AMD Ryzen Z2 A GPU vs Intel Arc B390 Comparison

The Verdict

The recorded data positions the AMD Ryzen Z2 A GPU and Intel Arc B390 in entirely different tiers. The Intel Arc B390 is the faster part by a wide margin, delivering 7.680 TFLOPS FP32 compute against the AMD Ryzen Z2 A GPU's 1.638 TFLOPS. That is a 4.7x raw throughput advantage. The Arc B390 also holds a benchmark score of 1482 in 3DMark Steel Nomad DX12, placing it in the 9th percentile of all GPUs. The Ryzen Z2 A GPU has no recorded benchmark score and sits at the 50th percentile. The Arc B390 is the clear pick for any workload where compute throughput, pixel fill, or texture fill matters. The Ryzen Z2 A GPU is the pick only for scenarios where power draw is the dominant constraint, since it uses 15 W versus 80 W. The data indicates the Arc B390 is a discrete-class integrated part, while the Ryzen Z2 A GPU is an ultra-low-power console-class chip. Buyers needing maximum performance from the database should choose the Arc B390. Buyers needing minimal power consumption should choose the Ryzen Z2 A GPU.

Architecture Differences

The two GPUs come from different manufacturers and use different process nodes. The AMD Ryzen Z2 A GPU uses the Van Gogh chip on a 7 nm TSMC process. The Intel Arc B390 uses the Panther Lake chip on a 3 nm Intel process. The Ryzen Z2 A GPU is built on RDNA 2.0 architecture, while the Arc B390 uses Xe3-LPG architecture. The Ryzen Z2 A GPU belongs to the Console GPU (AMD) generation, while the Arc B390 belongs to the Arc Graphics-M (Panther Lake) generation.

The transistor counts differ significantly. The Ryzen Z2 A GPU packs 2,400 million transistors on a 163 mm² die, giving a transistor density of 14.7M per mm². The Arc B390's transistor count and die size are not recorded in the database. The Ryzen Z2 A GPU has 512 shading units, 32 texture mapping units, 16 ROPs, and 8 ray tracing cores. The Arc B390 has 1536 shading units, 48 TMUs, 24 ROPs, and 12 ray tracing cores. Neither part lists tensor cores. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The Ryzen Z2 A GPU uses a 128-bit memory bus with 16 GB of LPDDR5 memory and 102.4 GB/s bandwidth. The Arc B390 uses system shared memory, with system dependent bandwidth and a system shared bus width. The Arc B390's memory clock is listed as system shared, while the Ryzen Z2 A GPU's memory clock is 800 MHz with 6.4 Gbps effective.

The display outputs also differ. The Ryzen Z2 A GPU has one USB Type-C output. The Arc B390's display outputs are portable device dependent. The Arc B390 is an IGP with no power connectors and an IGP bus interface. The Ryzen Z2 A GPU has no recorded slot width, power connectors, suggested PSU, or bus interface.

Head-to-Head Benchmarks

The database records no direct head-to-head benchmark comparisons between the AMD Ryzen Z2 A GPU and the Intel Arc B390. The wins counters for both parts are zero. However, the Arc B390 has a single recorded benchmark result: 1482 in 3DMark Steel Nomad DX12. That score places it in the 9th percentile of all GPUs. The Ryzen Z2 A GPU has no recorded benchmark scores and an average score of zero. Its percentile of 50 is based on the database's general ranking, not on a measured test.

The Arc B390's nearest rivals in the database are older NVIDIA parts. It leads the NVIDIA GeForce GT 520MX by 1.3%, the NVIDIA GeForce 800M by 1.5%, the NVIDIA GeForce GT 625 OEM by 2.5%, and the NVIDIA GeForce GT 710 by 2.7%. The Arc B390's score of 1482 is only marginally above these rivals. That suggests the Arc B390, despite its high compute figures, lands in the lower end of the performance distribution in the database. The Ryzen Z2 A GPU has no nearest rivals listed, meaning it has no comparable measured data.

The compute figures tell a clearer story than the benchmark scores. The Arc B390 produces 7.680 TFLOPS FP32 and 15.36 TFLOPS FP16. The Ryzen Z2 A GPU produces 1.638 TFLOPS FP32 and 3.277 TFLOPS FP16. The Arc B390 is 4.7x faster in FP32 and 4.7x faster in FP16. Pixel rate favors the Arc B390 at 60.00 GPixel/s versus 25.60 GPixel/s for the Ryzen Z2 A GPU. Texture rate favors the Arc B390 at 120.0 GTexel/s versus 51.20 GTexel/s for the Ryzen Z2 A GPU. Every throughput metric in the database favors the Arc B390 by at least 2.3x.

Specification Differences

The two parts differ in every major specification category except API support. The process node differs: 7 nm TSMC for the Ryzen Z2 A GPU versus 3 nm Intel for the Arc B390. The transistor count is 2,400 million for the Ryzen Z2 A GPU and unknown for the Arc B390. The die size is 163 mm² for the Ryzen Z2 A GPU and unknown for the Arc B390. Transistor density is 14.7M per mm² for the Ryzen Z2 A GPU and not recorded for the Arc B390.

