diff options
| -rw-r--r-- | sysdeps/powerpc/powerpc32/cell/memcpy.S | 24 | ||||
| -rw-r--r-- | sysdeps/powerpc/powerpc64/cell/memcpy.S | 24 |
2 files changed, 24 insertions, 24 deletions
diff --git a/sysdeps/powerpc/powerpc32/cell/memcpy.S b/sysdeps/powerpc/powerpc32/cell/memcpy.S index e6c076cbe1..cc1da99fd9 100644 --- a/sysdeps/powerpc/powerpc32/cell/memcpy.S +++ b/sysdeps/powerpc/powerpc32/cell/memcpy.S @@ -43,16 +43,16 @@ .align 7 EALIGN (BP_SYM (memcpy), 5, 0) - CALL_MCOUNT + CALL_MCOUNT dcbt 0,r4 /* Prefetch ONE SRC cacheline */ cmplwi cr1,r5,16 /* is size < 16 ? */ - mr r6,r3 + mr r6,r3 blt+ cr1,.Lshortcopy .Lbigcopy: neg r8,r3 /* LS 3 bits = # bytes to 8-byte dest bdry */ - clrlwi r8,r8,32-4 /* aling to 16byte boundary */ + clrlwi r8,r8,32-4 /* aling to 16byte boundary */ sub r7,r4,r3 cmplwi cr0,r8,0 beq+ .Ldst_aligned @@ -112,8 +112,8 @@ EALIGN (BP_SYM (memcpy), 5, 0) .LprefetchSRC: dcbt r12,r4 - addi r12,r12,128 - bdnz .LprefetchSRC + addi r12,r12,128 + bdnz .LprefetchSRC .Lnocacheprefetch: mtctr r7 @@ -122,7 +122,7 @@ EALIGN (BP_SYM (memcpy), 5, 0) beq cr6,.Lcachelinealigned .Laligntocacheline: - lfd fp9,0x08(r4) + lfd fp9,0x08(r4) lfdu fp10,0x10(r4) stfd fp9,0x08(r6) stfdu fp10,0x10(r6) @@ -131,10 +131,10 @@ EALIGN (BP_SYM (memcpy), 5, 0) .Lcachelinealigned: /* copy while cache lines */ - blt- cr1,.Llessthancacheline /* size <128 */ + blt- cr1,.Llessthancacheline /* size <128 */ .Louterloop: - cmpwi r11,0 + cmpwi r11,0 mtctr r11 beq- .Lendloop @@ -142,7 +142,7 @@ EALIGN (BP_SYM (memcpy), 5, 0) .align 4 /* Copy whole cachelines, optimized by prefetching SRC cacheline */ -.Lloop: /* Copy aligned body */ +.Lloop: /* Copy aligned body */ dcbt r12,r4 /* PREFETCH SOURCE some cache lines ahead */ lfd fp9, 0x08(r4) dcbz r11,r6 @@ -186,7 +186,7 @@ EALIGN (BP_SYM (memcpy), 5, 0) beq- .Lendloop2 mtctr r10 -.Lloop2: /* Copy aligned body */ +.Lloop2: /* Copy aligned body */ lfd fp9, 0x08(r4) lfd fp10, 0x10(r4) lfd fp11, 0x18(r4) @@ -206,7 +206,7 @@ EALIGN (BP_SYM (memcpy), 5, 0) mtctr r7 .Lcopy_remaining: - lfd fp9,0x08(r4) + lfd fp9,0x08(r4) lfdu fp10,0x10(r4) stfd fp9,0x08(r6) stfdu fp10,0x10(r6) @@ -214,7 +214,7 @@ EALIGN (BP_SYM (memcpy), 5, 0) .Ldo_lt16: /* less than 16 ? */ cmplwi cr0,r5,0 /* copy remaining bytes (0-15) */ - beqlr+ /* no rest to copy */ + beqlr+ /* no rest to copy */ addi r4,r4,8 addi r6,r6,8 diff --git a/sysdeps/powerpc/powerpc64/cell/memcpy.S b/sysdeps/powerpc/powerpc64/cell/memcpy.S index 2a00a6ed52..c6ee730e4e 100644 --- a/sysdeps/powerpc/powerpc64/cell/memcpy.S +++ b/sysdeps/powerpc/powerpc64/cell/memcpy.S @@ -43,16 +43,16 @@ .align 7 EALIGN (BP_SYM (memcpy), 5, 0) - CALL_MCOUNT 3 + CALL_MCOUNT 3 dcbt 0,r4 /* Prefetch ONE SRC cacheline */ cmpldi cr1,r5,16 /* is size < 16 ? */ - mr r6,r3 + mr r6,r3 blt+ cr1,.Lshortcopy .Lbigcopy: neg r8,r3 /* LS 3 bits = # bytes to 8-byte dest bdry */ - clrldi r8,r8,64-4 /* aling to 16byte boundary */ + clrldi r8,r8,64-4 /* aling to 16byte boundary */ sub r7,r4,r3 cmpldi cr0,r8,0 beq+ .Ldst_aligned @@ -112,8 +112,8 @@ EALIGN (BP_SYM (memcpy), 5, 0) .LprefetchSRC: dcbt r12,r4 - addi r12,r12,128 - bdnz .LprefetchSRC + addi r12,r12,128 + bdnz .LprefetchSRC .Lnocacheprefetch: mtctr r7 @@ -122,7 +122,7 @@ EALIGN (BP_SYM (memcpy), 5, 0) beq cr6,.Lcachelinealigned .Laligntocacheline: - ld r9,0x08(r4) + ld r9,0x08(r4) ldu r7,0x10(r4) std r9,0x08(r6) stdu r7,0x10(r6) @@ -131,10 +131,10 @@ EALIGN (BP_SYM (memcpy), 5, 0) .Lcachelinealigned: /* copy while cache lines */ - blt- cr1,.Llessthancacheline /* size <128 */ + blt- cr1,.Llessthancacheline /* size <128 */ .Louterloop: - cmpdi r11,0 + cmpdi r11,0 mtctr r11 beq- .Lendloop @@ -142,7 +142,7 @@ EALIGN (BP_SYM (memcpy), 5, 0) .align 4 /* Copy whole cachelines, optimized by prefetching SRC cacheline */ -.Lloop: /* Copy aligned body */ +.Lloop: /* Copy aligned body */ dcbt r12,r4 /* PREFETCH SOURCE some cache lines ahead */ ld r9, 0x08(r4) dcbz r11,r6 @@ -186,7 +186,7 @@ EALIGN (BP_SYM (memcpy), 5, 0) beq- .Lendloop2 mtctr r10 -.Lloop2: /* Copy aligned body */ +.Lloop2: /* Copy aligned body */ ld r9, 0x08(r4) ld r7, 0x10(r4) ld r8, 0x18(r4) @@ -206,7 +206,7 @@ EALIGN (BP_SYM (memcpy), 5, 0) mtctr r7 .Lcopy_remaining: - ld r8,0x08(r4) + ld r8,0x08(r4) ldu r7,0x10(r4) std r8,0x08(r6) stdu r7,0x10(r6) @@ -214,7 +214,7 @@ EALIGN (BP_SYM (memcpy), 5, 0) .Ldo_lt16: /* less than 16 ? */ cmpldi cr0,r5,0 /* copy remaining bytes (0-15) */ - beqlr+ /* no rest to copy */ + beqlr+ /* no rest to copy */ addi r4,r4,8 addi r6,r6,8 |