diff options
| author |   Andrey Smirnov <andrew.smirnov@gmail.com> | 2016-06-18 18:09:30 -0700 |
|---|---|---|
| committer |   Shawn Guo <shawnguo@kernel.org> | 2016-06-21 20:40:38 +0800 |
| commit | 1d9e94779956b765d316924cc39af2165ad631fb (patch) | |
| tree | 494f9ff55568aec4eb5260139a6ef23bf1570d03 | |
| parent | ARM: i.MX: system.c: Replace magic numbers (diff) | |
| download | linux-dev-1d9e94779956b765d316924cc39af2165ad631fb.tar.xz linux-dev-1d9e94779956b765d316924cc39af2165ad631fb.zip | |
ARM: i.MX: system.c: Tweak prefetch settings for performance
Update Prefetch Control Register settings to match that of Freescale's
Linux tree. As the commit e3addf1b773964eac7f797e8538c69481be4279c
states (author Nitin Garg):
"... set Prefetch offset to 15, since it improves memcpy performance by
35%. Don't enable Incr double Linefill enable since it adversely affects
memcpy performance by about 32MB/s and reads by 90MB/s. Tested with 4K
to 16MB sized src and dst aligned buffer..."
Those results are also corroborated by our own testing.
Acked-by: Arnd Bergmann <arnd@arndb.de>
Tested-by: Chris Healy <cphealy@gmail.com>
Signed-off-by: Andrey Smirnov <andrew.smirnov@gmail.com>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
| -rw-r--r-- | arch/arm/mach-imx/system.c | 8 |
1 files changed, 6 insertions, 2 deletions
diff --git a/arch/arm/mach-imx/system.c b/arch/arm/mach-imx/system.c index 76d7ebe883d7..bf7ab779d5bf 100644 --- a/arch/arm/mach-imx/system.c +++ b/arch/arm/mach-imx/system.c @@ -111,8 +111,12 @@ void __init imx_init_l2cache(void) val = readl_relaxed(l2x0_base + L310_PREFETCH_CTRL); val |= L310_PREFETCH_CTRL_DBL_LINEFILL | L310_PREFETCH_CTRL_INSTR_PREFETCH | - L310_PREFETCH_CTRL_DATA_PREFETCH | - L310_PREFETCH_CTRL_DBL_LINEFILL_INCR; + L310_PREFETCH_CTRL_DATA_PREFETCH; + + /* Set perfetch offset to improve performance */ + val &= ~L310_PREFETCH_CTRL_OFFSET_MASK; + val |= 15; + writel_relaxed(val, l2x0_base + L310_PREFETCH_CTRL); } |