[sending on behalf of Jackson Woodruff]
Hi all,
This patch removes a lot of duplicated code in aarch64-ldpstp.md.
The patterns that did not previously generate a base register now
do not check for aarch64_mem_pair_operand in the pattern. This has
been extracted to a check in aarch64_operands_ok_for_ldpstp.
All patterns in the file used to have explicit switching code to
swap loads and stores that were in the wrong order.
This has been extracted into aarch64_operands_ok_for_ldpstp
as a final operation after all the checks have been performed.
This patch is based on the patch here:
https://gcc.gnu.org/ml/gcc-patches/2018-05/msg01129.html
Bootstrap and regtest OK on AArch64.
OK for trunk?
Jackson.
gcc/
2018-05-22 Jackson Woodruff <jackson.woodr...@arm.com>
Kyrylo Tkachov <kyrylo.tkac...@arm.com>
* config/aarch64/aarch64-ldpstp.md: Replace uses of
aarch64_mem_pair_operand with memory_operand and delete operand swapping
code.
* config/aarch64/aarch64.c (aarch64_operands_ok_for_ldpstp):
Add check for legitimate_address.
(aarch64_gen_adjusted_ldpstp): Swap operands where appropriate.
(aarch64_swap_ldrstr_operands): New.
* config/aarch64/aarch64-protos.h (aarch64_swap_ldrstr_operands):
Define prototype.
diff --git a/gcc/config/aarch64/aarch64-ldpstp.md b/gcc/config/aarch64/aarch64-ldpstp.md
index f6fe8a6a93b5466723e3ed6b892e0ec1e67ee89d..7f1031dc80fab31f691c0b03d6a485c1b6fd7e53 100644
--- a/gcc/config/aarch64/aarch64-ldpstp.md
+++ b/gcc/config/aarch64/aarch64-ldpstp.md
@@ -20,26 +20,18 @@
(define_peephole2
[(set (match_operand:GPI 0 "register_operand" "")
- (match_operand:GPI 1 "aarch64_mem_pair_operand" ""))
+ (match_operand:GPI 1 "memory_operand" ""))
(set (match_operand:GPI 2 "register_operand" "")
(match_operand:GPI 3 "memory_operand" ""))]
"aarch64_operands_ok_for_ldpstp (operands, true, <MODE>mode)"
[(parallel [(set (match_dup 0) (match_dup 1))
(set (match_dup 2) (match_dup 3))])]
{
- rtx base, offset_1, offset_2;
-
- extract_base_offset_in_addr (operands[1], &base, &offset_1);
- extract_base_offset_in_addr (operands[3], &base, &offset_2);
- if (INTVAL (offset_1) > INTVAL (offset_2))
- {
- std::swap (operands[0], operands[2]);
- std::swap (operands[1], operands[3]);
- }
+ aarch64_swap_ldrstr_operands (operands, true);
})
(define_peephole2
- [(set (match_operand:GPI 0 "aarch64_mem_pair_operand" "")
+ [(set (match_operand:GPI 0 "memory_operand" "")
(match_operand:GPI 1 "aarch64_reg_or_zero" ""))
(set (match_operand:GPI 2 "memory_operand" "")
(match_operand:GPI 3 "aarch64_reg_or_zero" ""))]
@@ -47,39 +39,23 @@ (define_peephole2
[(parallel [(set (match_dup 0) (match_dup 1))
(set (match_dup 2) (match_dup 3))])]
{
- rtx base, offset_1, offset_2;
-
- extract_base_offset_in_addr (operands[0], &base, &offset_1);
- extract_base_offset_in_addr (operands[2], &base, &offset_2);
- if (INTVAL (offset_1) > INTVAL (offset_2))
- {
- std::swap (operands[0], operands[2]);
- std::swap (operands[1], operands[3]);
- }
+ aarch64_swap_ldrstr_operands (operands, false);
})
(define_peephole2
