The 66th percentile ranking for both GPUs suggests their overall positioning in the broader GPU landscape is similar, but the head-to-head numbers show they are not competing for the same users. The Arc A750’s launch MSRP is 289 USD, a figure that contextualizes its performance tier, but the Vega M GL has no MSRP listed. Choose the Arc A750 for performance, the Vega M GL for integration.

DETAILED SPECIFICATIONS

SPECIFICATION
RX Vega M GL
A750
Core Specs
Shading Units
1,280
3,584 +180.0%
Shaders
1,280
3,584 +180.0%
TMUs
80
224 +180.0%
ROPs
32
112 +250.0%
Compute Units
20
—
Execution Units
—
448
Clocks
Base Clock
931 MHz
2050 MHz
Boost Clock
1011 MHz
2400 MHz
Memory Clock
700 MHz 1400 Mbps effective
2000 MHz 16 Gbps effective
Memory
Memory Size
4 GB
8 GB
VRAM (MB)
4,096
8,192 +100.0%
Memory Type
HBM2
GDDR6
Memory Bus
1024 bit
256 bit
Bandwidth
179.2 GB/s
512.0 GB/s
Cache
L1 Cache
16 KB (per CU)
—
L2 Cache
1024 KB
16 MB
Performance
Pixel Rate
32.35 GPixel/s
268.8 GPixel/s
Texture Rate
80.88 GTexel/s
537.6 GTexel/s
FP32 (TFLOPS)
2.588 TFLOPS
17.20 TFLOPS
FP64 (TFLOPS)
161.8 GFLOPS (1:16)
2.150 TFLOPS (1:8)
FP16 (TFLOPS)
2.588 TFLOPS (1:1)
34.41 TFLOPS (2:1)
AI/RT
RT Cores
—
28
XMX Cores
—
448
Power
TDP
65 W
225 W
TDP (W)
65
225 +246.2%
Suggested PSU
—
550 W
Power Connectors
—
1x 6-pin + 1x 8-pin
Architecture
Architecture
GCN 4.0
Xe-HPG
GPU Name
Polaris 22
DG2-512
Generation
Vega (Vega M)
Alchemist (Arc 7)
Process Size
14 nm
6 nm
Transistors
5,000 million
21,700 million
Die Size
208 mm²
406 mm²
Foundry
GlobalFoundries
TSMC
Density
24.0M / mm²
53.4M / mm²
API Support
DirectX
12 (12_0)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.3
1.4
OpenCL
2.1
3.0
Shader Model
6.7
6.6
Physical
Slot Width
IGP
Dual-slot
Outputs
Portable Device Dependent
1x HDMI 2.13x DisplayPort 2.0
Bus Interface
IGP
PCIe 4.0 x16
Other
Launch Price
—
289 USD
Production
End-of-life
End-of-life
Predecessor
—
Xe Graphics
Successor
—
Battlemage
View Radeon RX Vega M GL Details View Arc A750 Details