aarch64: morello: string: memset

memset from arm optimized-routines morello branch.

diff --git a/sysdeps/aarch64/morello/memset.S b/sysdeps/aarch64/morello/memset.S
new file mode 100644 (file)
index 0000000..db65050
--- /dev/null
+++ b/sysdeps/aarch64/morello/memset.S
@@ -0,0 +1,154 @@
+/* Copyright (C) 2022 Free Software Foundation, Inc.
+
+   This file is part of the GNU C Library.
+
+   The GNU C Library is free software; you can redistribute it and/or
+   modify it under the terms of the GNU Lesser General Public
+   License as published by the Free Software Foundation; either
+   version 2.1 of the License, or (at your option) any later version.
+
+   The GNU C Library is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+   Lesser General Public License for more details.
+
+   You should have received a copy of the GNU Lesser General Public
+   License along with the GNU C Library.  If not, see
+   <https://www.gnu.org/licenses/>.  */
+
+#include <sysdep.h>
+
+#ifndef MEMSET
+# define MEMSET memset
+#endif
+
+/* Assumptions:
+ *
+ * ARMv8-a, AArch64, Morello, Advanced SIMD, unaligned accesses.
+ *
+ */
+
+#if defined(__CHERI_PURE_CAPABILITY__)
+#define dstin  c0
+#define val    x1
+#define valw   w1
+#define count  x2
+#define dst    c3
+#define xdst   x3
+#define dstend c4
+#define xdstend        x4
+#define zva_val        x5
+#else
+#define dstin  x0
+#define val    x1
+#define valw   w1
+#define count  x2
+#define dst    x3
+#define xdst   x3
+#define dstend x4
+#define xdstend        x4
+#define zva_val        x5
+#endif
+
+ENTRY (MEMSET)
+       PTR_ARG (0)
+       SIZE_ARG (2)
+
+       dup     v0.16B, valw
+       add     dstend, dstin, count
+
+       cmp     count, 96
+       b.hi    L(set_long)
+       cmp     count, 16
+       b.hs    L(set_medium)
+       mov     val, v0.D[0]
+
+       /* Set 0..15 bytes.  */
+       tbz     count, 3, 1f
+       str     val, [dstin]
+       str     val, [dstend, -8]
+       ret
+       .p2align 4
+1:     tbz     count, 2, 2f
+       str     valw, [dstin]
+       str     valw, [dstend, -4]
+       ret
+2:     cbz     count, 3f
+       strb    valw, [dstin]
+       tbz     count, 1, 3f
+       strh    valw, [dstend, -2]
+3:     ret
+
+       /* Set 17..96 bytes.  */
+L(set_medium):
+       str     q0, [dstin]
+       tbnz    count, 6, L(set96)
+       str     q0, [dstend, -16]
+       tbz     count, 5, 1f
+       str     q0, [dstin, 16]
+       str     q0, [dstend, -32]
+1:     ret
+
+       .p2align 4
+       /* Set 64..96 bytes.  Write 64 bytes from the start and
+          32 bytes from the end.  */
+L(set96):
+       str     q0, [dstin, 16]
+       stp     q0, q0, [dstin, 32]
+       stp     q0, q0, [dstend, -32]
+       ret
+
+       .p2align 4
+L(set_long):
+       and     valw, valw, 255
+#if defined(__CHERI_PURE_CAPABILITY__)
+       alignd  dst, dstin, 4
+#else
+       bic     dst, dstin, 15
+#endif
+       str     q0, [dstin]
+       cmp     count, 160
+       ccmp    valw, 0, 0, hs
+       b.ne    L(no_zva)
+
+#ifndef SKIP_ZVA_CHECK
+       mrs     zva_val, dczid_el0
+       and     zva_val, zva_val, 31
+       cmp     zva_val, 4              /* ZVA size is 64 bytes.  */
+       b.ne    L(no_zva)
+#endif
+       str     q0, [dst, 16]
+       stp     q0, q0, [dst, 32]
+#if defined(__CHERI_PURE_CAPABILITY__)
+       alignd  dst, dst, 6
+#else
+       bic     dst, dst, 63
+#endif
+       sub     count, xdstend, xdst    /* Count is now 64 too large.  */
+       sub     count, count, 128       /* Adjust count and bias for loop.  */
+
+       .p2align 4
+L(zva_loop):
+       add     dst, dst, 64
+       dc      zva, dst
+       subs    count, count, 64
+       b.hi    L(zva_loop)
+       stp     q0, q0, [dstend, -64]
+       stp     q0, q0, [dstend, -32]
+       ret
+
+L(no_zva):
+       sub     count, xdstend, xdst    /* Count is 16 too large.  */
+       sub     dst, dst, 16            /* Dst is biased by -32.  */
+       sub     count, count, 64 + 16   /* Adjust count and bias for loop.  */
+L(no_zva_loop):
+       stp     q0, q0, [dst, 32]
+       stp     q0, q0, [dst, 64]!
+       subs    count, count, 64
+       b.hi    L(no_zva_loop)
+       stp     q0, q0, [dstend, -64]
+       stp     q0, q0, [dstend, -32]
+       ret
+
+END (MEMSET)
+libc_hidden_builtin_def (MEMSET)