Two decades ago, the US high end microprocessor industry was a lively, diverse market where about five various instruction set architectures battled it out across the workstation and server fields. You had choices like DEC’s Alpha – the speed leader; MIPS – the Silicon Graphics heart; SPARC from Sun Microsystems, IBM POWER, HP PA, the nascent X86, and a few custom architectures for MPP massive parallel processing, for instance. The rest of the world pretty much had nothing – British Transputer and German Hyperstone platforms died out due to lack of funding, while ARM was still keeping to the low end embedded arena after the end of the
From HPC to HTPC: Can HTPC Become Your Main PC?
In the world of computing, the big iron – workstations, servers and HPC, were my main focus for the most of the past three decades. However, something on the opposite end of the spectrum from HPC, the kind of uber-mini desktop device, even smaller than HTPC – attracted my attention. This miniature box platform, using laptop CPU and chipset platforms & integration, but desktop peripherals and connectivity, is called many names: from NUC (Next Unit of Computing) by Intel, whose ex-desktop mainboard division is in charge is this product line; to Gigabyte’s BRIX line, likely named in the honor of their ex director and our
AMD Radeon Fury X: Potential Supercomputing Monster?
When AMD launched its Fiji-based graphics cards, all eyes were focused on its performance in consumer applications such as computer games. And while the first results forced Nvidia to launch “Titan Lite” in the form of GeForce GTX 980 Ti, DirectX 12 benchmarks are starting to show different, brighter outlook for AMD, starting with Ashes of the Singularity. The focus of this article however, is its potential and usage in applications where Fiji GPU will be branded as Fire Pro, and Fire Pro S (Server) – where AMD can take an ASIC and upsell it to commercial clients, with full-speed enabled for Double Precision floating point
ASUS Enterprise Road to Nowhere – Whither Taiwan IT Industry?
Taiwan IT industry, for a long time the leading among all Asian nations in terms of hardware manufacturing, has had its ups and downs over the decades. Does anyone still remember FIC (First International Computer), once the world’s leading mainboard maker? Or Elitegroup as the close second, while today’s leaders, Gigabyte, ASUS and MSI were far behind? Not many do… The gigantic Formosa Plastics consortium, which owned FIC, continued down the road with VIA Technologies and HTC, showing their love for three lettered acronyms. While these two still survive, the twisted sense of marketing and PR in these companies – one of the stones around their
Computex 2015 In Review: Advancing Downwards to Dumbed-Down Consumerism
Computex 2015: Intel Goes for The SSD jugular
Computex 2015: 65-core Smartphone Spotted in Intel Press Room
Intel’s 2015 Roadmap Conundrum: Tick-Tock is Not a Swiss Clock
In my 30-year career as an IT hardware expert, I’ve seen thousands of roadmaps, leaked, manage-leaked and official alike. Many were on target, yet still quite a few headed for the “failed” dustbin. Among all of them, Intel’s “tick-tock” plan was probably the most ambitious one in terms of attempted consistency and predictability. Knowing the multiple interlinked uncertainties of semiconductor process, CPU architecture, ecosystem changes and others, it was a wonder in itself that it lasted for several years, until the major slippages occurred in the Sandy Bridge generation. From then on, not only there were major delays introduced to the high end lines as the
Whither Galaxy S6? Samsung’s Newest Entry Shows Misdirected Smartphone Evolution
The Samsung Galaxy S6 shows the evolution of smartphones doesn’t mean an increase in productivity.
Intel Xeon D: Hitting the ARM Microserver Hopes?
Today, Intel (NASDAQ: INTC) is announcing its first Broadwell-based Xeon processor. It isn’t the mainstream E3 series derived from desktop chips, nor the high end E5 either — both of those will wait for later in the year. The new Xeon D goes for the upper end of the nascent microserver market, as well as for the dedicated storage and network appliances — exactly the focus of the current ARM server campaign. Microservers were chosen by ARM (LON: ARM) as, compared to the bigger server iron, they mostly rely on open source Web 2.0 stack, while the storage and network devices usually run specific applications.
Year-End Thoughts: Intel Goes High-End in 2015?
Connecting the CPUs and GPUs: Battles of Choices Are Coming
As GPUs get more powerful, a better solution to bridge the connectivity gap with the CPU is needed. Might AMD have the solution?
Intel Core i7-5960X on Gigabyte X99-Gaming G1 WIFI: The Ultimate Enthusiast PC Combo?
Intel’s launch of the Haswell-based Core i7 5960X and the associated X99 chipset with DDR4 memory has required a brand new series of motherboards as well. The four major vendors – Gigabyte, Asus, MSI and Asrock – grabbed the chance to introduce other new features into the just launched platform to entice the users to upgrade. Recently, Bright Side of News* reviewed Intel’s flagship CPU with Gigabyte’s X99-Gaming 5 motherboard, which by itself is a decent balance between top performance, features and compact size. How about the flagship mainboard in Gigabyte line, Gaming G1 WiFi? At 305 x 259 mm, the board itself is a
Intel Core i7-5960X on Gigabyte X99-Gaming G1 WIFI: The Ultimate Enthusiast PC Combo?