[(set (match_operand:GPF 0 "register_operand" "")
- (match_operand:GPF 1 "aarch64_mem_pair_operand" ""))
+ (match_operand:GPF 1 "memory_operand" ""))
(set (match_operand:GPF 2 "register_operand" "")
(match_operand:GPF 3 "memory_operand" ""))]
"aarch64_operands_ok_for_ldpstp (operands, true, <MODE>mode)"
[(parallel [(set (match_dup 0) (match_dup 1))
(set (match_dup 2) (match_dup 3))])]
{
- rtx base, offset_1, offset_2;
-
- extract_base_offset_in_addr (operands[1], &base, &offset_1);
- extract_base_offset_in_addr (operands[3], &base, &offset_2);
- if (INTVAL (offset_1) > INTVAL (offset_2))
- {
- std::swap (operands[0], operands[2]);
- std::swap (operands[1], operands[3]);
- }
+ aarch64_swap_ldrstr_operands (operands, true);
})
(define_peephole2
- [(set (match_operand:GPF 0 "aarch64_mem_pair_operand" "")
+ [(set (match_operand:GPF 0 "memory_operand" "")
(match_operand:GPF 1 "aarch64_reg_or_fp_zero" ""))
(set (match_operand:GPF 2 "memory_operand" "")
(match_operand:GPF 3 "aarch64_reg_or_fp_zero" ""))]
@@ -87,39 +63,23 @@ (define_peephole2
[(parallel [(set (match_dup 0) (match_dup 1))
(set (match_dup 2) (match_dup 3))])]
{
- rtx base, offset_1, offset_2;
-
- extract_base_offset_in_addr (operands[0], &base, &offset_1);
- extract_base_offset_in_addr (operands[2], &base, &offset_2);
- if (INTVAL (offset_1) > INTVAL (offset_2))
- {
- std::swap (operands[0], operands[2]);
- std::swap (operands[1], operands[3]);
- }
+ aarch64_swap_ldrstr_operands (operands, false);
})
(define_peephole2
[(set (match_operand:DREG 0 "register_operand" "")
- (match_operand:DREG 1 "aarch64_mem_pair_operand" ""))
+ (match_operand:DREG 1 "memory_operand" ""))
(set (match_operand:DREG2 2 "register_operand" "")
(match_operand:DREG2 3 "memory_operand" ""))]
"aarch64_operands_ok_for_ldpstp (operands, true, <DREG:MODE>mode)"
[(parallel [(set (match_dup 0) (match_dup 1))
(set (match_dup 2) (match_dup 3))])]
{
- rtx base, offset_1, offset_2;
-
- extract_base_offset_in_addr (operands[1], &base, &offset_1);
- extract_base_offset_in_addr (operands[3], &base, &offset_2);
- if (INTVAL (offset_1) > INTVAL (offset_2))
- {
- std::swap (operands[0], operands[2]);
- std::swap (operands[1], operands[3]);
- }
+ aarch64_swap_ldrstr_operands (operands, true);
})
(define_peephole2
- [(set (match_operand:DREG 0 "aarch64_mem_pair_operand" "")
+ [(set (match_operand:DREG 0 "memory_operand" "")
(match_operand:DREG 1 "register_operand" ""))
(set (match_operand:DREG2 2 "memory_operand" "")
(match_operand:DREG2 3 "register_operand" ""))]
@@ -128,57 +88,33 @@ (define_peephole2
[(parallel [(set (match_dup 0) (match_dup 1))
(set (match_dup 2) (match_dup 3))])]
{
- rtx base, offset_1, offset_2;
-
- extract_base_offset_in_addr (operands[0], &base, &offset_1);
- extract_base_offset_in_addr (operands[2], &base, &offset_2);
- if (INTVAL (offset_1) > INTVAL (offset_2))
- {
- std::swap (operands[0], operands[2]);
- std::swap (operands[1], operands[3]);
- }
+ aarch64_swap_ldrstr_operands (operands, false);
})
;; Handle sign/zero extended consecutive load/store.
