AMD Radeon 840M vs AMD Ryzen Z1 Extreme GPU Comparison

The Verdict

The data shows two AMD integrated graphics solutions at very different performance tiers. The AMD Ryzen Z1 Extreme GPU is the substantially stronger part, with a 768 shading unit count versus 256 on the AMD Radeon 840M. Raw compute figures confirm the gap: the Z1 Extreme GPU delivers 8.294 TFLOPS of FP32 throughput, while the Radeon 840M produces 1,484.8 GFLOPS. That is roughly 5.6 times more compute capacity for the Z1 Extreme GPU, and benchmark results indicate this translates into a dominant position across every category where the two overlap.

The Z1 Extreme GPU also carries a 50th percentile ranking among all GPUs, same as the Radeon 840M, but that equal percentile does not reflect the recorded hardware differences. The Radeon 840M is a low-power IGP designed for thin portable systems, with a 15 W TDP. The Ryzen Z1 Extreme GPU is a 30 W part, uses more memory bandwidth, and carries a larger die. For anyone choosing based strictly on performance, the Z1 Extreme GPU is the clear pick. The Radeon 840M is the choice only when power draw and system integration matter more than frame rates.

Architecture Differences

Both parts come from TSMC on a 4 nm process, but they belong to different architectural generations. The Radeon 840M uses RDNA 3.5 and is built on the Krackan Point chip, positioned within the Navi III IGP (Strix Point Mobile) generation. The Ryzen Z1 Extreme GPU uses older RDNA 3.0 architecture on the Phoenix chip, classified as a Console GPU. The transistor counts differ sharply: the Z1 Extreme GPU packs 25,390 million transistors on a 178 mm² die with a density of 142.6M per mm², while the Radeon 840M's transistor count and die size are not recorded in the database.

The memory architecture is another major split. The Radeon 840M uses system-shared memory with system-dependent bandwidth, meaning its performance scales with whatever system memory is installed. The Z1 Extreme GPU has a dedicated 16 GB LPDDR5 pool on a 64-bit bus, delivering 51.20 GB/s of bandwidth. That fixed memory allocation avoids contention with the CPU and gives the Z1 Extreme GPU a predictable memory performance baseline.

Clock behavior differs as well. The Radeon 840M has a 400 MHz base clock and a 2900 MHz boost clock. The Z1 Extreme GPU starts at 800 MHz base and boosts to 2700 MHz. The Radeon 840M's higher boost clock does not compensate for its much smaller execution engine. The Z1 Extreme GPU also lists its memory clock at 800 MHz with 6.4 Gbps effective transfer, while the Radeon 840M's memory clock is tied to the system.

Ray tracing hardware is present on both, but the Z1 Extreme GPU has 12 RT cores versus 4 on the Radeon 840M. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The Z1 Extreme GPU uses PCIe connectivity through a USB Type-C display output, while the Radeon 840M's display outputs are portable-device dependent and it connects via PCIe 4.0 x8.

FAQ

Q: Which GPU has higher raw compute throughput?

A: The AMD Ryzen Z1 Extreme GPU. It delivers 8.294 TFLOPS of FP32 and 16.59 TFLOPS of FP16 (2:1 ratio). The AMD Radeon 840M manages 1,484.8 GFLOPS for both FP32 and FP16 (1:1 ratio). The Z1 Extreme GPU is about 5.6 times faster in FP32.

Q: Do both GPUs use the same manufacturing process?

A: Yes, both are fabricated by TSMC on a 4 nm process. Their foundry is identical, but the underlying architectures differ: RDNA 3.5 for the Radeon 840M and RDNA 3.0 for the Ryzen Z1 Extreme GPU.

Q: How does memory configuration affect performance?

A: The Z1 Extreme GPU uses 16 GB of LPDDR5 on a 64-bit bus with 51.20 GB/s bandwidth. The Radeon 840M relies on system-shared memory with bandwidth described as system dependent. The fixed memory on the Z1 Extreme GPU provides consistent bandwidth, while the Radeon 840M's performance varies with the host system's memory.

Q: Which GPU has more shading units and texture units?

A: The Z1 Extreme GPU has 768 shading units, 48 TMUs, and 32 ROPs. The Radeon 840M has 256 shading units, 16 TMUs, and 8 ROPs. The Z1 Extreme GPU also has 12 RT cores versus 4 on the Radeon 840M.

Q: What are the power requirements for each?

A: The Radeon 840M has a 15 W TDP. The Ryzen Z1 Extreme GPU has a 30 W TDP. Neither requires external power connectors.

Q: What is the release timeline for these two GPUs?

A: The Ryzen Z1 Extreme GPU was released on 2023-06-12 with a launch MSRP of 699 USD. The Radeon 840M was released later, on 2025-02-28, and has no recorded launch MSRP in the database.

Specification Differences

The two GPUs differ across nearly every recorded specification. Process node is shared at 4 nm TSMC, but the architectures diverge: RDNA 3.5 for the Radeon 840M, RDNA 3.0 for the Z1 Extreme GPU. The Z1 Extreme GPU's chip is Phoenix with a 25,390 million transistor count and 178 mm² die size, while the Radeon 840M uses the Krackan Point chip with unknown transistor count and die size.

