The developers of felix86, an emulator built for #RISCV based computers to allow the operation of x86 programs, made a blog post today showing off x86 Windows gameplay. The exceptionally good framerate (by RISC-V standards) for 3D games in particular demonstrates progress for truly #OpenSource source hardware.
https://www.newinlinux.com/here-are-3d-windows-games-running-smoothly-on-open-source-risc-v/
I feel like overlapping FP and integer register file and ports may be better than overlapping FP with SIMD.
Because you kind of want scalar FP to be higher issue and lower latency that you need for SIMD float operations.
If you have 128-bit SIMD the goals are mostly aligned, but for >=256-bit sharing FP with SIMD becomes less attractive in my mind.
This also isn't all that relevant if your integer execution isn't something like 6 wide or wider.
It also gives you have more control over FP32 and FP64. Maybe you put FP32 on all ALUs, but FP64 only on the ones that also support IMUL (if you can share that logic).
felix86 x86 and x86-64 emulator for RISC-V — Finally, some gaming!
felix86 x86 and x86-64 emulator for RISC-V — Finally, some gaming!
This month we received the new SpacemiT K3 board. Since its inception, felix86 wasn’t able to run on any of the out-of-order execution hardware, such as the SiFive P550 or the SOPHON SG2042. The former has no vector support, the latter has XTheadVector support. While initially there was consideration for supporting hardware without RVV 1.0 or hardware with XTheadVector, ultimately the decision was that we should instead focus on the future of RISC-V consumer hardware which will have RVV 1.0 due to it being mandatory in the RVA23 profile. If you watched the felix86 talk at the RISC-V NA summit you might’ve seen a video of gameplay on K1 hardware. You would notice the lack of modern 3D games running on the emulator, because a lot of them would run at less than 5 frames per second. Now that we have much faster hardware, there’s more to show! TLDW: Huge performance improvements over the K1, and RISC-V performance will only go up from here.
A weekend project: CH32V003 library for AMG88XX 8x8 IR thermal camera:
https://github.com/artyom-poptsov/ch32v003-amg88xx
Ask HN: Have you ever created a custom RISC-V ISA extension?
We may not have `vlast.m` but at least we can still compute it.
The RISC-V Vector Extension (RVV) includes several instructions to operate on masks and compute interesting things. One of them is vfirst.m that compute the lowest-numbered element of the mask that is set. However, there is no vlast.m instruction that computes the highest-numbered element of the mask that is set.
Alibaba gets Android 16 running on RISC-V
Petros CH32H417M Alef – A Raspberry Pi Pico-sized RISC-V USB 3.0 camera board
XPU Labs' Petros CH32H417M Alef is a Raspberry Pi Pico-sized board based on the WCH CH32H417W RISC-V USB 3.0 microcontroller and taking a 2MP OV2640 camera module through the MCU's digital image interface (DVP). The board comes with 896KB SRAM and 960KB Flash from the WCH microcontroller, two 20-pin GPIO headers following the Raspberry Pi Pico's pinout, a 6-pin SWD and UART6 header for debugging, and a Reset button. Petros CH32H417M Alef specifications: MCU – WCH CH32H417MEQ6 MCU QingKe RISC-V5F up to 400 MHz QinKe RISC-V3F up to 144 MHz GPU – Graphics Processing Hardware Accelerator GPHA Memory – 896KB SRAM Storage – 960KB Flash Camera I/F - 40-pin B2B connector with DVP @ 144MHz, SPI, I2C and ADC interfaces for 2MP Phos Ayin OV2640 camera module USB - 1x USB 3.0 Type-A port (5Gbps, tested up to 430 MB/s) for data, power, and firmware flashing Debugging – 6-pin SWD and
u-blox ALMA-B2 Bluetooth 6.0 and 802.15.4 module features Nordic nRF54LM20 Edge AI wireless MCU
u-blox has recently announced the ALMA-B2 standalone BLE 6.0 and 802.15.4 module family built around the Nordic Semi nRF54LM20 Cortex-M33 wireless microcontroller with a dedicated NPU for low-latency Edge AI applications. There are four specific product variants in the u-blox ALMA-B2 series: ALMA-B201, ALMA-B206, ALMA-B211, and ALMA-B216, all of which support Bluetooth 6.0 and Bluetooth Channel Sounding for distance measurement. They also support IEEE 802.15.4, including Thread, Zigbee, and Matter, as well as Nordic’s proprietary 2.4 GHz protocol and NFC. The company also mentions that the nRF54LM20B-based ALMA-B211 and ALMA-B216 variants include an Axon NPU that performs machine learning tasks up to 15 times faster and with greater energy efficiency than running the same tasks on the main processor alone. u-blox ALMA-B2 Series Specifications: Wireless SoC - Nordic Semiconductor nRF54LM20A (for ALMA-B201 and B206) or nRF54LM20B (for ALMA-B211 and B216) CPU Arm Cortex-M33 application processor clocked at up to 128 MHz RISC-V
New In Linux
camelcdr
cm0002
Jure Repinc
avp
Hacker News
Roger Ferrer Ibáñez