(define_peephole2
[(set (match_operand:DI 0 "register_operand" "")
- (sign_extend:DI (match_operand:SI 1 "aarch64_mem_pair_operand" "")))
+ (sign_extend:DI (match_operand:SI 1 "memory_operand" "")))
(set (match_operand:DI 2 "register_operand" "")
(sign_extend:DI (match_operand:SI 3 "memory_operand" "")))]
"aarch64_operands_ok_for_ldpstp (operands, true, SImode)"
[(parallel [(set (match_dup 0) (sign_extend:DI (match_dup 1)))
(set (match_dup 2) (sign_extend:DI (match_dup 3)))])]
{
- rtx base, offset_1, offset_2;
-
- extract_base_offset_in_addr (operands[1], &base, &offset_1);
- extract_base_offset_in_addr (operands[3], &base, &offset_2);
- if (INTVAL (offset_1) > INTVAL (offset_2))
- {
- std::swap (operands[0], operands[2]);
- std::swap (operands[1], operands[3]);
- }
+ aarch64_swap_ldrstr_operands (operands, true);
})
(define_peephole2
[(set (match_operand:DI 0 "register_operand" "")
- (zero_extend:DI (match_operand:SI 1 "aarch64_mem_pair_operand" "")))
+ (zero_extend:DI (match_operand:SI 1 "memory_operand" "")))
(set (match_operand:DI 2 "register_operand" "")
(zero_extend:DI (match_operand:SI 3 "memory_operand" "")))]
"aarch64_operands_ok_for_ldpstp (operands, true, SImode)"
[(parallel [(set (match_dup 0) (zero_extend:DI (match_dup 1)))
(set (match_dup 2) (zero_extend:DI (match_dup 3)))])]
{
- rtx base, offset_1, offset_2;
-
- extract_base_offset_in_addr (operands[1], &base, &offset_1);
- extract_base_offset_in_addr (operands[3], &base, &offset_2);
- if (INTVAL (offset_1) > INTVAL (offset_2))
- {
- std::swap (operands[0], operands[2]);
- std::swap (operands[1], operands[3]);
- }
+ aarch64_swap_ldrstr_operands (operands, true);
})
;; Handle storing of a floating point zero with integer data.
@@ -192,7 +128,7 @@ (define_peephole2
;; as aarch64_operands_ok_for_ldpstp checks that the modes are
;; compatible.
(define_peephole2
- [(set (match_operand:DSX 0 "aarch64_mem_pair_operand" "")
+ [(set (match_operand:DSX 0 "memory_operand" "")
(match_operand:DSX 1 "aarch64_reg_zero_or_fp_zero" ""))
(set (match_operand:<FCVT_TARGET> 2 "memory_operand" "")
(match_operand:<FCVT_TARGET> 3 "aarch64_reg_zero_or_fp_zero" ""))]
@@ -200,15 +136,7 @@ (define_peephole2
[(parallel [(set (match_dup 0) (match_dup 1))
(set (match_dup 2) (match_dup 3))])]
{
- rtx base, offset_1, offset_2;
-
- extract_base_offset_in_addr (operands[0], &base, &offset_1);
- extract_base_offset_in_addr (operands[2], &base, &offset_2);
- if (INTVAL (offset_1) > INTVAL (offset_2))
- {
- std::swap (operands[0], operands[2]);
- std::swap (operands[1], operands[3]);
- }
+ aarch64_swap_ldrstr_operands (operands, false);
})
;; Handle consecutive load/store whose offset is out of the range
@@ -230,18 +158,6 @@ (define_peephole2
"aarch64_operands_adjust_ok_for_ldpstp (operands, true, <MODE>mode)"
[(const_int 0)]
{
- rtx base, offset_1, offset_2;
-
- extract_base_offset_in_addr (operands[1], &base, &offset_1);
- extract_base_offset_in_addr (operands[3], &base, &offset_2);
- if (INTVAL (offset_1) > INTVAL (offset_2))
- {
- std::swap (operands[0], operands[6]);
- std::swap (operands[1], operands[7]);
- std::swap (operands[2], operands[4]);
- std::swap (operands[3], operands[5]);
- }
-
if (aarch64_gen_adjusted_ldpstp (operands, true, <MODE>mode, UNKNOWN))
DONE;
else
@@ -262,18 +178,6 @@ (define_peephole2
"aarch64_operands_adjust_ok_for_ldpstp (operands, true, <MODE>mode)"
[(const_int 0)]
{
- rtx base, offset_1, offset_2;
-
- extract_base_offset_in_addr (operands[1], &base, &offset_1);
- extract_base_offset_in_addr (operands[3], &base, &offset_2);
- if (INTVAL (offset_1) > INTVAL (offset_2))
- {
- std::swap (operands[0], operands[6]);
- std::swap (operands[1], operands[7]);