Clock speeds: the Radeon 840M runs at 400 MHz base and 2900 MHz boost. The Z1 Extreme GPU runs at 800 MHz base and 2700 MHz boost. The Z1 Extreme GPU's memory clock is 800 MHz with 6.4 Gbps effective, while the Radeon 840M's memory clock is system shared.

Compute resources: the Radeon 840M has 256 shading units, 16 TMUs, 8 ROPs, and 4 RT cores. The Z1 Extreme GPU has 768 shading units, 48 TMUs, 32 ROPs, and 12 RT cores. Pixel rate is 23.20 GPixel/s for the Radeon 840M versus 86.40 GPixel/s for the Z1 Extreme GPU. Texture rate is 46.40 GTexel/s versus 129.6 GTexel/s. FP32 throughput is 1,484.8 GFLOPS versus 8.294 TFLOPS. FP16 is 1,484.8 GFLOPS (1:1) versus 16.59 TFLOPS (2:1).

Memory: the Radeon 840M uses system-shared memory with system-dependent bandwidth. The Z1 Extreme GPU has 16 GB LPDDR5, a 64-bit bus, and 51.20 GB/s bandwidth. The Radeon 840M's TDP is 15 W; the Z1 Extreme GPU's is 30 W. The Z1 Extreme GPU has physical dimensions of 280 mm by 111 mm by 21 mm, while the Radeon 840M's dimensions are not recorded. The Radeon 840M uses a PCIe 4.0 x8 interface and portable-device-dependent display outputs. The Z1 Extreme GPU has a single USB Type-C display output. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Head-to-Head Benchmarks

The database lists no direct head-to-head benchmark scores for these two GPUs, so the comparison rests on the recorded hardware specifications and derived performance figures. The Z1 Extreme GPU's FP32 output of 8.294 TFLOPS dwarfs the Radeon 840M's 1,484.8 GFLOPS. In pixel throughput, the Z1 Extreme GPU reaches 86.40 GPixel/s against 23.20 GPixel/s for the Radeon 840M, a 3.7 times advantage. Texture fill rate follows the same pattern: 129.6 GTexel/s versus 46.40 GTexel/s, a 2.8 times lead for the Z1 Extreme GPU.

The shading unit count difference is the most telling. With 768 shading units versus 256, the Z1 Extreme GPU has exactly three times the shader hardware. The ROP count also triples from 8 to 32, and the RT core count triples from 4 to 12. These ratios align with the compute throughput numbers, indicating the Z1 Extreme GPU is not merely clocked higher but fundamentally larger in every execution resource.

The memory subsystem reinforces the gap. The Z1 Extreme GPU's 51.20 GB/s of dedicated LPDDR5 bandwidth is fixed and available. The Radeon 840M's system-shared memory has no guaranteed bandwidth figure in the database, so its effective performance depends entirely on the host platform. In a best-case system with fast memory, the Radeon 840M still faces a 3-to-1 deficit in shader count and a 5.6-to-1 deficit in FP32 compute.

Clock speeds provide the only area where the Radeon 840M holds a nominal advantage: its 2900 MHz boost is 200 MHz higher than the Z1 Extreme GPU's 2700 MHz boost. That difference does not offset the massive resource disparity. The Z1 Extreme GPU's higher base clock of 800 MHz versus 400 MHz also means it sustains more performance under sustained loads.

Where Each One Wins

The AMD Ryzen Z1 Extreme GPU wins every performance category recorded in the database. It leads in shading units, TMUs, ROPs, RT cores, pixel rate, texture rate, FP32 throughput, and FP16 throughput. It also has fixed memory bandwidth, which eliminates variability. Its 30 W TDP is double the Radeon 840M's 15 W, but that power budget purchases roughly 5.6 times the FP32 compute. The Z1 Extreme GPU is the correct choice for any workload that stresses graphics, compute, or ray tracing.

The AMD Radeon 840M wins on power efficiency metrics and integration simplicity. Its 15 W TDP is half that of the Z1 Extreme GPU, making it suitable for systems where thermal and power constraints are severe. Its system-shared memory means no dedicated VRAM allocation is needed, which simplifies memory management in portable devices. The Radeon 840M also carries a newer architecture, RDNA 3.5 versus RDNA 3.0, and a higher boost clock at 2900 MHz versus 2700 MHz. These advantages matter only in scenarios where the Z1 Extreme GPU cannot be used due to power, size, or integration constraints.

The release dates also frame the comparison. The Radeon 840M arrived later, on 2025-02-28, while the Z1 Extreme GPU launched on 2023-06-12. The Z1 Extreme GPU's 699 USD launch MSRP positions it as a premium part, while the Radeon 840M has no recorded launch price. The Z1 Extreme GPU's physical footprint, 280 mm by 111 mm by 21 mm, indicates a larger board design, whereas the Radeon 840M is an IGP with no recorded dimensions and no slot width. For builders selecting a GPU, the Z1 Extreme GPU delivers the performance, and the Radeon 840M delivers the low-power integrated alternative.