diff options
Diffstat (limited to 'arch/powerpc/lib/memcpy_power7.S')
| -rw-r--r-- | arch/powerpc/lib/memcpy_power7.S | 81 |
1 files changed, 45 insertions, 36 deletions
diff --git a/arch/powerpc/lib/memcpy_power7.S b/arch/powerpc/lib/memcpy_power7.S index 0663630baf3..2ff5c142f87 100644 --- a/arch/powerpc/lib/memcpy_power7.S +++ b/arch/powerpc/lib/memcpy_power7.S @@ -20,18 +20,27 @@ #include <asm/ppc_asm.h> _GLOBAL(memcpy_power7) + +#ifdef __BIG_ENDIAN__ +#define LVS(VRT,RA,RB) lvsl VRT,RA,RB +#define VPERM(VRT,VRA,VRB,VRC) vperm VRT,VRA,VRB,VRC +#else +#define LVS(VRT,RA,RB) lvsr VRT,RA,RB +#define VPERM(VRT,VRA,VRB,VRC) vperm VRT,VRB,VRA,VRC +#endif + #ifdef CONFIG_ALTIVEC cmpldi r5,16 cmpldi cr1,r5,4096 - std r3,48(r1) + std r3,-STACKFRAMESIZE+STK_REG(R31)(r1) blt .Lshort_copy bgt cr1,.Lvmx_copy #else cmpldi r5,16 - std r3,48(r1) + std r3,-STACKFRAMESIZE+STK_REG(R31)(r1) blt .Lshort_copy #endif @@ -207,7 +216,7 @@ _GLOBAL(memcpy_power7) lbz r0,0(r4) stb r0,0(r3) -15: ld r3,48(r1) +15: ld r3,-STACKFRAMESIZE+STK_REG(R31)(r1) blr .Lunwind_stack_nonvmx_copy: @@ -217,16 +226,16 @@ _GLOBAL(memcpy_power7) #ifdef CONFIG_ALTIVEC .Lvmx_copy: mflr r0 - std r4,56(r1) - std r5,64(r1) + std r4,-STACKFRAMESIZE+STK_REG(R30)(r1) + std r5,-STACKFRAMESIZE+STK_REG(R29)(r1) std r0,16(r1) stdu r1,-STACKFRAMESIZE(r1) - bl .enter_vmx_copy + bl enter_vmx_copy cmpwi cr1,r3,0 ld r0,STACKFRAMESIZE+16(r1) - ld r3,STACKFRAMESIZE+48(r1) - ld r4,STACKFRAMESIZE+56(r1) - ld r5,STACKFRAMESIZE+64(r1) + ld r3,STK_REG(R31)(r1) + ld r4,STK_REG(R30)(r1) + ld r5,STK_REG(R29)(r1) mtlr r0 /* @@ -438,8 +447,8 @@ _GLOBAL(memcpy_power7) stb r0,0(r3) 15: addi r1,r1,STACKFRAMESIZE - ld r3,48(r1) - b .exit_vmx_copy /* tail call optimise */ + ld r3,-STACKFRAMESIZE+STK_REG(R31)(r1) + b exit_vmx_copy /* tail call optimise */ .Lvmx_unaligned_copy: /* Get the destination 16B aligned */ @@ -485,13 +494,13 @@ _GLOBAL(memcpy_power7) li r10,32 li r11,48 - lvsl vr16,0,r4 /* Setup permute control vector */ + LVS(vr16,0,r4) /* Setup permute control vector */ lvx vr0,0,r4 addi r4,r4,16 bf cr7*4+3,5f lvx vr1,r0,r4 - vperm vr8,vr0,vr1,vr16 + VPERM(vr8,vr0,vr1,vr16) addi r4,r4,16 stvx vr8,r0,r3 addi r3,r3,16 @@ -499,9 +508,9 @@ _GLOBAL(memcpy_power7) 5: