Remove NEON optimizations for memcpy
diff --git a/libc/arch-arm/bionic/memcpy.S b/libc/arch-arm/bionic/memcpy.S
index 4ea2c6d..fcb58cd 100644
--- a/libc/arch-arm/bionic/memcpy.S
+++ b/libc/arch-arm/bionic/memcpy.S
@@ -28,111 +28,6 @@
#include <machine/cpu-features.h>
-#if __ARM_ARCH__ == 7 || defined(__ARM_NEON__)
-
- .text
- .fpu neon
-
- .global memcpy
- .type memcpy, %function
- .align 4
-
-#define NEON_MAX_PREFETCH_DISTANCE 320
-
-memcpy:
- .fnstart
- mov ip, r0
- cmp r2, #16
- blt 4f @ Have less than 16 bytes to copy
-
- @ First ensure 16 byte alignment for the destination buffer
- tst r0, #0xF
- beq 2f
- tst r0, #1
- ldrneb r3, [r1], #1
- strneb r3, [ip], #1
- subne r2, r2, #1
- tst ip, #2
- ldrneb r3, [r1], #1
- strneb r3, [ip], #1
- ldrneb r3, [r1], #1
- strneb r3, [ip], #1
- subne r2, r2, #2
-
- tst ip, #4
- beq 1f
- vld4.8 {d0[0], d1[0], d2[0], d3[0]}, [r1]!
- vst4.8 {d0[0], d1[0], d2[0], d3[0]}, [ip, :32]!
- sub r2, r2, #4
-1:
- tst ip, #8
- beq 2f
- vld1.8 {d0}, [r1]!
- vst1.8 {d0}, [ip, :64]!
- sub r2, r2, #8
-2:
- subs r2, r2, #32
- blt 3f
- mov r3, #32
-
- @ Main copy loop, 32 bytes are processed per iteration.
- @ ARM instructions are used for doing fine-grained prefetch,
- @ increasing prefetch distance progressively up to
- @ NEON_MAX_PREFETCH_DISTANCE at runtime
-1:
- vld1.8 {d0-d3}, [r1]!
- cmp r3, #(NEON_MAX_PREFETCH_DISTANCE - 32)
- pld [r1, r3]
- addle r3, r3, #32
- vst1.8 {d0-d3}, [ip, :128]!
- sub r2, r2, #32
- cmp r2, r3
- bge 1b
- cmp r2, #0
- blt 3f
-1: @ Copy the remaining part of the buffer (already prefetched)
- vld1.8 {d0-d3}, [r1]!
- subs r2, r2, #32
- vst1.8 {d0-d3}, [ip, :128]!
- bge 1b
-3: @ Copy up to 31 remaining bytes
- tst r2, #16
- beq 4f
- vld1.8 {d0, d1}, [r1]!
- vst1.8 {d0, d1}, [ip, :128]!
-4:
- @ Use ARM instructions exclusively for the final trailing part
- @ not fully fitting into full 16 byte aligned block in order
- @ to avoid "ARM store after NEON store" hazard. Also NEON
- @ pipeline will be (mostly) flushed by the time when the
- @ control returns to the caller, making the use of NEON mostly
- @ transparent (and avoiding hazards in the caller code)
-
- movs r3, r2, lsl #29
- bcc 1f
- .rept 8
- ldrcsb r3, [r1], #1
- strcsb r3, [ip], #1
- .endr
-1:
- bpl 1f
- .rept 4
- ldrmib r3, [r1], #1
- strmib r3, [ip], #1
- .endr
-1:
- movs r2, r2, lsl #31
- ldrcsb r3, [r1], #1
- strcsb r3, [ip], #1
- ldrcsb r3, [r1], #1
- strcsb r3, [ip], #1
- ldrmib r3, [r1], #1
- strmib r3, [ip], #1
- bx lr
- .fnend
-
-#else /* __ARM_ARCH__ < 7 */
-
.text
.global memcpy
@@ -490,5 +385,3 @@
bx lr
.fnend
-#endif
-