Intel’s launch of the Haswell-based Core i7 5960X and the associated X99 chipset with DDR4 memory has required a brand new series of motherboards as well. The four major vendors – Gigabyte, Asus, MSI and Asrock – grabbed the chance to introduce other new features into the just launched platform to entice the users to upgrade. VR World’s sister site, Bright Side of News* reviewed Intel’s flagship CPU with Gigabyte’s X99-Gaming 5 motherboard, which by itself is a decent balance between top performance, features and compact size. How about the flagship mainboard in Gigabyte line, Gaming G1 WiFi? At 305 x 259 mm, the board
HASWELL-E引發爭議:INTEL該如何應對ASUS和插槽2084?
Intel科技論壇(IDF)早在開始前就相當忙碌了,Gigabyte(台灣證交所股票代碼:2376)的超頻(overclocking)競賽就選在主題論壇登場的前一天舉辦。 Cookie、Charles Wirth和其他競賽者的OC成果表現良好,Gigabyte面板以Core i7-5960X採用液態氮(LN2)冷卻,得到5.8至6 GHz的成果。受試的RAM表現也相當出色,G Skill和Kingston超越3 GHz,在DIMM這項重要參考數據上則稍低於此。 然而,我們卻在overclocking的會場,與來自Hardware.info的朋友Koen一起察覺一件更有意思的事情。還記得Asus(台灣證交所股票代碼:2357)聲稱LGA 2011-3插槽上額外的針腳,也就是「插槽2084」,能透過使用沒有正式記錄的針孔,為Intel(那斯達克交易代號:INTC)的新CPU提升效能和OC可靠度嗎?以下是Asus的聲明內容: ASUS O.C.插槽 ASUS是經驗豐富的電腦公司,我們的團隊也致力進行廣泛研究,以為您推出精進且配備ASUS O.C.插槽的X99平台。為了持續保有身為消費者完美首選的地位,我們的主機板務必超越一般人的認知,並且提供完整的解決方案,這表示我們必須運用尖端技術。我們在引領業界的ASUS O.C.插槽中採用更多CPU針腳,讓您能100%應用新款CPU,透過ASUS O.C.插槽充分運用針腳能為您提供下列四個優勢。 增進電壓監控程度 Strap 166更具搭接能力 達到高記憶體頻率 取得最大的Vcore電壓值 業界消息人士指出,Asus曾考慮為插槽申請專利,以防堵製造商Foxconn(台灣證交所股票代碼:2354)將插槽賣給其他供應商。另一方面,另一個極具份量的業界消息人士表示,這些針腳和Asus的說法不盡相同,只能用來進行CPU偵錯,並且測試在這一代的插槽重新採用的針腳。因此它們對overclocking來說不僅毫無用途,如果連接到生產系統,恐怕還會引發當機的風險。 接著,別忘了還有另一點:Core i7-5960X不過是和Xeon E5 v3 8核Haswell-EP採用相同晶片的減縮版罷了,此外雙QPI通道、記憶體ECC和其他幾項功能都遭停用,這牽涉到大約150個訊號針腳。也許「企業集團」比「客戶集團」更了解這些在新處理器上沒有正式記錄的針腳,究竟內情為何? 備註:Foxconn針對一般插槽47191和OC插槽建模的模型為46391。 下一個步驟,是使用完全相同的「特殊」插槽,針對這些CPU檢視Gigabyte全新的LN2冷卻優化主機板: 並且和舊款插槽互相比較: 結果顯示Gigabyte能掌握相同的插槽,問題在於那些額外針腳連接到哪。如果以上宣稱的第一種可能性屬實,也就是這些針腳確實提供額外功率、監測範圍等,能讓OC更好也更可靠,那麼Asus絕對無法取得專利,因為這直接關係到Intel IP,插槽和驗證也都包含在內。 但如果是第二種可能性,也就是測試、偵測或暴露出沒有連結的針腳,那就成了嚴重的行銷垃圾,可能用來欺騙高端買家,他們可是Intel及其重要OEM,也就是Asus和Gigabyte視如珍寶的對象。你別忘了,這已經搭載產品上市,就是Asus頂尖的Rampage V Extreme。 Asus、Gigabyte甚或Foxconn都不大可能回應這個問題,看來只能靠Intel來解開謎題,尤其是他們頂尖的CPU隨著時間過去,的確提升效能,也擁有解除鎖定的能力。 重要的問題在於:如果因為將CPU插入配備沒有正式記錄針腳的插槽,而造成失敗時,公司能提供哪些保固。
搶先一睹 HASWELL-EP 工作站:XEON E5 V3 很讚,但是依然大有可為
隨著 Intel (那斯達克交易代號:INTC) 在今日發表第三代 Xeon E5 雙 CPU 平台,許多人也相當關注這項產品能如何提升資料中心的伺服器。然而,產品為高檔工作站所帶來的好處就算沒更多,也可說是不遑多讓。 首先,Haswell 核心意味著搭配積和熔加運算 (FMA),使得 AVX 的浮點運算功能大幅增強。舉例來說,像是就 Linpack 等標準而言,理論上錯誤辨識率會增加一倍。Haswell 之 AVX2 的重要性也不相上下,它將整數處理移至寬廣平行的 AVX 引擎,實際上將位址計算之外的任何事物卸載至類似 RISC 的三位址 AVX 指令格式,以及寬的暫存器集。就工作站應用程式而言,一旦為了運用這項產品而重新編譯,就有望獲得龐大的優勢,同時還能逐漸捨棄過時的 X86 程式碼基底。 其次,可就每一個 SKU 選擇多種核心 (從 8 個多達 18 個),能讓你根據應用程式的平行處理原則,在每核心速度 (例如每執行緒效能) 和核心數之間,挑選出恰當的平衡點。有些應用程式在許多核心的延展並不出色,因此偏好採用高的每核心速度,像是射線追蹤等其他應用程式則會儘量利用許多核心。 Xeon-E5 v3 系列的初始工作站 SKU 為E5 2687W v3,擁有 3.1 GHz 10 核零件,且確實在 2 核心 (及其相關快取) 關閉時,使用 12 核晶片。現在它的繼任者,也就是在 Ivy Bridge 平台作業的2687Wv2,即使停用晶片的某些核心,依然擁有完整的 L3 快取,我猜我們只有等到 Broadwell-EP (E5 v4) SKU 在明年推出時,才能見識到這項優勢。 接著我們來看 DDR4,沒錯,初始 DIMM 的速度並不算快,在延遲方面尤其如此,但是 DDR4 擁有較低電壓和其他可靠性的特色,加上其速度和延遲預期會在其後幾季中快速改善,所以應當能夠在雙插槽工作站提供使用者前所未見的生產力,不僅超越1.5 TB RAM,還不會像 DDR3 那樣,在高負載時犧牲頻寬。 改良 PCIe 頻寬、整合電壓調整器,並且將 QPI 的速度提升至 9.6 GT/s,也都是重要的其他優勢。 性能測試 現在我們來檢視初始參考工作站,這以 Intel 的 SKU 為基礎,且由 BOXX 封裝。機器在 SuperMicro X10DAi 工作站主機板採用液態冷卻技術,本身頗為精簡,並且配備三個 PCIe x16 v3 插槽。這並不會讓平台理論上的四個 GPU 完整頻寬功能達到最大值,但是對多數使用者來說,應該夠用了。反之,主機板的空間可供16 個 DDR4 DIMM 使用,也就是如果使用 64 GB 模組,就能在明年年初使用
