On POWER6 systems RA needs to be the base and RB the index. If they are reversed you take a misdirect hit.
Signed-off-by: Mike Wolf <[email protected]> ---- --- altivec.orig/arch/powerpc/include/asm/ppc_asm.h 2009-08-17 15:39:52.000000000 -0500 +++ altivec/arch/powerpc/include/asm/ppc_asm.h 2009-08-20 18:08:30.000000000 -0500 @@ -98,13 +98,13 @@ #define REST_16FPRS(n, base) REST_8FPRS(n, base); REST_8FPRS(n+8, base) #define REST_32FPRS(n, base) REST_16FPRS(n, base); REST_16FPRS(n+16, base) -#define SAVE_VR(n,b,base) li b,THREAD_VR0+(16*(n)); stvx n,b,base +#define SAVE_VR(n,b,base) li b,THREAD_VR0+(16*(n)); stvx n,base,b #define SAVE_2VRS(n,b,base) SAVE_VR(n,b,base); SAVE_VR(n+1,b,base) #define SAVE_4VRS(n,b,base) SAVE_2VRS(n,b,base); SAVE_2VRS(n+2,b,base) #define SAVE_8VRS(n,b,base) SAVE_4VRS(n,b,base); SAVE_4VRS(n+4,b,base) #define SAVE_16VRS(n,b,base) SAVE_8VRS(n,b,base); SAVE_8VRS(n+8,b,base) #define SAVE_32VRS(n,b,base) SAVE_16VRS(n,b,base); SAVE_16VRS(n+16,b,base) -#define REST_VR(n,b,base) li b,THREAD_VR0+(16*(n)); lvx n,b,base +#define REST_VR(n,b,base) li b,THREAD_VR0+(16*(n)); lvx n,base,b #define REST_2VRS(n,b,base) REST_VR(n,b,base); REST_VR(n+1,b,base) #define REST_4VRS(n,b,base) REST_2VRS(n,b,base); REST_2VRS(n+2,b,base) #define REST_8VRS(n,b,base) REST_4VRS(n,b,base); REST_4VRS(n+4,b,base) @@ -112,26 +112,26 @@ #define REST_32VRS(n,b,base) REST_16VRS(n,b,base); REST_16VRS(n+16,b,base) /* Save the lower 32 VSRs in the thread VSR region */ -#define SAVE_VSR(n,b,base) li b,THREAD_VSR0+(16*(n)); STXVD2X(n,b,base) +#define SAVE_VSR(n,b,base) li b,THREAD_VSR0+(16*(n)); STXVD2X(n,base,b) #define SAVE_2VSRS(n,b,base) SAVE_VSR(n,b,base); SAVE_VSR(n+1,b,base) #define SAVE_4VSRS(n,b,base) SAVE_2VSRS(n,b,base); SAVE_2VSRS(n+2,b,base) #define SAVE_8VSRS(n,b,base) SAVE_4VSRS(n,b,base); SAVE_4VSRS(n+4,b,base) #define SAVE_16VSRS(n,b,base) SAVE_8VSRS(n,b,base); SAVE_8VSRS(n+8,b,base) #define SAVE_32VSRS(n,b,base) SAVE_16VSRS(n,b,base); SAVE_16VSRS(n+16,b,base) -#define REST_VSR(n,b,base) li b,THREAD_VSR0+(16*(n)); LXVD2X(n,b,base) +#define REST_VSR(n,b,base) li b,THREAD_VSR0+(16*(n)); LXVD2X(n,base,b) #define REST_2VSRS(n,b,base) REST_VSR(n,b,base); REST_VSR(n+1,b,base) #define REST_4VSRS(n,b,base) REST_2VSRS(n,b,base); REST_2VSRS(n+2,b,base) #define REST_8VSRS(n,b,base) REST_4VSRS(n,b,base); REST_4VSRS(n+4,b,base) #define REST_16VSRS(n,b,base) REST_8VSRS(n,b,base); REST_8VSRS(n+8,b,base) #define REST_32VSRS(n,b,base) REST_16VSRS(n,b,base); REST_16VSRS(n+16,b,base) /* Save the upper 32 VSRs (32-63) in the thread VSX region (0-31) */ -#define SAVE_VSRU(n,b,base) li b,THREAD_VR0+(16*(n)); STXVD2X(n+32,b,base) +#define SAVE_VSRU(n,b,base) li b,THREAD_VR0+(16*(n)); STXVD2X(n+32,base,b) #define SAVE_2VSRSU(n,b,base) SAVE_VSRU(n,b,base); SAVE_VSRU(n+1,b,base) #define SAVE_4VSRSU(n,b,base) SAVE_2VSRSU(n,b,base); SAVE_2VSRSU(n+2,b,base) #define SAVE_8VSRSU(n,b,base) SAVE_4VSRSU(n,b,base); SAVE_4VSRSU(n+4,b,base) #define SAVE_16VSRSU(n,b,base) SAVE_8VSRSU(n,b,base); SAVE_8VSRSU(n+8,b,base) #define SAVE_32VSRSU(n,b,base) SAVE_16VSRSU(n,b,base); SAVE_16VSRSU(n+16,b,base) -#define REST_VSRU(n,b,base) li b,THREAD_VR0+(16*(n)); LXVD2X(n+32,b,base) +#define REST_VSRU(n,b,base) li b,THREAD_VR0+(16*(n)); LXVD2X(n+32,base,b) #define REST_2VSRSU(n,b,base) REST_VSRU(n,b,base); REST_VSRU(n+1,b,base) #define REST_4VSRSU(n,b,base) REST_2VSRSU(n,b,base); REST_2VSRSU(n+2,b,base) #define REST_8VSRSU(n,b,base) REST_4VSRSU(n,b,base); REST_4VSRSU(n+4,b,base) _______________________________________________ Linuxppc-dev mailing list [email protected] https://lists.ozlabs.org/listinfo/linuxppc-dev
