AMD Radeon 820M vs AMD Ryzen Z1 Extreme GPU Comparison

AMD Radeon 820M and AMD Ryzen Z1 Extreme GPU are both integrated graphics solutions from AMD, but they serve very different performance segments. The Radeon 820M is a low-power IGP built on the RDNA 3.5 architecture, while the Ryzen Z1 Extreme GPU is a much larger, higher-power part based on RDNA 3.0. The database shows a massive performance gap driven by core counts, clock behavior, memory configuration, and power envelopes.

FAQ

Q: What are the architectural generations of these two GPUs?

A: The AMD Radeon 820M uses RDNA 3.5 architecture and belongs to the Navi III IGP (Strix Point Mobile) generation. The AMD Ryzen Z1 Extreme GPU uses RDNA 3.0 architecture and is classified as a Console GPU (AMD) generation part.

Q: How do the shading unit counts compare?

A: The Radeon 820M has 128 shading units, while the Ryzen Z1 Extreme GPU has 768 shading units. That is a 6x difference in raw shader count, which directly explains the large gap in compute performance.

Q: What is the difference in FP32 floating-point performance?

A: The Radeon 820M delivers 716.8 GFLOPS of FP32 performance. The Ryzen Z1 Extreme GPU delivers 8.294 TFLOPS, which is approximately 11.6 times higher.

Q: What memory configurations do these GPUs use?

A: The Radeon 820M uses system shared memory with a system-dependent bandwidth. The Ryzen Z1 Extreme GPU has 16 GB of dedicated LPDDR5 memory on a 64-bit bus with 51.20 GB/s of bandwidth.

Q: What are the power ratings for each GPU?

A: The Radeon 820M has a 15 W TDP. The Ryzen Z1 Extreme GPU has a 30 W TDP, double the power envelope of the smaller part.

Q: Which GPU has more ray tracing cores?

A: The Radeon 820M has 2 ray tracing cores. The Ryzen Z1 Extreme GPU has 12 ray tracing cores, a 6x difference that corresponds with the shading unit ratio.

Architecture Differences

The two GPUs share a common AMD family lineage but diverge in architecture revision, scale, and implementation. The Radeon 820M is built on RDNA 3.5, while the Ryzen Z1 Extreme GPU uses RDNA 3.0. Both are fabricated on a 4 nm process at TSMC, so the manufacturing node is identical. The architectural difference is therefore not about process technology but about the design generation and the scale of the execution units.

The Radeon 820M is a compact IGP with 128 shading units, 8 texture mapping units, and 4 render output units. It includes 2 ray tracing cores. The Ryzen Z1 Extreme GPU is a substantially larger design with 768 shading units, 48 TMUs, and 32 ROPs, plus 12 ray tracing cores. The Ryzen Z1 Extreme GPU also has a known transistor count of 25,390 million on a die size of 178 mm², giving a transistor density of 142.6M per mm². The Radeon 820M transistor count and die size are not recorded in the database.

Clock behavior differs as well. The Radeon 820M has a base clock of 400 MHz and a boost clock of 2800 MHz. The Ryzen Z1 Extreme GPU has a higher base clock of 800 MHz but a slightly lower boost clock of 2700 MHz. The memory clocks differ: the Radeon 820M uses system shared memory, while the Ryzen Z1 Extreme GPU has a memory clock of 800 MHz with 6.4 Gbps effective data rate. The Radeon 820M runs its FP16 and FP32 at a 1:1 ratio, both at 716.8 GFLOPS. The Ryzen Z1 Extreme GPU runs FP16 at 16.59 TFLOPS, which is a 2:1 ratio relative to its FP32 figure of 8.294 TFLOPS.

The Radeon 820M uses a PCIe 4.0 x8 bus interface and has no power connectors. The Ryzen Z1 Extreme GPU has no recorded bus interface and also uses no power connectors. The Radeon 820M is an IGP with slot width marked as IGP. The Ryzen Z1 Extreme GPU has physical dimensions recorded: 280 mm length (11 inches), 111 mm height (4.4 inches), and 21 mm width (0.8 inches), suggesting it is an integrated module on a larger carrier board.

Head-to-Head Benchmarks

The database contains no direct head-to-head benchmark results between these two GPUs, and the average benchmark score for both is recorded as zero. The percentile versus all GPUs is identical at 50 for both parts. Without measured benchmark scores, the comparison must rely on the recorded specification data, which shows a decisive performance advantage for the Ryzen Z1 Extreme GPU across every compute metric.

