Several tablets based on AllWinner A31 quad core processor have been announced this week, such as Onda V972, but we did not really have full details on the processor. We now know more since AllWinner added product pages for two new (sun6i architecture. [Edit: A20 is actually sun7i…]) processors: AllWinner A31 and AllWinner A20. AllWinner A31 Specifications AllWinner A31 is a quad core Cortex A7 processor with PowerVR SGX544MP2 GPU (8 shader engines). CPU – ARM Cortex-A7 Quad-Core with 256KB L1-Cache/1MB L2-Cache GPU – POWER VR SGX 544 with Eight logic cores. Open GL ES2.0, Open CL1.x and DX 9_3 compliant. Memory – Dual-Channel LPDDR2/DDR3/DDR3L Controller, Dual-Channel NAND FLASH Controller and 64-bit ECC Video UHD H.264 4K ×2K @30fps video decoding Full HD video decoding BD Directory, BD ISO and BD m2ts video decoding H.264 High Profile 1080P@60fps encoding 3840×1080@30fps 3D decoding Complies with RTSP, HTTP, HLS, RTMP, MMS streaming […]
2D/3D Graphics Linux Demo (X11, EGL, GLES2, Qt4) on AllWinner A10 Tablet
Xlab (Maxim Kouprianov) has tested 2D & 3D capabilities of AllWinner A10 SoC (with Mali-400 GPU) on a Ployer MOMO11 Bird Edition tablet running OpenEmbedded with kernel 3.0.52+ testing X11, EGL, OpenGL ES2 and Qt4 on the platform, and the results are pretty smooth as you can see in the video below, although there appears to be some flickering in LunaSysMgr demo. The tools used in the demos are xfwm4 (Xfce Windows Manager), es2gears_x11, cube (Qt), LunaSysMgr (Qt/WebOS) and glmark2-es2. Qt4 acceleration is done via XlibGL platform which in turns uses X11-EGL. He used the Mali drivers version r3p0 (mali400-gles20-gles11-linux-x11-ump) and xf86-video-mali on sunxi-linux github repository mainly maintained by rz2k. You can get more details on how to build Mali-400 support for AllWinner A10 on http://linux-sunxi.org/Mali400, and GPU benchmark results for A10 show the drivers seem to work as expected. Jean-Luc Aufranc (CNXSoft)Jean-Luc started CNX Software in 2010 as a part-time […]
ARM Announces 3 New Midgard GPUs – Mali-T624, Mali-T628 and Mali-T678
ARM announced the second generation of the Mali-T600 Series GPUs targeting tablets, smartphones and smart TVs. Those new GPUs provide up to 50% performance increase over the first generation Midgard GPUs (T-604 & T-658) and include support for Adaptive Scalable Texture Compression (ASTC), a texture compression technique. The company explains that ASTC significantly optimizes GPU performance and increases battery life in devices. Those 3 new GPUs based on Mali Midgard architecture are named as follows: Mali-T624 – 1 to 4 cores – Market: Smartphones and smart-Tvs Mali-T628 – 5 to 8 cores – Market: Smartphones and smart-Tvs Mali-T678 – Up to 8 cores, 4x the GPU compute performance of Mali-T628 – Market: Tablets As with previous Midgard GPUs, the new GPUs support GPU compute with improves performance and energy-efficiency for math intensive activities, such as: Computational photography – computational methods of enhancing or extending digital photography Multi perspective views – […]
ARM Unveils Some Details About Mali-450 GPU
EETimes reports that ARM has shown details about its new GPU, the Mali-T450, which offers up to twice the performance of the Mali-400 and can be scaled up to 8 cores, whereas Mali-400 can only be scaled up to 4 cores. The Mali-450 (codename Tyr) targets entry-level and mid-range mobile devices, and is said to be software compatible with Mali-400. ARM new GPU has also been “tweaked” to provide better performance at the cost of occupying a slightly larger area. The company recommends the use Mali-400 for 1 to 4 cores configuration and Mali-450 for 5 to 8 cores configuration for higher end products. Contrary to Mali-T604 and Mali-T685 GPU, Mali-450 does not support general purpose computing on GPU (GPGPU). ARM is also working on a new GPU codenamed Skrymir based on Midgard architecture (Like Mali-T604 & T658) that should be available in 2014. Source: EETimes Jean-Luc Aufranc (CNXSoft)Jean-Luc started […]
