Search String: Display: Description: Sort:

Results:

References: [ +subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*\[PATCH\]\s+skb_\{over\,under\}_panic\s+optimizations\s*$/: 10 ]

Total 10 documents matching your query.

1. [PATCH] skb_{over,under}_panic optimizations (score: 1)
Author: xxxxxxxxxxxxxx>
Date: Sun, 15 Jul 2001 22:37:03 -0400 (EDT)
Hello Dave & all, Below is a patch that moves the skb_{over,under}_panic function calls in skb_put and skb_push out of line on i386 and hopefully improves register allocation. If this turns out to be
/archives/netdev/2001-07/msg00029.html (14,475 bytes)

2. Re: [PATCH] skb_{over,under}_panic optimizations (score: 1)
Author: crl@xxxxxxxxxx>
Date: Mon, 16 Jul 2001 13:11:05 +1000
'call skb_" why "_panic' will break using module symbol versions, skb_*_panic symbols are exported so all references to those symbols need to be visible to cpp, not inside string quotes. This should
/archives/netdev/2001-07/msg00030.html (8,951 bytes)

3. Re: [PATCH] skb_{over,under}_panic optimizations (score: 1)
Author: aos@xxxxxxxxxx>
Date: Mon, 16 Jul 2001 13:20:43 +1000
Oops, pressed send too soon. Because you are putting the code in .text.lock which is an unusual section, it will make debugging easier if you make the skb code look like the existing lock code, where
/archives/netdev/2001-07/msg00031.html (9,732 bytes)

4. Re: [PATCH] skb_{over,under}_panic optimizations (score: 1)
Author: xxxxxxxxxxxxxx>
Date: Mon, 16 Jul 2001 15:11:03 +0200
How ugly. Does this really make any benchmarkable difference? (very much doubting it) If you really care about such microoptimization just use __builtin_expect. -Andi
/archives/netdev/2001-07/msg00033.html (8,239 bytes)

5. Re: [PATCH] skb_{over,under}_panic optimizations (score: 1)
Author: vem@xxxxxxxxxx>
Date: Mon, 16 Jul 2001 15:36:46 -0700 (PDT)
I can't see how this can make all that much of a difference, as Andi has stated already. Especially on x86. I mean, GCC is going to generate a branch around the "call skb_foo_panic" code block, and t
/archives/netdev/2001-07/msg00045.html (8,446 bytes)

6. [PATCH] skb_{over,under}_panic optimizations (score: 1)
Author: Ben LaHaise <bcrl@xxxxxxxxxx>
Date: Sun, 15 Jul 2001 22:37:03 -0400 (EDT)
Hello Dave & all, Below is a patch that moves the skb_{over,under}_panic function calls in skb_put and skb_push out of line on i386 and hopefully improves register allocation. If this turns out to be
/archives/netdev/2001-07/msg00206.html (14,475 bytes)

7. Re: [PATCH] skb_{over,under}_panic optimizations (score: 1)
Author: Keith Owens <kaos@xxxxxxxxxx>
Date: Mon, 16 Jul 2001 13:11:05 +1000
'call skb_" why "_panic' will break using module symbol versions, skb_*_panic symbols are exported so all references to those symbols need to be visible to cpp, not inside string quotes. This should
/archives/netdev/2001-07/msg00207.html (8,998 bytes)

8. Re: [PATCH] skb_{over,under}_panic optimizations (score: 1)
Author: Keith Owens <kaos@xxxxxxxxxx>
Date: Mon, 16 Jul 2001 13:20:43 +1000
Oops, pressed send too soon. Because you are putting the code in .text.lock which is an unusual section, it will make debugging easier if you make the skb code look like the existing lock code, where
/archives/netdev/2001-07/msg00208.html (9,779 bytes)

9. Re: [PATCH] skb_{over,under}_panic optimizations (score: 1)
Author: Andi Kleen <ak@xxxxxx>
Date: Mon, 16 Jul 2001 15:11:03 +0200
How ugly. Does this really make any benchmarkable difference? (very much doubting it) If you really care about such microoptimization just use __builtin_expect. -Andi
/archives/netdev/2001-07/msg00210.html (8,375 bytes)

10. Re: [PATCH] skb_{over,under}_panic optimizations (score: 1)
Author: "David S. Miller" <davem@xxxxxxxxxx>
Date: Mon, 16 Jul 2001 15:36:46 -0700 (PDT)
I can't see how this can make all that much of a difference, as Andi has stated already. Especially on x86. I mean, GCC is going to generate a branch around the "call skb_foo_panic" code block, and t
/archives/netdev/2001-07/msg00222.html (8,542 bytes)


This search system is powered by Namazu