The FP32 throughput difference is the clearest indicator. The Radeon 820M produces 716.8 GFLOPS, while the Ryzen Z1 Extreme GPU produces 8.294 TFLOPS. The larger part is roughly 11.6 times faster in raw single-precision compute. In FP16, the Radeon 820M stays at 716.8 GFLOPS due to its 1:1 ratio, while the Ryzen Z1 Extreme GPU reaches 16.59 TFLOPS with its 2:1 ratio. That is a 23.1 times higher FP16 throughput for the Ryzen Z1 Extreme GPU.

Texture and pixel rates show the same pattern. The Radeon 820M has a texture rate of 22.40 GTexel/s and a pixel rate of 11.20 GPixel/s. The Ryzen Z1 Extreme GPU has a texture rate of 129.6 GTexel/s and a pixel rate of 86.40 GPixel/s. The Ryzen Z1 Extreme GPU is 5.8 times faster in texture fill and 7.7 times faster in pixel fill.

The memory subsystem reinforces the compute advantage. The Radeon 820M relies on system shared memory with bandwidth described as system dependent, meaning its performance varies with the host platform. The Ryzen Z1 Extreme GPU has 16 GB of LPDDR5 memory on a 64-bit bus delivering 51.20 GB/s of fixed bandwidth. This dedicated memory arrangement gives the Ryzen Z1 Extreme GPU a consistent memory bandwidth that the Radeon 820M cannot guarantee.

Ray tracing hardware also differs significantly. The Radeon 820M has 2 ray tracing cores, while the Ryzen Z1 Extreme GPU has 12. That is a 6x increase in ray tracing cores, matching the shading unit ratio. The Radeon 820M does include ray tracing support, but the much higher core count on the Ryzen Z1 Extreme GPU indicates substantially better ray tracing throughput.

Specification Differences

The two GPUs differ in nearly every recorded specification field. The architecture is RDNA 3.5 for the Radeon 820M versus RDNA 3.0 for the Ryzen Z1 Extreme GPU. The generation differs: Navi III IGP (Strix Point Mobile) for the Radeon 820M, Console GPU (AMD) for the Ryzen Z1 Extreme GPU. The chip names differ as well, with the Radeon 820M using Krackan Point 2 and the Ryzen Z1 Extreme GPU using Phoenix.

Process node and foundry are the same: 4 nm at TSMC. Transistor count is unknown for the Radeon 820M, while the Ryzen Z1 Extreme GPU has 25,390 million transistors. Die size is unknown for the Radeon 820M, while the Ryzen Z1 Extreme GPU measures 178 mm². Transistor density is not recorded for the Radeon 820M, while the Ryzen Z1 Extreme GPU has 142.6M per mm².

Clock speeds differ. The Radeon 820M has a 400 MHz base clock and 2800 MHz boost clock. The Ryzen Z1 Extreme GPU has an 800 MHz base clock and 2700 MHz boost clock. The memory clock for the Radeon 820M is listed as system shared, while the Ryzen Z1 Extreme GPU has an 800 MHz memory clock with 6.4 Gbps effective. Memory size is system shared for the Radeon 820M versus 16 GB for the Ryzen Z1 Extreme GPU. Memory type is system shared versus LPDDR5. Bus width is system shared versus 64 bit. Bandwidth is system dependent versus 51.20 GB/s.

Core counts differ across the board. Shading units are 128 versus 768. TMUs are 8 versus 48. ROPs are 4 versus 32. Ray tracing cores are 2 versus 12. Pixel rate is 11.20 GPixel/s versus 86.40 GPixel/s. Texture rate is 22.40 GTexel/s versus 129.6 GTexel/s. FP32 is 716.8 GFLOPS versus 8.294 TFLOPS. FP16 is 716.8 GFLOPS (1:1) versus 16.59 TFLOPS (2:1).

TDP is 15 W versus 30 W. Slot width is IGP for the Radeon 820M, while the Ryzen Z1 Extreme GPU has no recorded slot width. The bus interface is PCIe 4.0 x8 for the Radeon 820M, while the Ryzen Z1 Extreme GPU has none recorded. Display outputs are portable device dependent for the Radeon 820M versus 1x USB Type-C for the Ryzen Z1 Extreme GPU. DirectX, OpenGL, and Vulkan support are identical: 12 Ultimate (12_2), 4.6, and 1.4 respectively.

