Accelerator
NVIDIA GeForce GTX 580: 1536 MiB of GDDR5 and 192.4 GB/s peak bandwidth.
An EVGA GeForce GTX 580, a partner card on NVIDIA's reference design. The dust and scratches are the condition of this card, not a modification of it.
NVIDIA's surviving launch table supplies clocks, memory and bandwidth. It does not state an explicitly labelled FP32 peak or a numeric board-power rating.
| Component | Role | Count | Clock | Capacity |
|---|---|---|---|---|
| NVIDIA Fermi (NVIDIA GeForce GTX 580) Reference-card graphics clock. | GPU | 1 | 772 MHz Nominal clock | — |
| NVIDIA GeForce GTX 580 frame buffer | Video memory | 1 | — | 1536 MiB |
provisional A figure marked provisional is recorded but not accepted: its evidence is unsettled. It may rely on one source, an unconfirmed announcement, or a digit read from a damaged scan. The reason appears under the figure. The catalog shows the figure but never uses it in a multiplier. How records are judged.
| Metric | Value | Evidence | Basis | Method | Source |
|---|---|---|---|---|---|
| Memory bandwidth whole-system provisional | 192.4 GB/s | Confirmed | Derived | Theoretical peak Computed here from figures the vendor stated Adds the one fitted frame-buffer bandwidth. No host memory is included. |
provisional A figure marked provisional is recorded but not accepted: its evidence is unsettled. It may rely on one source, an unconfirmed announcement, or a digit read from a damaged scan. The reason appears under the figure. The catalog shows the figure but never uses it in a multiplier. How records are judged.
| Metric | Value | Evidence | Basis | Method | Source |
|---|---|---|---|---|---|
| Clock frequency gpu provisional | 772 MHz | Confirmed | Vendor-rated | Nominal clock Stated by the vendor The reference-card graphics clock. | |
| Thermal design power gpu provisional | 243 W | Rumored | Vendor-rated | Rated power From community documentation Nvidia's own material for this chip states no thermal figure. Wikipedia gives 243 W as the card's rated thermal design power, and the catalog carries it as rumored. |
| Metric | Value | Evidence | Basis | Method | Source |
|---|---|---|---|---|---|
| Peak FP32 rate gpu provisional | unknown The launch table gives CUDA-core and processor-clock figures, but no explicitly labelled single-precision throughput. | Not stated | Theoretical | Theoretical peak Stated by the vendor The recovered NVIDIA launch material does not state an explicitly labelled FP32 peak. |
provisional A figure marked provisional is recorded but not accepted: its evidence is unsettled. It may rely on one source, an unconfirmed announcement, or a digit read from a damaged scan. The reason appears under the figure. The catalog shows the figure but never uses it in a multiplier. How records are judged.
| Metric | Value | Evidence | Basis | Method | Source |
|---|---|---|---|---|---|
| Memory bandwidth memory provisional | 192.4 GB/s | Confirmed | Theoretical | Theoretical peak Stated by the vendor Vendor-stated maximum transfer rate of this memory interface, not a benchmarked application result. | |
| Memory capacity whole-system provisional | 1536 MiB | Confirmed | Vendor-rated | Design capacity Stated by the vendor The frame buffer fitted to the reference accelerator; host memory is excluded. |
192 400 000 000 B/s
a + b + … sum v1 Adds 1 memory-bandwidth figure obtained by theoretical-peak. Nothing in the catalog is left out of it. A total is only as trustworthy as the decision about what belongs in it, so both the terms and the exclusions are named records.
This accelerator’s whole-system memory is its fitted frame buffer; host memory is excluded. Partner cards may differ from this reference configuration.