diff --git a/arch/arc/lib/memset-archs.S b/arch/arc/lib/memset-archs.S index 92d573c734b5b3d52dec2d8fcf6eb67cc96d16f6..365b183648154c70de1726955b9242e88d3cc60c 100644 --- a/arch/arc/lib/memset-archs.S +++ b/arch/arc/lib/memset-archs.S @@ -10,12 +10,6 @@ #undef PREALLOC_NOT_AVAIL -#ifdef PREALLOC_NOT_AVAIL -#define PREWRITE(A,B) prefetchw [(A),(B)] -#else -#define PREWRITE(A,B) prealloc [(A),(B)] -#endif - ENTRY(memset) prefetchw [r0] ; Prefetch the write location mov.f 0, r2 @@ -51,9 +45,15 @@ ENTRY(memset) ;;; Convert len to Dwords, unfold x8 lsr.f lp_count, lp_count, 6 + lpnz @.Lset64bytes ;; LOOP START - PREWRITE(r3, 64) ;Prefetch the next write location +#ifdef PREALLOC_NOT_AVAIL + prefetchw [r3, 64] ;Prefetch the next write location +#else + prealloc [r3, 64] +#endif +#ifdef CONFIG_ARC_HAS_LL64 std.ab r4, [r3, 8] std.ab r4, [r3, 8] std.ab r4, [r3, 8] @@ -62,16 +62,45 @@ ENTRY(memset) std.ab r4, [r3, 8] std.ab r4, [r3, 8] std.ab r4, [r3, 8] +#else + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] +#endif .Lset64bytes: lsr.f lp_count, r2, 5 ;Last remaining max 124 bytes lpnz .Lset32bytes ;; LOOP START prefetchw [r3, 32] ;Prefetch the next write location +#ifdef CONFIG_ARC_HAS_LL64 std.ab r4, [r3, 8] std.ab r4, [r3, 8] std.ab r4, [r3, 8] std.ab r4, [r3, 8] +#else + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] + st.ab r4, [r3, 4] +#endif .Lset32bytes: and.f lp_count, r2, 0x1F ;Last remaining 31 bytes