- Joined
- Oct 9, 2007
- Messages
- 47,895 (7.38/day)
- Location
- Dublin, Ireland
System Name | RBMK-1000 |
---|---|
Processor | AMD Ryzen 7 5700G |
Motherboard | Gigabyte B550 AORUS Elite V2 |
Cooling | DeepCool Gammax L240 V2 |
Memory | 2x 16GB DDR4-3200 |
Video Card(s) | Galax RTX 4070 Ti EX |
Storage | Samsung 990 1TB |
Display(s) | BenQ 1440p 60 Hz 27-inch |
Case | Corsair Carbide 100R |
Audio Device(s) | ASUS SupremeFX S1220A |
Power Supply | Cooler Master MWE Gold 650W |
Mouse | ASUS ROG Strix Impact |
Keyboard | Gamdias Hermes E2 |
Software | Windows 11 Pro |
Intel's discrete graphics card for PC enthusiasts is real. Intel won't just address the pro-graphics and accelerated-compute markets, but also consumer graphics, challenging the duopoly of NVIDIA GeForce and AMD Radeon. Scheduled for 2020, the new Intel Xᵉ is a family of discrete GPUs targeting client-segment (consumer graphics) as well as enterprise (pro-graphics and compute).
As for performance, we speculate that the first Xᵉ products could span a vast lineup of ASICs starting single-digit TFLOP/s range for the client-segment GPU, looking purely at a nondescript performance-time graph presented by Intel. This graph depicts performance double linearly over time up to Gen9, and increase to Intel's own state 1 TFLOP/s for the Gen11 iGPU core in 2019 (a full four years following Gen9). There are a spectrum of GPUs going from the entry-level client-segment all the way up to mid-range and enthusiast segment (Intel finally used the E-word).
For the enterprise-segment GPU, however, we see a sharp rise in performance over Gen11, which could well be in the double-thru-triple digit TFLOP/s range. Intel is targeting the compute data-center market dominated by NVIDIA Tesla and AMD Radeon Instinct. This graph perfectly explains why Intel wants a discrete GPU now: it wants to go after the lucrative compute data-center segment, but wants to give the dividends of its R&D to gamers, too.
View at TechPowerUp Main Site
As for performance, we speculate that the first Xᵉ products could span a vast lineup of ASICs starting single-digit TFLOP/s range for the client-segment GPU, looking purely at a nondescript performance-time graph presented by Intel. This graph depicts performance double linearly over time up to Gen9, and increase to Intel's own state 1 TFLOP/s for the Gen11 iGPU core in 2019 (a full four years following Gen9). There are a spectrum of GPUs going from the entry-level client-segment all the way up to mid-range and enthusiast segment (Intel finally used the E-word).


For the enterprise-segment GPU, however, we see a sharp rise in performance over Gen11, which could well be in the double-thru-triple digit TFLOP/s range. Intel is targeting the compute data-center market dominated by NVIDIA Tesla and AMD Radeon Instinct. This graph perfectly explains why Intel wants a discrete GPU now: it wants to go after the lucrative compute data-center segment, but wants to give the dividends of its R&D to gamers, too.
View at TechPowerUp Main Site