Physical dimensions are not recorded for the Radeon 820M. The Ryzen Z1 Extreme GPU has dimensions of 280 mm length, 111 mm height, and 21 mm width. Release dates differ: the Radeon 820M was released on 2025-02-28, while the Ryzen Z1 Extreme GPU was released on 2023-06-12. The Radeon 820M has a predecessor listed as Navi II IGP. The Ryzen Z1 Extreme GPU has no predecessor recorded. The Radeon 820M has no launch MSRP recorded. The Ryzen Z1 Extreme GPU has a launch MSRP of 699 USD.

Where Each One Wins

The Radeon 820M wins in power efficiency and compactness. Its 15 W TDP is half that of the Ryzen Z1 Extreme GPU, making it suitable for small, low-power portable devices. It has a higher boost clock at 2800 MHz compared to 2700 MHz, which is a small but real advantage in lightly threaded or short-duration workloads. The Radeon 820M also uses the newer RDNA 3.5 architecture, which may bring architectural refinements over RDNA 3.0. Its PCIe 4.0 x8 interface is explicitly recorded, while the Ryzen Z1 Extreme GPU has no bus interface listed. The Radeon 820M has no physical dimensions recorded, consistent with an IGP that is integrated directly onto a processor package.

The Ryzen Z1 Extreme GPU wins in every measure of raw graphics performance. Its 768 shading units, 48 TMUs, and 32 ROPs provide 6x, 6x, and 8x the respective counts of the Radeon 820M. FP32 performance is 8.294 TFLOPS versus 716.8 GFLOPS, an 11.6x advantage. FP16 performance is 16.59 TFLOPS versus 716.8 GFLOPS, a 23.1x advantage. Texture rate is 129.6 GTexel/s versus 22.40 GTexel/s, and pixel rate is 86.40 GPixel/s versus 11.20 GPixel/s.

The Ryzen Z1 Extreme GPU also wins on memory. It has 16 GB of dedicated LPDDR5 memory with 51.20 GB/s bandwidth, while the Radeon 820M depends on system shared memory with system dependent bandwidth. Dedicated memory avoids contention with the CPU and provides predictable performance. The higher base clock of 800 MHz versus 400 MHz gives the Ryzen Z1 Extreme GPU a better minimum performance floor. The 12 ray tracing cores versus 2 provide a 6x advantage in ray tracing workloads.

The Ryzen Z1 Extreme GPU has a recorded launch MSRP of 699 USD. The Radeon 820M has no recorded launch MSRP.

The Verdict

The recorded data indicates a decisive performance hierarchy. The AMD Ryzen Z1 Extreme GPU is the much faster graphics processor in every compute, fill rate, memory, and ray tracing metric. Its FP32 throughput of 8.294 TFLOPS dwarfs the 716.8 GFLOPS of the Radeon 820M. Its dedicated 16 GB LPDDR5 memory with 51.20 GB/s bandwidth removes the variability of system shared memory. Its 768 shading units and 12 ray tracing cores position it for substantially heavier graphics and compute workloads.

The AMD Radeon 820M occupies the opposite role. With a 15 W TDP, it is designed for minimal power draw. Its 128 shading units, 4 ROPs, and 2 ray tracing cores are appropriate for basic graphics output and low-intensity tasks. The newer RDNA 3.5 architecture and higher 2800 MHz boost clock are notable, but they do not close the gap created by the 6x difference in shading units and the 11.6x difference in FP32 throughput.

The choice between these two depends entirely on the workload. Systems using the Radeon 820M should target light, power-constrained environments where the 15 W envelope and IGP form factor are priorities. Systems using the Ryzen Z1 Extreme GPU should target graphics-intensive applications where the 30 W power draw is acceptable in exchange for 8.294 TFLOPS of FP32 performance, 129.6 GTexel/s texture rate, and 86.40 GPixel/s pixel rate.

The identical percentile versus all GPUs at 50 and zero average benchmark scores for both parts mean the database does not yet contain standardized performance measurements for either GPU. The specification comparison is therefore the primary evidence. That evidence is unambiguous: the Ryzen Z1 Extreme GPU delivers more than an order of magnitude higher compute throughput, a fixed high-bandwidth memory subsystem, and six times the ray tracing hardware. The Radeon 820M offers a lower power draw, a newer architecture revision, and a higher boost clock, but those advantages are secondary to the massive execution resource disparity.