Open Source Mali 200/400 Drivers (LIMA) Demo on Android Tablet
Luc Verhaegen, the lead developer of LIMA open source project, provided an update at LinuxTag 2012 last week-end. This open-source MALI GPU driver isn’t ready for consumers yet, but the LIMA team has made some progress and showcased an OpenGL ES demos running on a Chinese tablet running Android. Luc said the tablet used for the demo is the same hardware as the Spark KDE/Vivaldi tablet, so the video demo below must be running on an AMLogic 8726-M processor with a Mali 400 GPU. The drivers already (partially) work on both Mali-200 and Mali-400 GPUs. The fragment shader instructions set is fully known and they have disassembler and assembler fully implement, but they still need to work on the compiler. The vertex shader instruction set is 80% known, they have a simple shader disassembler and are working on the assembler. You can also watch the 40 minute presentation at LinuxTag […]
Linux 3.4 Release
Linus Torvalds has just announced the release of Linux Kernel 3.4 on the 20th of May: I just pushed out the 3.4 release. Nothing really exciting happened since -rc7, although the workaround for a linker bug on x86 is larger than I’d have liked at this stage, and sticks out like a sore thumb in the diffstat. That said, it’s not like even that patch was really all that scary. In fact, I think the 3.4 release cycle as a whole has been fairly calm. Sure, I always wish for the -rc’s to calm down more quickly than they ever seem to do, but I think on the whole we didn’t have any big disruptive events, which is just how I like it. Let’s hope the 3.5 merge window is a calm one too. Linus Linux 3.3 merged Android drivers to mainline, added further improvements to btrfs and ext-4 file […]
Ziilabs MandelMark Benchmark Shows ZMS-40 GPU Compute Performance is 18 Times Faster than Nvidia Tegra 3
Ziilabs released comparative GPU compute benchmark results for its ZMS-40 stem cells processor and made available its MandelMark floating point benchmark for Android 4.0 as an apk file. Since Ziilabs is using its own benchmark tool, which they released as a binary but did not open source, the results should be taken with a grain of salt. GPU Compute (aka GPGPU – General Purpose computing on GPU) is a technique to use the GPU to perform complex calculations usually performed by the CPU. MandelMark benchmark visualizes the solutions to the Mandelbrot to measure the floating point performance of mobile processors. Ziilabs compared their ZMS-40 Quad Core Cortex A9 processor with 96 stemcell cores to the following competitors: IPAD 3 – Apple A5X processor with a quad-core PowerVR SGX543MP4 GPU Galaxy Tab 7+ – Samsung Exynos 4210 processor with a quad-core ARM Mali-400 GPU Galaxy Nexus – TI OMAP 4460 processor […]
Binary Blobs Attack – ELC 2012
Zach Pfeffer, Android Platform Lead at Linaro, talks about (GPU) Binary Blobs and the problems they cause at Embedded Linux Conference 2012. Abstract: Binary Blobs Attack!!! Most SoC vendors distribute binary blobs with Linux kernel shims. These binary blobs enable graphics engines, DSPs and other cores on ARM and other architecture SoCs. These binary blobs tend to be tied to specific kernel versions which limits unreadability and hackability and complicates device manufactures, which slows down innovation and the introduction of new and unique computing devices. Here’s what I noted from this presentation: Most of the issues at Linaro come from (GPU) Binary blobs, they delay projects and cause projects to cost more as FAE and more engineers must be involved in solving problems. Blobs are here to stay mostly due to legal reasons (patents). Binary Blob are usually OS independent, e.g. the same binary is used in Windows and Linux, […]