ATI Radeon X800 XT Mac Edition

The ATI Radeon X800 XT Mac Edition is an AGP Pro 8x graphics card from AMD, built on the R423 chip and the R400 architecture. Manufactured by TSMC on a 130 nm process, the die holds 160 million transistors across 289 mm², yielding a transistor density of 553.6K per mm². The card pairs 16 texture mapping units with 16 render output units, achieving a pixel rate of 7.600 GPixel/s and a texture rate of 7.600 GTexel/s. Its memory subsystem consists of 256 MB of GDDR3 on a 256-bit bus, running at 500 MHz (1000 Mbps effective) for 32.00 GB/s of bandwidth. The card is rated at 54 W TDP, requires a 250 W suggested power supply, uses no external power connectors, and fits in a single slot. Released on November 30, 2004, it is now end-of-life. It sits at the 50th percentile among all GPUs in the database, with no recorded benchmark scores and no listed nearest rivals.

Benchmark Performance

The benchmark data for the ATI Radeon X800 XT Mac Edition is minimal. The benchmark array is empty, and the average benchmark score is listed as 0. The only comparative metric available is the 50th percentile ranking, which places the card at the exact median of all GPUs tracked in the database. Half of the GPU population scores above it, and half scores below it. This is a clear positional statement: the card is a middle-of-the-pack performer, not a leader and not a laggard.

The fill-rate specifications give context to that ranking. The pixel rate of 7.600 GPixel/s and the texture rate of 7.600 GTexel/s are identical. With 16 TMUs and 16 ROPs, both units operate at the same effective clock, producing balanced pixel and texture throughput. The card does not favor one type of workload over the other — pixel shading and texture sampling are served at the same rate. The 32.00 GB/s memory bandwidth is the data path that feeds these fill rates, and the 256-bit bus width provides the channel for that bandwidth.

Because the nearestRivals list is empty, no rival names, scores, or deltaPct values are available for comparison. No exact percentage deltas can be cited. The 50th percentile is the sole cross-GPU figure, and it indicates that the card lands at the midpoint of the database's historical GPU population. The average benchmark score of 0 reflects the absence of recorded benchmark entries rather than a measured performance result. The transistor density of 553.6K per mm², derived from 160 million transistors on a 289 mm² die, is a structural characteristic that informs the card's throughput ceiling, but it is not a performance score.

How It Compares

The database lists no nearest rivals for this card, so direct competitor comparisons are not possible. The card's position must be understood through its product lineage. Its predecessor is the Radeon R300, and its successor is the Radeon R500 AGP. The X800 XT Mac Edition belongs to the Radeon R400 AGP generation, specifically the X800 family, built on the R423 chip. This places it one generation after the R300 and one generation before the R500 AGP.

Within its own generation, the specifications define its tier. The 16 TMUs and 16 ROPs, combined with 256 MB of GDDR3 memory, indicate a card positioned in the middle of the performance spectrum. The 50th percentile ranking across all GPUs reinforces this reading: the card is neither a flagship nor an entry-level part. The R400 generation is an AGP-era product line, and this Mac Edition variant uses the AGP Pro 8x bus interface.

The Mac Edition designation is significant for platform compatibility. The card provides 2x DVI display outputs, which support digital display connectivity on Mac systems of that period. The AGP Pro 8x interface is the connection standard for that platform. Because no rival data is present, the comparison is limited to the card's position in its own family: between the R300 and R500 AGP, within the R400 generation, at the 50th percentile of all GPUs tracked in the database. The absence of rival entries means no percentage-based positioning statements can be made; the percentile ranking is the only quantitative anchor.

Ray Tracing and Feature Set

The card has no ray tracing cores and no tensor cores — both fields are recorded as null. This is consistent with a GPU from the R400 generation, which predates dedicated ray tracing hardware and AI acceleration. The feature set is defined by its API support: DirectX 9.0b (9_2) and OpenGL 2.1. Vulkan is not supported, as the field is null.

The DirectX 9.0b (9_2) support limits the card to the feature level of DirectX 9 with the 9_2 revision. This covers the shader model capabilities of that era but does not include later DirectX revisions. OpenGL 2.1 support provides an alternative API path for applications using the OpenGL interface. The absence of Vulkan support means modern Vulkan-based applications cannot run on this hardware.

The display output configuration is 2x DVI, which is the only output option listed. The card does not list any RT or tensor functionality, so workloads requiring hardware-accelerated ray tracing or tensor-based AI inference are unsupported. The feature set is purely rasterization-focused, aligned with the DirectX 9.0b (9_2) and OpenGL 2.1 API levels. Users who need ray tracing or tensor core features will not find them in this card's data.

Who Should Consider It

The data positions this card at the 50th percentile of all GPUs, with no recorded benchmark scores. Users should consider it for workloads that match its measured characteristics: a 7.600 GPixel/s pixel rate, a 7.600 GTexel/s texture rate, and 32.00 GB/s of memory bandwidth. These figures describe a card that handles rasterization workloads within a 256 MB GDDR3 frame buffer.

The 256 MB memory capacity is the primary constraint. Settings that require more than 256 MB of frame buffer — such as very high-resolution textures or large render targets — will exceed the available memory. The 32.00 GB/s bandwidth is sufficient for the card's fill rates, but it is not a high-bandwidth design relative to the full GPU population in the database. The 50th percentile ranking suggests the card is appropriate for users whose performance expectations are at the median level.

For users with AGP Pro 8x systems, this card provides dual DVI output, which is useful for digital display connectivity. The single-slot design and lack of external power connectors make installation straightforward in systems with a 250 W power supply. Users seeking higher-than-median performance, or those requiring ray tracing or tensor core features, should look elsewhere, as the data shows no such capabilities. The card is end-of-life, meaning production has ceased.

Power and Cooling

The card has a TDP of 54 W, which is modest. The suggested power supply is 250 W, and the card requires no external power connectors — the powerConnectors field is "None". This means the card draws its power entirely from the AGP Pro 8x slot. The single-slot design keeps the physical footprint compact.

The 54 W TDP is the only thermal figure in the data. The lack of power connectors simplifies installation: no auxiliary power cables are needed. The 250 W suggested PSU is the minimum recommended system power supply. Cooling is handled within a single-slot form factor, though the data does not specify the cooler design. Users should ensure their system's power supply meets or exceeds the 250 W suggestion and that the AGP Pro 8x slot can deliver the required power.

Memory Subsystem

The memory subsystem consists of 256 MB of GDDR3 on a 256-bit bus. The memory clock is 500 MHz, with an effective data rate of 1000 Mbps. This produces a bandwidth of 32.00 GB/s. The 256-bit bus width is a key factor: a wider bus allows more data to be transferred per clock cycle, and 32.00 GB/s is the resulting aggregate bandwidth.

For high resolutions, the 256 MB capacity is the limiting factor. Larger frame buffers are required for high-resolution textures and anti-aliasing buffers. The 32.00 GB/s bandwidth must serve both the pixel rate of 7.600 GPixel/s and the texture rate of 7.600 GTexel/s. At the card's 50th percentile performance level, the memory subsystem is balanced with the fill rates — the bandwidth is neither overprovisioned nor underprovisioned relative to the compute throughput.

The GDDR3 memory type and 256-bit bus were appropriate for the R400 generation. The effective 1000 Mbps data rate, combined with the 256-bit bus, yields the 32.00 GB/s figure. Users running high-resolution workloads should be aware that the 256 MB capacity will be exhausted more quickly at higher resolutions, and the 32.00 GB/s bandwidth sets the ceiling for texture streaming and frame buffer updates.