ARM: Improve armv7 memcpy performance.

Only enter the aligned copy loop with buffers that can be 8-byte
aligned. This improves performance slightly on Cortex-A9 and
Cortex-A15 cores for large copies with buffers that are 4-byte
aligned but not 8-byte aligned.

ports/ChangeLog.arm:

2013-09-16  Will Newton  <will.newton@linaro.org>

	* sysdeps/arm/armv7/multiarch/memcpy_impl.S: Tighten check
	on entry to aligned copy loop to improve performance.

diff --git a/ports/ChangeLog.arm b/ports/ChangeLog.arm
index 8ef09b1..35f6f77 100644 (file)
--- a/ports/ChangeLog.arm
+++ b/ports/ChangeLog.arm
@@ -1,3 +1,8 @@
+2013-09-16  Will Newton  <will.newton@linaro.org>
+
+       * sysdeps/arm/armv7/multiarch/memcpy_impl.S: Tighten check
+       on entry to aligned copy loop to improve performance.
+
 2013-08-30  Roland McGrath  <roland@hack.frob.com>
 
        * sysdeps/arm/armv6t2/strlen.S: Use sfi_pld and sfi_breg macros.

diff --git a/ports/sysdeps/arm/armv7/multiarch/memcpy_impl.S b/ports/sysdeps/arm/armv7/multiarch/memcpy_impl.S
index 3decad6..ad43a3d 100644 (file)
--- a/ports/sysdeps/arm/armv7/multiarch/memcpy_impl.S
+++ b/ports/sysdeps/arm/armv7/multiarch/memcpy_impl.S
@@ -24,7 +24,6 @@
     ARMv6 (ARMv7-a if using Neon)
     ARM state
     Unaligned accesses
-    LDRD/STRD support unaligned word accesses
 
  */
 
@@ -369,8 +368,8 @@ ENTRY(memcpy)
        cfi_adjust_cfa_offset (FRAME_SIZE)
        cfi_rel_offset (tmp2, 0)
        cfi_remember_state
-       and     tmp2, src, #3
-       and     tmp1, dst, #3
+       and     tmp2, src, #7
+       and     tmp1, dst, #7
        cmp     tmp1, tmp2
        bne     .Lcpy_notaligned
 
@@ -381,9 +380,9 @@ ENTRY(memcpy)
        vmov.f32        s0, s0
 #endif
 
-       /* SRC and DST have the same mutual 32-bit alignment, but we may
+       /* SRC and DST have the same mutual 64-bit alignment, but we may
           still need to pre-copy some bytes to get to natural alignment.
-          We bring DST into full 64-bit alignment.  */
+          We bring SRC and DST into full 64-bit alignment.  */
        lsls    tmp2, dst, #29
        beq     1f
        rsbs    tmp2, tmp2, #0
@@ -515,7 +514,7 @@ ENTRY(memcpy)
 
 .Ltail63aligned:                       /* Count in tmp2.  */
        /* Copy up to 7 d-words of data.  Similar to Ltail63unaligned, but
-          we know that the src and dest are 32-bit aligned so we can use
+          we know that the src and dest are 64-bit aligned so we can use
           LDRD/STRD to improve efficiency.  */
        /* TMP2 is now negative, but we don't care about that.  The bottom
           six bits still tell us how many bytes are left to copy.  */