Bookmark and Share


Intel Corp. earlier this month published the first details about its next-generation micro-architecture code-named Haswell. The forthcoming chips will feature new instructions that accelerate a wide number of applications and workloads.

Intel’s Ivy Bridge and Haswell microprocessors are projected to offer increased performance amid moderate power supply. Those chips will enable new class of mobile computers that Intel calls ultrabooks. With Haswell, Intel promises to change the mainstream laptop thermal design point by reducing the microprocessor power to half of today’s design point, which means something like 15W - 18.5W. The chips are also expected to offer much improved integrated graphics cores.

These new set of instructions are build upon the instructions coming in Intel micro-architecture code name Ivy Bridge, including the digital random number generator, half-float (float16) accelerators, and extend the Intel Advanced Vector extensions (AVX) that launched in 2011.

The instructions fit into several categories:

  • AVX2 - Integer data types expanded to 256-bit SIMD. AVX2’s integer support is particularly useful for processing visual data commonly encountered in consumer imaging and video processing workloads. With Haswell, Intel will have AVX for floating point, and AVX2 for integer data types.
  • Bit manipulation instructions are useful for compressed database, hashing , large number arithmetic, and a variety of general purpose codes.
  • Gather useful for vectorizing codes with nonadjacent data elements. Haswell gathers are masked for safety, (like the conditional loads and stores introduced in Intel AVX), which favors their use in codes with clipping or other conditionals.
  • Any-to-Any permutes – useful shuffling operations. Haswell adds support for DWORD and QWORD granularity permutes across an entire 256-bit register.
  • Vector-Vector Shifts: We added shifts with the vector shift controls. These are critical in vectorizing loops with variable shifts.
  • Floating Point Multiply Accumulate – Intel’s floating-point multiply accumulate significantly increases peak flops and provides improved precision to further improve transcendental mathematics. They are broadly usable in high performance computing, professional quality imaging, and face detection. They operate on scalar, 128-bit packed single and double precision data types, and 256-bit packed single and double-precision data types.
  • The vector instructions build upon the expanded (256-bit) register state added in Intel AVX, and as such as supported by any operating system that supports Intel AVX.

Tags: Intel, Haswell, 22nm, Larrabee, AVX


Comments currently: 14
Discussion started: 06/26/11 07:52:40 PM
Latest comment: 07/13/16 11:16:14 AM
Expand all threads | Collapse all threads


Intel isn't slowing down that's for sure. AMD has a lot of ground to makeup.
0 0 [Posted by: SteelCity1981  | Date: 06/26/11 07:52:40 PM]
- collapse thread

Unfortunately it seems that AMD will never be able to catch up. If the buildozer architecture goes well, it has a good chance in the Enterprise. Multicore is king there. But in the desktop and mobile space, Intel seems unstopable.
1 2 [Posted by: redhavoc  | Date: 06/27/11 01:20:59 AM]
In the heterogeneous processing, Intel isn't even able to start, not even close to starting.
0 0 [Posted by: jaja  | Date: 06/27/11 01:23:14 AM]
Not to rant, but AMD has caught up to Intel processors. This depends on where your money goes for a new computer. AMD does have the low-end processors better than Intel. Also AMD does have some processors that can compete against high performance while costing a lot less if you are into over clocking.
0 1 [Posted by: tecknurd  | Date: 06/27/11 09:04:46 PM]
Sorry, but you are wrong. Intel's i3 Sandy Bridge dual core outperforms AMD's quad core and at the same price. In terms of competing in the high end, AMD is a joke.

Right now, with Intel's new tri-gate transistors, AMD is about 4 years behind.
0 0 [Posted by: AnonymousGuy  | Date: 06/28/11 04:24:18 PM]
Only in floating point...Only in floating point....

