Arnd Bergmann 2fb9d20636 [PATCH] spufs: set irq affinity for running threads ... For far, all SPU triggered interrupts always end up on the first SMT thread, which is a bad solution. This patch implements setting the affinity to the CPU that was running last when entering execution on an SPU. This should result in a significant reduction in IPI calls and better cache locality for SPE thread specific data. Signed-off-by: Arnd Bergmann <arndb@de.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>		2006-01-09 15:44:57 +11:00
..
spufs	[PATCH] spufs: set irq affinity for running threads	2006-01-09 15:44:57 +11:00
interrupt.c	[PATCH] spufs: set irq affinity for running threads	2006-01-09 15:44:57 +11:00
interrupt.h	[PATCH] spufs: set irq affinity for running threads	2006-01-09 15:44:57 +11:00
iommu.c	[PATCH] powerpc/cell: add iommu support for larger memory	2006-01-09 14:53:24 +11:00
iommu.h	[PATCH] powerpc: move arch/ppc64/kernel/bpa* to arch/powerpc/platforms/cell	2005-11-01 21:03:07 +11:00
Kconfig	[PATCH] spufs: The SPU file system, base	2006-01-09 14:49:12 +11:00
Makefile	[PATCH] spufs: abstract priv1 register access.	2006-01-09 15:44:49 +11:00
pervasive.c	[PATCH] cell: enable pause(0) in cpu_idle	2006-01-09 15:44:32 +11:00
pervasive.h	[PATCH] cell: enable pause(0) in cpu_idle	2006-01-09 15:44:32 +11:00
setup.c	[PATCH] cell: enable pause(0) in cpu_idle	2006-01-09 15:44:32 +11:00
smp.c
spider-pic.c	[PATCH] powerpc: move arch/ppc64/kernel/bpa* to arch/powerpc/platforms/cell	2005-11-01 21:03:07 +11:00
spu_base.c	[PATCH] spufs: set irq affinity for running threads	2006-01-09 15:44:57 +11:00
spu_priv1.c	[PATCH] spufs: abstract priv1 register access.	2006-01-09 15:44:49 +11:00
spu_syscalls.c	[PATCH] spufs: fix module refcount race	2006-01-09 14:53:11 +11:00