- std::swap (operands[2], operands[4]);
- std::swap (operands[3], operands[5]);
- }
-
if (aarch64_gen_adjusted_ldpstp (operands, true, <MODE>mode, UNKNOWN))
DONE;
else
@@ -294,18 +198,6 @@ (define_peephole2
"aarch64_operands_adjust_ok_for_ldpstp (operands, true, SImode)"
[(const_int 0)]
{
- rtx base, offset_1, offset_2;
-
- extract_base_offset_in_addr (operands[1], &base, &offset_1);
- extract_base_offset_in_addr (operands[3], &base, &offset_2);
- if (INTVAL (offset_1) > INTVAL (offset_2))
- {
- std::swap (operands[0], operands[6]);
- std::swap (operands[1], operands[7]);
- std::swap (operands[2], operands[4]);
- std::swap (operands[3], operands[5]);
- }
-
if (aarch64_gen_adjusted_ldpstp (operands, true, SImode, SIGN_EXTEND))
DONE;
else
@@ -326,18 +218,6 @@ (define_peephole2
"aarch64_operands_adjust_ok_for_ldpstp (operands, true, SImode)"
[(const_int 0)]
{
- rtx base, offset_1, offset_2;
-
- extract_base_offset_in_addr (operands[1], &base, &offset_1);
- extract_base_offset_in_addr (operands[3], &base, &offset_2);
- if (INTVAL (offset_1) > INTVAL (offset_2))
- {
- std::swap (operands[0], operands[6]);
- std::swap (operands[1], operands[7]);
- std::swap (operands[2], operands[4]);
- std::swap (operands[3], operands[5]);
- }
-
if (aarch64_gen_adjusted_ldpstp (operands, true, SImode, ZERO_EXTEND))
DONE;
else
@@ -358,18 +238,6 @@ (define_peephole2
"aarch64_operands_adjust_ok_for_ldpstp (operands, false, <MODE>mode)"
[(const_int 0)]
{
- rtx base, offset_1, offset_2;
-
- extract_base_offset_in_addr (operands[0], &base, &offset_1);
- extract_base_offset_in_addr (operands[2], &base, &offset_2);
- if (INTVAL (offset_1) > INTVAL (offset_2))
- {
- std::swap (operands[0], operands[6]);
- std::swap (operands[1], operands[7]);
- std::swap (operands[2], operands[4]);
- std::swap (operands[3], operands[5]);
- }
-
if (aarch64_gen_adjusted_ldpstp (operands, false, <MODE>mode, UNKNOWN))
DONE;
else
@@ -390,18 +258,6 @@ (define_peephole2
"aarch64_operands_adjust_ok_for_ldpstp (operands, false, <MODE>mode)"
[(const_int 0)]
{
- rtx base, offset_1, offset_2;
-
- extract_base_offset_in_addr (operands[0], &base, &offset_1);
- extract_base_offset_in_addr (operands[2], &base, &offset_2);
- if (INTVAL (offset_1) > INTVAL (offset_2))
- {
- std::swap (operands[0], operands[6]);
- std::swap (operands[1], operands[7]);
- std::swap (operands[2], operands[4]);
- std::swap (operands[3], operands[5]);
- }
-
if (aarch64_gen_adjusted_ldpstp (operands, false, <MODE>mode, UNKNOWN))
DONE;
else
diff --git a/gcc/config/aarch64/aarch64-protos.h b/gcc/config/aarch64/aarch64-protos.h
index cda2895d28e7496f8fd6c1b365c4bb497b54c323..4ab68110eb4602939582fa4498cca686468bebb6 100644
--- a/gcc/config/aarch64/aarch64-protos.h
+++ b/gcc/config/aarch64/aarch64-protos.h
@@ -534,6 +534,7 @@ int aarch64_ccmp_mode_to_code (machine_mode mode);
bool extract_base_offset_in_addr (rtx mem, rtx *base, rtx *offset);
bool aarch64_operands_ok_for_ldpstp (rtx *, bool, machine_mode);
bool aarch64_operands_adjust_ok_for_ldpstp (rtx *, bool, scalar_mode);
+void aarch64_swap_ldrstr_operands (rtx *, bool);
extern void aarch64_asm_output_pool_epilogue (FILE *, const char *,
tree, HOST_WIDE_INT);
diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index b75a588eb9aa49b1796161d34494d452a6742e4d..f60e0ad37565b044b3ffe446eebcc0f40f9d99db 100644
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -16874,9 +16874,16 @@ aarch64_operands_ok_for_ldpstp (rtx *operands, bool load,
/* In increasing order, the last load can clobber the address. */
if (offval_1 > offval_2 && reg_mentioned_p (reg_2, mem_2))
- return false;
+ return false;
}
+ /* One of the memory accesses must be a mempair operand.