Haswell-E Controversy: What Should Intel Do About Asus And Socket 2084?
IDF is busy, even before it starts – so it was this time in San Francisco with Gigabyte Overclocking competition just a day before the keynote. The OC results from Cookie, Charles Wirth and others were good, with 5.8 to 6 GHz achieved LN2 cooling results on the Core i7-5960X on Gigabyte boards seen here. The RAM on trial also performed well, hovering above 3 GHz for the G.Skill and Kingston part, with Crucial reference DIMMs just below that. However, something far more interesting was found on the overclocking floor (together with our friend Koen from Hardware.info). Remember Asus’ claims about additional pins on its LGA 2011-3 socket,
Haswell-E Controversy: What Should Intel Do About Asus And Socket 2084?
IDF is busy, even before it starts – so it was this time in San Francisco with Gigabyte (TPE: 2376) Overclocking competition just a day before the keynote. The OC results from Cookie, Charles Wirth and others were good, with 5.8 to 6 GHz achieved LN2 cooling results on the Core i7-5960X on Gigabyte boards seen here. The RAM on trial also performed well, hovering above 3 GHz for the G.Skill and Kingston part, with Crucial reference DIMMs just below that. However, something far more interesting was found on the overclocking floor (together with our friend Koen from Hardware.info). Remember Asus’ (TPE: 2357) claims about additional pins on its
Haswell-EP Workstation Preview: Xeon E5 v3 Rocks, But Still More To Go
Today, as Intel (NASDAQ: INTC) launches the third generation of its Xeon E5 dual-CPU platform, many eyes are on the improvements it brings to the servers in the datacenter. However, the benefits are just as high – if not higher – on the high-end workstation front. First of all, Haswell core means sped-up AVX floating point, by inclusion of fused multiply-add (FMA) ops for theoretical FP rate doubling in benchmarks like Linpack, for instance. Haswell’s AVX2 also, just as importantly, moves integer processing to the wide parallel AVX engines, essentially offloading anything aside the address calculations to the RISC-like, three-address AVX instruction format and wide
Haswell-EP Workstation Preview: Xeon E5 v3 Rocks, But Still More To Go
Today, as Intel (NASDAQ: INTC) launches the third generation of its Xeon E5 dual-CPU platform, many eyes are on the improvements it brings to the servers in the datacenter. However, the benefits are just as high – if not higher – on the high-end workstation front. First of all, Haswell core means sped-up AVX floating point, by inclusion of fused multiply-add (FMA) ops for theoretical FP rate doubling in benchmarks like Linpack, for instance. Haswell’s AVX2 also, just as importantly, moves integer processing to the wide parallel AVX engines, essentially offloading anything aside the address calculations to the RISC-like, three-address AVX instruction format and wide