Hi,
This patch wires up our new target hook for AArch64. This means we can
bring back the two failing SRA tests (churn :( ). For now, I've just used
the old values we had for MOVE_RATIO. We should refactor that, as we use it
in two places (more churn :( ).
Bootstrapped on AArch64 with no issues and benchmarked with no discernible
impact.
OK for trunk?
Thanks,
James
---
gcc/
2014-08-20 James Greenhalgh <james.greenha...@arm.com>
* config/aarch64/aarch64.c
(aarch64_expand_movmem): Refactor old move costs.
(aarch64_default_max_total_scalarization_size): New.
(TARGET_DEFAULT_MAX_TOTAL_SCALARIZATION_SIZE): Likewise.
* config/aarch64/aarch64.h (AARCH64_MOVE_RATIO): New.
(MOVE_RATIO): Use it.
gcc/testsuite/
2014-08-20 James Greenhalgh <james.greenha...@arm.com>
* gcc.dg/tree-ssa/pr42585.c: Bring back for AArch64.
* gcc.dg/tree-ssa/sra-12.c: Likewise.
diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index c3c871e..d608717 100644
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -9725,7 +9725,7 @@ aarch64_expand_movmem (rtx *operands)
/* When optimizing for size, give a better estimate of the length of a
memcpy call, but use the default otherwise. */
- unsigned int max_instructions = (speed_p ? 15 : AARCH64_CALL_RATIO) / 2;
+ unsigned int max_instructions = AARCH64_MOVE_RATIO (speed_p);
/* We can't do anything smart if the amount to copy is not constant. */
if (!CONST_INT_P (operands[2]))
@@ -9826,6 +9826,14 @@ aarch64_expand_movmem (rtx *operands)
return true;
}
+/* Implement TARGET_DEFAULT_MAX_TOTAL_SCALARIZATION_SIZE. */
+
+static unsigned int
+aarch64_default_max_total_scalarization_size (bool size_p)
+{
+ return AARCH64_MOVE_RATIO (!size_p);
+}
+
#undef TARGET_ADDRESS_COST
#define TARGET_ADDRESS_COST aarch64_address_cost
@@ -9949,6 +9957,10 @@ aarch64_expand_movmem (rtx *operands)
#undef TARGET_MANGLE_TYPE
#define TARGET_MANGLE_TYPE aarch64_mangle_type
+#undef TARGET_DEFAULT_MAX_TOTAL_SCALARIZATION_SIZE
+#define TARGET_DEFAULT_MAX_TOTAL_SCALARIZATION_SIZE \
+ aarch64_default_max_total_scalarization_size
+
#undef TARGET_MEMORY_MOVE_COST
#define TARGET_MEMORY_MOVE_COST aarch64_memory_move_cost
diff --git a/gcc/config/aarch64/aarch64.h b/gcc/config/aarch64/aarch64.h
index db950da..5401061 100644
--- a/gcc/config/aarch64/aarch64.h
+++ b/gcc/config/aarch64/aarch64.h
@@ -681,6 +681,8 @@ do { \
/* The base cost overhead of a memcpy call, for MOVE_RATIO and friends. */
#define AARCH64_CALL_RATIO 8
+#define AARCH64_MOVE_RATIO(speed) (((speed) ? 15 : AARCH64_CALL_RATIO) / 2)
+
/* MOVE_RATIO dictates when we will use the move_by_pieces infrastructure.
move_by_pieces will continually copy the largest safe chunks. So a
7-byte copy is a 4-byte + 2-byte + byte copy. This proves inefficient
@@ -688,7 +690,7 @@ do { \
standard name to implement the copy. This logic does not apply when
targeting -mstrict-align, so keep a sensible default in that case. */
#define MOVE_RATIO(speed) \
- (!STRICT_ALIGNMENT ? 2 : (((speed) ? 15 : AARCH64_CALL_RATIO) / 2))
+ (!STRICT_ALIGNMENT ? 2 : AARCH64_MOVE_RATIO (speed))
/* For CLEAR_RATIO, when optimizing for size, give a better estimate
of the length of a memset call, but use the default otherwise. */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr42585.c b/gcc/testsuite/gcc.dg/tree-ssa/pr42585.c
index 07f575d..a970c85 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/pr42585.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr42585.c
@@ -35,6 +35,6 @@ Cyc_string_ungetc (int ignore, struct _fat_ptr *sptr)
/* Whether the structs are totally scalarized or not depends on the
MOVE_RATIO macro definition in the back end. The scalarization will
not take place when using small values for MOVE_RATIO. */
-/* { dg-final { scan-tree-dump-times "struct _fat_ptr _ans" 0 "optimized" { target { ! "aarch64*-*-* arm*-*-* avr-*-* nds32*-*-* powerpc*-*-* s390*-*-* sh*-*-*" } } } } */
-/* { dg-final { scan-tree-dump-times "struct _fat_ptr _T2" 0 "optimized" { target { ! "aarch64*-*-* arm*-*-* avr-*-* nds32*-*-* powerpc*-*-* s390*-*-* sh*-*-*" } } } } */
+/* { dg-final { scan-tree-dump-times "struct _fat_ptr _ans" 0 "optimized" { target { ! "arm*-*-* avr-*-* nds32*-*-* powerpc*-*-* s390*-*-* sh*-*-*" } } } } */
+/* { dg-final { scan-tree-dump-times "struct _fat_ptr _T2" 0 "optimized" { target { ! "arm*-*-* avr-*-* nds32*-*-* powerpc*-*-* s390*-*-* sh*-*-*" } } } } */
/* { dg-final { cleanup-tree-dump "optimized" } } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/sra-12.c b/gcc/testsuite/gcc.dg/tree-ssa/sra-12.c
index 45aa963..59e5e6a 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/sra-12.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/sra-12.c
@@ -21,5 +21,5 @@ int foo (struct S *p)
*p = l;
}
-/* { dg-final { scan-tree-dump-times "l;" 0 "release_ssa" { target { ! "aarch64*-*-* avr*-*-* nds32*-*-*" } } } } */
+/* { dg-final { scan-tree-dump-times "l;" 0 "release_ssa" { target { ! "avr*-*-* nds32*-*-*" } } } } */
/* { dg-final { cleanup-tree-dump "release_ssa" } } */