bf cr7*4+2,6f lvx vr1,r0,r4 - vperm vr8,vr0,vr1,vr16 + VPERM(vr8,vr0,vr1,vr16) lvx vr0,r4,r9 - vperm vr9,vr1,vr0,vr16 + VPERM(vr9,vr1,vr0,vr16) addi r4,r4,32 stvx vr8,r0,r3 stvx vr9,r3,r9 @@ -509,13 +518,13 @@ _GLOBAL(memcpy_power7) 6: bf cr7*4+1,7f lvx vr3,r0,r4 - vperm vr8,vr0,vr3,vr16 + VPERM(vr8,vr0,vr3,vr16) lvx vr2,r4,r9 - vperm vr9,vr3,vr2,vr16 + VPERM(vr9,vr3,vr2,vr16) lvx vr1,r4,r10 - vperm vr10,vr2,vr1,vr16 + VPERM(vr10,vr2,vr1,vr16) lvx vr0,r4,r11 - vperm vr11,vr1,vr0,vr16 + VPERM(vr11,vr1,vr0,vr16) addi r4,r4,64 stvx vr8,r0,r3 stvx vr9,r3,r9 @@ -544,21 +553,21 @@ _GLOBAL(memcpy_power7) .align 5 8: lvx vr7,r0,r4 - vperm vr8,vr0,vr7,vr16 + VPERM(vr8,vr0,vr7,vr16) lvx vr6,r4,r9 - vperm vr9,vr7,vr6,vr16 + VPERM(vr9,vr7,vr6,vr16) lvx vr5,r4,r10 - vperm vr10,vr6,vr5,vr16 + VPERM(vr10,vr6,vr5,vr16) lvx vr4,r4,r11 - vperm vr11,vr5,vr4,vr16 + VPERM(vr11,vr5,vr4,vr16) lvx vr3,r4,r12 - vperm vr12,vr4,vr3,vr16 + VPERM(vr12,vr4,vr3,vr16) lvx vr2,r4,r14 - vperm vr13,vr3,vr2,vr16 + VPERM(vr13,vr3,vr2,vr16) lvx vr1,r4,r15 - vperm vr14,vr2,vr1,vr16 + VPERM(vr14,vr2,vr1,vr16) lvx vr0,r4,r16 - vperm vr15,vr1,vr0,vr16 + VPERM(vr15,vr1,vr0,vr16) addi r4,r4,128 stvx vr8,r0,r3 stvx vr9,r3,r9 @@ -582,13 +591,13 @@ _GLOBAL(memcpy_power7) bf cr7*4+1,9f lvx vr3,r0,r4 - vperm vr8,vr0,vr3,vr16 + VPERM(vr8,vr0,vr3,vr16) lvx vr2,r4,r9 - vperm vr9,vr3,vr2,vr16 + VPERM(vr9,vr3,vr2,vr16) lvx vr1,r4,r10 - vperm vr10,vr2,vr1,vr16 + VPERM(vr10,vr2,vr1,vr16) lvx vr0,r4,r11 - vperm vr11,vr1,vr0,vr16 + VPERM(vr11,vr1,vr0,vr16) addi r4,r4,64 stvx vr8,r0,r3 stvx vr9,r3,r9 @@ -598,9 +607,9 @@ _GLOBAL(memcpy_power7) 9: bf cr7*4+2,10f lvx vr1,r0,r4 - vperm vr8,vr0,vr1,vr16 + VPERM(vr8,vr0,vr1,vr16) lvx vr0,r4,r9 - vperm vr9,vr1,vr0,vr16 + VPERM(vr9,vr1,vr0,vr16) addi r4,r4,32 stvx vr8,r0,r3 stvx vr9,r3,r9 @@ -608,7 +617,7 @@ _GLOBAL(memcpy_power7) 10: bf cr7*4+3,11f lvx vr1,r0,r4 - vperm vr8,vr0,vr1,vr16 + VPERM(vr8,vr0,vr1,vr16) addi r4,r4,16 stvx vr8,r0,r3 addi r3,r3,16 @@ -642,6 +651,6 @@ _GLOBAL(memcpy_power7) stb r0,0(r3) 15: addi r1,r1,STACKFRAMESIZE - ld r3,48(r1) - b .exit_vmx_copy /* tail call optimise */ + ld r3,-STACKFRAMESIZE+STK_REG(R31)(r1) + b exit_vmx_copy /* tail call optimise */ #endif /* CONFiG_ALTIVEC */ |