+ If it is not the first one, they need to be swapped by the
+ peephole. */
+ if (!aarch64_mem_pair_operand (mem_1, GET_MODE (mem_1))
+ && !aarch64_mem_pair_operand (mem_2, GET_MODE (mem_2)))
+ return false;
+
if (REG_P (reg_1) && FP_REGNUM_P (REGNO (reg_1)))
rclass_1 = FP_REGS;
else
@@ -16894,6 +16901,40 @@ aarch64_operands_ok_for_ldpstp (rtx *operands, bool load,
return true;
}
+/* Given OPERANDS of consecutive load/store that can be merged,
+ swap them if they are not in ascending order. */
+void
+aarch64_swap_ldrstr_operands (rtx* operands, bool load)
+{
+ rtx mem_1, mem_2, base_1, base_2, offset_1, offset_2;
+ HOST_WIDE_INT offval_1, offval_2;
+
+ if (load)
+ {
+ mem_1 = operands[1];
+ mem_2 = operands[3];
+ }
+ else
+ {
+ mem_1 = operands[0];
+ mem_2 = operands[2];
+ }
+
+ extract_base_offset_in_addr (mem_1, &base_1, &offset_1);
+ extract_base_offset_in_addr (mem_2, &base_2, &offset_2);
+
+ offval_1 = INTVAL (offset_1);
+ offval_2 = INTVAL (offset_2);
+
+ if (offval_1 > offval_2)
+ {
+ /* Irrespective of whether this is a load or a store,
+ we do the same swap. */
+ std::swap (operands[0], operands[2]);
+ std::swap (operands[1], operands[3]);
+ }
+}
+
/* Given OPERANDS of consecutive load/store, check if we can merge
them into ldp/stp by adjusting the offset. LOAD is true if they
are load instructions. MODE is the mode of memory operands.
@@ -17053,7 +17094,7 @@ bool
aarch64_gen_adjusted_ldpstp (rtx *operands, bool load,
scalar_mode mode, RTX_CODE code)
{
- rtx base, offset, t1, t2;
+ rtx base, offset_1, offset_2, t1, t2;
rtx mem_1, mem_2, mem_3, mem_4;
HOST_WIDE_INT off_val, abs_off, adj_off, new_off, stp_off_limit, msize;
@@ -17061,6 +17102,30 @@ aarch64_gen_adjusted_ldpstp (rtx *operands, bool load,
{
mem_1 = operands[1];
mem_2 = operands[3];
+ }
+ else
+ {
+ mem_1 = operands[0];
+ mem_2 = operands[2];
+ }
+
+ extract_base_offset_in_addr (mem_1, &base, &offset_1);
+ extract_base_offset_in_addr (mem_2, &base, &offset_2);
+ gcc_assert (base != NULL_RTX && offset_1 != NULL_RTX
+ && offset_2 != NULL_RTX);
+
+ if (INTVAL (offset_1) > INTVAL (offset_2))
+ {
+ std::swap (operands[0], operands[6]);
+ std::swap (operands[1], operands[7]);
+ std::swap (operands[2], operands[4]);
+ std::swap (operands[3], operands[5]);
+ }
+
+ if (load)
+ {
+ mem_1 = operands[1];
+ mem_2 = operands[3];
mem_3 = operands[5];
mem_4 = operands[7];
}
@@ -17073,13 +17138,14 @@ aarch64_gen_adjusted_ldpstp (rtx *operands, bool load,
gcc_assert (code == UNKNOWN);
}
- extract_base_offset_in_addr (mem_1, &base, &offset);
- gcc_assert (base != NULL_RTX && offset != NULL_RTX);
+ /* Extract the offset of the new first address. */
+ extract_base_offset_in_addr (mem_1, &base, &offset_1);
+ extract_base_offset_in_addr (mem_2, &base, &offset_2);
/* Adjust offset thus it can fit in ldp/stp instruction. */
msize = GET_MODE_SIZE (mode);
stp_off_limit = msize * 0x40;
- off_val = INTVAL (offset);
+ off_val = INTVAL (offset_1);
abs_off = (off_val < 0) ? -off_val : off_val;
new_off = abs_off % stp_off_limit;
adj_off = abs_off - new_off;
