| To: | linux-mips@linux-mips.org, ralf@linux-mips.org |
|---|---|
| Subject: | [PATCH] MIPS: Optimize pgd_init and pmd_init |
| From: | David Daney <ddaney.cavm@gmail.com> |
| Date: | Thu, 16 Aug 2012 11:15:22 -0700 |
| Cc: | David Daney <ddaney@caviumnetworks.com> |
| Dkim-signature: | v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=from:to:cc:subject:date:message-id:x-mailer; bh=w3Tokz21YM55dmrmpD/SIFo8zNpOxfwZxsxLBqx5cUI=; b=M9sUdkM7W8O5bAaTq3jN4Nzs0rKNl8Dc5MrgRBYZNl/NPMBcKVfVnxSqDpr3LPlb/I h4auET7DcdReiB9CuPZSWEy3R9xMlnfJKWCMqj/xP0KZ2xnML7RlKRnzWCTtMSEEP65z ZCjlVPwGLlj+nT+wpeZNdkEQWEYgCBmYG84gw2Byzm/vd29s0HkRc+IY7E2fNcqbtWQY LJ3rZomXC8xST8c+KO4z9h0CL9tzIDIsQ1e1lkMnUMDwUruqmioTsDilWePp+YCbQw4a 1FBzhyYDotqor54U8GvhlPs59BC3vRBvyyzPNNGt4UPjo2KbpOOvh1OztC8PbvWG3VGw j3ag== |
| List-archive: | <http://www.linux-mips.org/archives/linux-mips/> |
| List-help: | <mailto:ecartis@linux-mips.org?Subject=help> |
| List-id: | linux-mips <linux-mips.eddie.linux-mips.org> |
| List-owner: | <mailto:ralf@linux-mips.org> |
| List-post: | <mailto:linux-mips@linux-mips.org> |
| List-software: | Ecartis version 1.0.0 |
| List-subscribe: | <mailto:ecartis@linux-mips.org?subject=subscribe%20linux-mips> |
| List-unsubscribe: | <mailto:ecartis@linux-mips.org?subject=unsubscribe%20linux-mips> |
| Sender: | linux-mips-bounce@linux-mips.org |
From: David Daney <ddaney@caviumnetworks.com>
On a dual issue processor GCC generates code that saves a couple of
clock cycles per loop if we rearrange things slightly. Checking for
p != end saves a SLTU per loop, moving the increment to the middle can
let it dual issue on multi-issue processors.
Signed-off-by: David Daney <ddaney@caviumnetworks.com>
---
arch/mips/mm/pgtable-64.c | 20 ++++++++++----------
1 file changed, 10 insertions(+), 10 deletions(-)
diff --git a/arch/mips/mm/pgtable-64.c b/arch/mips/mm/pgtable-64.c
index cda4e30..2540779 100644
--- a/arch/mips/mm/pgtable-64.c
+++ b/arch/mips/mm/pgtable-64.c
@@ -26,17 +26,17 @@ void pgd_init(unsigned long page)
p = (unsigned long *) page;
end = p + PTRS_PER_PGD;
- while (p < end) {
+ do {
p[0] = entry;
p[1] = entry;
p[2] = entry;
p[3] = entry;
p[4] = entry;
- p[5] = entry;
- p[6] = entry;
- p[7] = entry;
p += 8;
- }
+ p[-3] = entry;
+ p[-2] = entry;
+ p[-1] = entry;
+ } while (p != end);
}
#ifndef __PAGETABLE_PMD_FOLDED
@@ -47,17 +47,17 @@ void pmd_init(unsigned long addr, unsigned long pagetable)
p = (unsigned long *) addr;
end = p + PTRS_PER_PMD;
- while (p < end) {
+ do {
p[0] = pagetable;
p[1] = pagetable;
p[2] = pagetable;
p[3] = pagetable;
p[4] = pagetable;
- p[5] = pagetable;
- p[6] = pagetable;
- p[7] = pagetable;
p += 8;
- }
+ p[-3] = pagetable;
+ p[-2] = pagetable;
+ p[-1] = pagetable;
+ } while (p != end);
}
#endif
--
1.7.11.2
|
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Re: [PATCH v2 3/3] MIPS: BCM47xx: rewrite GPIO handling and use gpiolib, Rafał Miłecki |
|---|---|
| Next by Date: | Re: [PATCH v3 6/7] mm: make clear_huge_page cache clear only around the fault address, Andrea Arcangeli |
| Previous by Thread: | [PATCH v2 0/3] MIPS: BCM47xx: use gpiolib, Hauke Mehrtens |
| Next by Thread: | Re: [PATCH] MIPS: Optimize pgd_init and pmd_init, Ralf Baechle |
| Indexes: | [Date] [Thread] [Top] [All Lists] |