GPU Name | Calistoga | TU102 |
---|---|---|
GPU Variante | Calistoga-GME | TU102-875-A1 |
Architektur | Generation 3.5 | Turing |
Hersteller | Intel | TSMC |
Prozessgröße | 90 nm | 12 nm |
Transistoren | unknown | 18,600 million |
Chipgröße | unknown | 754 mm² |
Veröffentlichungsdatum | 2006 | — |
---|---|---|
Generation | GMA Graphics-M (GMA 950 IGP) | — |
Produktion | End-of-life | — |
Businterface | FSB | — |
Reviews | 1 in our database | — |
GPU-Taktung | 250 MHz | — |
---|---|---|
Speicher-Taktung | System Shared | 1750 MHz 14 Gbps effective |
Basis-Taktfrequenz | — | 1440 MHz |
Boost-Takt | — | 1770 MHz |
Speichergröße | System Shared | 24 GB |
---|---|---|
Speichertyp | System Shared | GDDR6 |
Speicherbus | System Shared | 384 bit |
Bandbreite | System Dependent | 672.0 GB/s |
Pixelshader | 4 | — |
---|---|---|
Vertex-Shader | 1 | — |
TMUs | 4 | 288 |
ROPs | 1 | 96 |
Shading-Einheiten | — | 4608 |
Anzahl SM | — | 72 |
Tensor Cores | — | 576 |
RT-Kerne | — | 72 |
Cache L1 | — | 64 KB (per SM) |
Cache L2 | — | 6 MB |
Pixelrate | 250.0 MPixel/s | 169.9 GPixel/s |
---|---|---|
Vertex-Rate | 62.50 MVertices/s | — |
Texturrate | 1.000 GTexel/s | 509.8 GTexel/s |
FP16 (half) Leistung | — | 32.62 TFLOPS (2:1) |
FP32 (float) Leistung | — | 16.31 TFLOPS |
FP64 (double) Leistung | — | 509.8 GFLOPS (1:32) |
Steckplatzbreite | IGP | Dual-slot |
---|---|---|
TDP | 7 W | 260 W |
Ausgabe | No outputs | 4x DisplayPort1x USB Type-C |
Länge | — | 267 mm 10.5 inches |
Breite | — | 111 mm 4.4 inches |
Vorgeschlagenes Netzteil | — | 600 W |
Stromverbindung | — | 1x 6-pin + 1x 8-pin |
Board-Nummer | — | PG150 SKU 510 |
DirectX | 9.0c | 12 Ultimate (12_2) |
---|---|---|
OpenGL | 2.0 | 4.6 |
OpenCL | — | 3.0 |
Vulkan | — | 1.2 |
Shader-Modell | 3.0 | 6.6 |
CUDA | — | 7.5 |
Veröffentlichungsdatum | — | Aug 13th, 2018 |
---|---|---|
Generation | — | Quadro |
Produktion | — | Active |
Originalpreis | — | 6,299 USD |
Businterface | — | PCIe 3.0 x16 |