Re: just for fun: it's so GREAT delphi (2006) !!!!!!!!!!!!

It looks like the world is in competition
to make sure that every extra bit of performance that CPU
manufacturers are struggling for is nullified by bloatware
without giving any benefits.

Enter world of sloppy unqualified people with their craniums
stuffed with propaganda instead of brains

It's really too bad. CPU's slow down at the memory access bottleneck.
Thus, you want as much of your program to fit into L1/L2/L3 cache as
possible otherwise memory access hurts performance. This means the majority
if your application needs to fit into 512k for modern processors and 256k
for older processors (granted, there are 1MB+ L1 caches but they aren't the
norm -- yet).

So when you create software that starts up consuming 30MB (Office) or 280MB
(VS 2005) then you have no performance benefits because you'll constantly be
accessing main RAM through the 800 MB FSB, but not at CPU speed (L1 - L3
cache).

For server applications, its easier to write something in under 256k.
Modulerize properly and it can be done.

But the fact is, most people don't want to tweak. Tools themselves generate
bloated code but its far easier to maintain and enhance fairly (compiler)
standard code than heavily tweaked code. Overall, the general population
isn't concerned about performance or memory anyway because we are so
brainwashed to think that more memory and more CPU speeed and more CPU cores
mitigates that fact. Perhaps to an extend, but I see no reason to be
glutonous with memory consumption when there is no need. After all, try
creating a simpile calculator in VC and right off the bat you're consuming
30k memory. Do the same program in MASM and its taking 3k of ram. How many
of us program windows programs in Assembly, though?


Thanks,
Shawn


.

Relevant Pages

  • Re: FPGA-based hardware accelerator for PC
    ... I know that in most cases the CPU ... that it contsins no cache, as BRAMs are too precious resources to be wasted ... The BRAMs are what define the opportunity, ... many threads with full associativity of memory lines using hashed MMU ...
    (comp.arch.fpga)
  • Re: Adjusting PC Hyperthreading for Spice Simulation
    ... Memory access taking hundreds of cycles? ... ago), 350 CPU cycles for a code cache miss was not atypical, but RAM ...
    (sci.electronics.design)
  • Re: Cost of calling a standard library function
    ... It accesses/reads memory using esi 4 ... > safly move it within the cache, without having to go via ebx. ... try it the same thing on a different earlier CPU, ... should check it out...for "tight inner loop" stuff, ...
    (alt.lang.asm)
  • Re: What can I check to fix system performance?
    ... it seems you have plenty of memory available: ... copies of files you have read of written lately, in a cache, in case ... processes per CPU, or 40 in all. ... Consider the disk structure. ...
    (comp.os.linux.setup)
  • Re: Adjusting PC Hyperthreading for Spice Simulation
    ... Memory access taking hundreds of cycles? ... ago), 350 CPU cycles for a code cache miss was not atypical, but RAM ...
    (sci.electronics.design)