AMD beats Intel in the Integer race
0 0 [Posted by: seronx  | Date: 06/28/11 07:06:51 PM]

You got that the wrong way around: Intel is usually the Integer, cache and IPC king while AMD relies on Core Count and FP and GPU performance. No wonder why Llano shines in the consumer market: AMD spent roughly speaking 50% of their transistor budget on the IGPU, and GPU computing is starting to gain some serious traction. OTOH, the IGPU of Sandy Bridge i2600 is already capable of fluent HD/3D content playback, so unless one is serious with openGL/DX stuff, it doesn't matter that much.
0 0 [Posted by: sanity  | Date: 06/29/11 01:15:00 PM]

They are both moving toward different ways. AMD doesn't have to follow Intel.
3 0 [Posted by: jaja  | Date: 06/27/11 01:21:10 AM]

Are these instructions sets going to be proprietary or will other chip makers be able to use them?
0 0 [Posted by: GavinT  | Date: 06/27/11 02:54:01 AM]

AMD's 3DNow! was awesome at that time.

"As an enhancement to the MMX instruction set, the 3DNow! instruction-set augmented the MMX SIMD registers to support common arithmetic operations (add/subtract/multiply) on single-precision (32-bit) floating-point data. Software written to use AMD's 3DNow! instead of the slower x87 FPU could execute up to 4x faster, depending on the instruction-mix."
According to Wikipedia.

I very like to see more new such innovations from past AMD again.
1 0 [Posted by: Pouria  | Date: 06/27/11 05:00:41 AM]
- collapse thread

It does not matter if 3DNow! was awesome. The computer industry did not use it. Unfortunately, Intel owns the computer industry, so MMX and SSE ruled during the time that 3DNow!.

AVX is Intel's proprietary SIMD instruction set that AMD have to get rights to implement into their processors. The FTC did nothing to Intel to stop Intel's monopoly tactics.

AMD is making something awesome at this time with their Bulldozer core and APU. Intel is not making the transition to a different way of making a CPU. Technically, the Bulldozer core and APU does not have an FPU. Intel's processors still has an old aged FPU.
1 1 [Posted by: tecknurd  | Date: 06/27/11 08:19:00 PM]
They DOES have FPUs or Flex FP or any other names they could have.
APUs are good but still they have crappy Central Processing Unit inside them and at least one year late for them to launch. AMD is definitely proud of AMD(Ouch, I mean ATI). Guess what happens if Intel's graphic parts change or something....

"The E-350 has dual "out of order" X86 cores built on a 40nm process technology, with a total of 1MB of L2 cache (512KB per core). The chip also supports full X86-64 extensions and sports a 64-bit FPU as well." Hothardware :
0 0 [Posted by: Pouria  | Date: 06/28/11 01:22:22 AM]

Its still somewhere 2013. Thats a lot of time. In 2013 next generation or improved bulldozer cores will come out, and probably 2 generation of GPU-s.
I think we will need to wait till 2013. The rest of the world is not sleeping.

Thats probably a bad habit from ARM and the mobile space, to praise your products 2.5 year before launch.
0 1 [Posted by: Zool  | Date: 06/28/11 03:28:54 AM]


Add your Comment

Related news

Latest News

Wednesday, November 5, 2014

10:48 pm | LG’s Unique Ultra-Wide Curved 34” Display Finally Hits the Market. LG 34UC97 Available in the U.S. and the U.K.

Wednesday, October 8, 2014

12:52 pm | Lisa Su Appointed as New CEO of Advanced Micro Devices. Rory Read Steps Down, Lisa Su Becomes New CEO of AMD

Thursday, August 28, 2014

4:22 am | AMD Has No Plans to Reconsider Recommended Prices of Radeon R9 Graphics Cards. AMD Will Not Lower Recommended Prices of Radeon R9 Graphics Solutions

Wednesday, August 27, 2014

1:09 pm | Samsung Begins to Produce 2.13GHz 64GB DDR4 Memory Modules. Samsung Uses TSV DRAMs for 64GB DDR4 RDIMMs

Tuesday, August 26, 2014

10:41 am | AMD Quietly Reveals Third Iteration of GCN Architecture with Tonga GPU. AMD Unleashes Radeon R9 285 Graphics Cards, Tonga GPU, GCN 1.2 Architecture