Clock speeds differ substantially. The Ryzen Z2 A GPU has a base clock of 1000 MHz and a boost clock of 1600 MHz. The Arc B390 has a base clock of 300 MHz and a boost clock of 2500 MHz. The Arc B390 boosts 900 MHz higher but idles much lower. Memory configurations are completely different: the Ryzen Z2 A GPU has 16 GB of LPDDR5 on a 128-bit bus with 102.4 GB/s bandwidth, while the Arc B390 uses system shared memory with system dependent bandwidth. The Ryzen Z2 A GPU has a memory clock of 800 MHz with 6.4 Gbps effective; the Arc B390's memory clock is system shared.

Compute resources differ: 512 shading units, 32 TMUs, 16 ROPs, and 8 RT cores for the Ryzen Z2 A GPU versus 1536 shading units, 48 TMUs, 24 ROPs, and 12 RT cores for the Arc B390. Pixel rate is 25.60 GPixel/s versus 60.00 GPixel/s. Texture rate is 51.20 GTexel/s versus 120.0 GTexel/s. FP32 is 1.638 TFLOPS versus 7.680 TFLOPS. FP16 is 3.277 TFLOPS versus 15.36 TFLOPS, both at a 2:1 ratio. TDP is 15 W versus 80 W. The Arc B390 is an IGP with no power connectors; the Ryzen Z2 A GPU has no recorded slot width or power connectors. Display outputs differ: one USB Type-C for the Ryzen Z2 A GPU versus portable device dependent for the Arc B390. Release dates differ by about a year: the Ryzen Z2 A GPU released on 2024-12-31, the Arc B390 on 2026-01-26. Both are active production parts. Neither has a recorded launch MSRP, predecessor, or successor.

FAQ

Q: Which GPU is faster in raw compute?

A: The Intel Arc B390. It delivers 7.680 TFLOPS FP32 and 15.36 TFLOPS FP16, versus 1.638 TFLOPS FP32 and 3.277 TFLOPS FP16 for the AMD Ryzen Z2 A GPU.

Q: What benchmark data exists for these two GPUs?

A: The Arc B390 has one recorded result: 1482 in 3DMark Steel Nomad DX12, placing it in the 9th percentile. The Ryzen Z2 A GPU has no recorded benchmark scores and an average score of zero.

Q: How does the Arc B390 compare to its nearest rivals?

A: It leads the NVIDIA GeForce GT 520MX by 1.3%, the NVIDIA GeForce 800M by 1.5%, the NVIDIA GeForce GT 625 OEM by 2.5%, and the NVIDIA GeForce GT 710 by 2.7%.

Q: What are the memory specifications of each GPU?

A: The Ryzen Z2 A GPU has 16 GB of LPDDR5 on a 128-bit bus with 102.4 GB/s bandwidth. The Arc B390 uses system shared memory with system dependent bandwidth and a system shared bus width.

Q: Which GPU uses more power?

A: The Arc B390 has an 80 W TDP. The Ryzen Z2 A GPU has a 15 W TDP.

Q: Do both GPUs support the same APIs?

A: Yes. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Where Each One Wins

The Intel Arc B390 wins in every measured performance category in the database. Its FP32 compute is 4.7x higher than the Ryzen Z2 A GPU. Its FP16 compute is also 4.7x higher. Its pixel rate of 60.00 GPixel/s is more than double the Ryzen Z2 A GPU's 25.60 GPixel/s. Its texture rate of 120.0 GTexel/s is more than double the 51.20 GTexel/s of the Ryzen Z2 A GPU. It has 3x the shading units, 1.5x the TMUs, 1.5x the ROPs, and 1.5x the ray tracing cores. It has a higher boost clock at 2500 MHz versus 1600 MHz. It is the only part of the two with a recorded benchmark score, and that score, 1482, confirms it functions as a working graphics solution in the database.

The AMD Ryzen Z2 A GPU wins in power efficiency and memory capacity. Its TDP of 15 W is one-fifth of the Arc B390's 80 W. It carries 16 GB of dedicated LPDDR5 memory with a fixed 102.4 GB/s bandwidth, whereas the Arc B390 depends on system shared memory with system dependent bandwidth. The Ryzen Z2 A GPU also has a higher base clock at 1000 MHz versus 300 MHz, which may benefit sustained low-power workloads. Its transistor density of 14.7M per mm² on a 7 nm process is recorded, while the Arc B390's transistor density is not recorded.

The use-case split follows the data. For gaming, rendering, or any compute-heavy task, the Arc B390 is the only choice with measured performance and a dominant throughput advantage. For ultra-portable or battery-constrained systems where 15 W is the power budget, the Ryzen Z2 A GPU is the only viable option. The Arc B390's 80 W TDP and IGP form factor with no power connectors suggest it targets larger portable devices. The Ryzen Z2 A GPU's single USB Type-C output and console generation label suggest an embedded or handheld role. The database does not record a head-to-head benchmark, so direct frame-rate comparisons are not possible, but the specification gaps are large enough to make the hierarchy clear: the Arc B390 sits far above the Ryzen Z2 A GPU in performance, while the Ryzen Z2 A GPU sits far below in power draw.