For large unaligned block move, lib call may have better performance
than expanding.
Let's just return, if length is
larger than 64 on O32
larger than 128 on N32/N64.
Here are some test results:
CPU Aligned O32 N32 N64
Cavium 7130 1 72 192 192
Cavium 7130 2 96 192 192
Cavium 7130 4 +inf 192 192
Cavium 7130 8 +inf +inf +inf
LS3A 2000 1 32 32 64
LS3A 2000 2 32 64 64
LS3A 2000 4 +inf 32 48
LS3A 2000 8 +inf +inf +inf
LS3A 4000 1 32 64 128
LS3A 4000 2 64 64 128
LS3A 4000 4 192 128 192
LS3A 4000 8 192 +inf +inf
Ingenic X2000 1 96 - -
Ingenic X2000 2 96 - -
Ingenic X2000 4 +inf - -
interAptiv 1 64 - -
interAptiv 2 64 - -
interAptiv 4 +inf - -
P6600 1 64 128 128
P6600 2 64 128 128
P6600 4 256 192 128
P6600 8 +inf +inf +inf
P6600 1U 48 48 48 -mno-unaligned-access
P6600 2U 128 96 96 -mno-unaligned-access
P6600 4U 384 768 768 -mno-unaligned-access
P6600 8U 1024 +inf +inf -mno-unaligned-access
I6500 1 384 896 640
I6500 2 256 768 512
I6500 4 384 704 512
I6500 8 512 1024 1024
I6500 1U 32 32 32 -mno-unaligned-access
I6500 2U 96 64 64 -mno-unaligned-access
I6500 4U 384 640 768 -mno-unaligned-access
I6500 8U 256 +inf +inf -mno-unaligned-access
When the length of block move is larger than this value,
(g)libc call has better performance.
gcc/
* config/mips/mips.cc (mips_expand_block_move): don't expand
large unaligned block move.
gcc/testsuite/
* gcc.target/mips/expand-block-move-large.c: new test.
---
gcc/config/mips/mips.cc | 6 +++++
.../gcc.target/mips/expand-block-move-large.c | 22 +++++++++++++++++++
2 files changed, 28 insertions(+)
create mode 100644 gcc/testsuite/gcc.target/mips/expand-block-move-large.c
diff --git a/gcc/config/mips/mips.cc b/gcc/config/mips/mips.cc
index ca297e3c1e5..7a7f4be627f 100644
--- a/gcc/config/mips/mips.cc
+++ b/gcc/config/mips/mips.cc
@@ -8308,6 +8308,12 @@ mips_expand_block_move (rtx dest, rtx src, rtx length)
|| MEM_ALIGN (dest) < MIPS_MIN_MOVE_MEM_ALIGN))
return false;
+ if ((ISA_HAS_LWL_LWR || ISA_HAS_UNALIGNED_ACCESS)
+ && INTVAL (length) > MIPS_MAX_MOVE_BYTES_STRAIGHT * 2
+ && MEM_ALIGN (src) < BITS_PER_WORD
+ && MEM_ALIGN (dest) < BITS_PER_WORD)
+ return false;
+
if (INTVAL (length) <= MIPS_MAX_MOVE_BYTES_PER_LOOP_ITER)
{
mips_block_move_straight (dest, src, INTVAL (length));
diff --git a/gcc/testsuite/gcc.target/mips/expand-block-move-large.c
b/gcc/testsuite/gcc.target/mips/expand-block-move-large.c
new file mode 100644
index 00000000000..98705f6c560
--- /dev/null
+++ b/gcc/testsuite/gcc.target/mips/expand-block-move-large.c
@@ -0,0 +1,22 @@
+/* { dg-final { scan-assembler "memcpy" } } */
+/* { dg-final { scan-assembler-not "lwl" } } */
+/* { dg-final { scan-assembler-not "swl" } } */
+/* { dg-final { scan-assembler-not "lwr" } } */
+/* { dg-final { scan-assembler-not "swr" } } */
+/* { dg-final { scan-assembler-not "ldl" } } */
+/* { dg-final { scan-assembler-not "sdl" } } */
+/* { dg-final { scan-assembler-not "ldr" } } */
+/* { dg-final { scan-assembler-not "sdr" } } */
+
+char a[4097], b[4097];
+#ifdef __mips64
+#define MAX_SIZE 128
+#else
+#define MAX_SIZE 64
+#endif
+
+NOCOMPRESSION void
+foo ()
+{
+ __builtin_memcpy(&a[1], &b[1], MAX_SIZE + 16);
+}
--
2.30.2
