Hi,
Add support for fused compare with branch. Rename the existing
AARCH64_FUSE_CMP_BRANCH to ALU_BRANCH, and AARCH64_FUSE_ALU_BRANCH
to ALU_CBZ to make it clear what is being fused.
AArch64 bootstrap OK, OK to commit?
ChangeLog:
2019-11-29 Wilco Dijkstra <wdijk...@arm.com>
* config/aarch64/aarch64.c
(thunderxt88_tunings): Use AARCH64_FUSE_ALU_BRANCH.
(thunderx_tunings): Likewise.
(tsv110_tunings): Use AARCH64_FUSE_ALU_BRANCH and AARCH64_FUSE_ALU_CBZ.
(thunderx2t99_tunings): Likewise.
(aarch_macro_fusion_pair_p): Add support for AARCH64_FUSE_CMP_BRANCH.
* config/aarch64/aarch64-fusion-pairs.def: Add ALU_CBZ fusion.
--
diff --git a/gcc/config/aarch64/aarch64-fusion-pairs.def
b/gcc/config/aarch64/aarch64-fusion-pairs.def
index
ce4bb92d5c9d1f187c026b1a714e485a2b9f1a74..051009b42b2db4e79a8b302fd3f1b65dedfdba8f
100644
--- a/gcc/config/aarch64/aarch64-fusion-pairs.def
+++ b/gcc/config/aarch64/aarch64-fusion-pairs.def
@@ -35,5 +35,6 @@ AARCH64_FUSION_PAIR ("adrp+ldr", ADRP_LDR)
AARCH64_FUSION_PAIR ("cmp+branch", CMP_BRANCH)
AARCH64_FUSION_PAIR ("aes+aesmc", AES_AESMC)
AARCH64_FUSION_PAIR ("alu+branch", ALU_BRANCH)
+AARCH64_FUSION_PAIR ("alu+cbz", ALU_CBZ)
#undef AARCH64_FUSION_PAIR
diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index
94e664af52fb0e3404e76d4d0b67a618023571ba..f74134ea2e080c361be0facc274575c09fbb7a82
100644
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -915,7 +915,7 @@ static const struct tune_params thunderxt88_tunings =
SVE_NOT_IMPLEMENTED, /* sve_width */
6, /* memmov_cost */
2, /* issue_rate */
- AARCH64_FUSE_CMP_BRANCH, /* fusible_ops */
+ AARCH64_FUSE_ALU_BRANCH, /* fusible_ops */
"8", /* function_align. */
"8", /* jump_align. */
"8", /* loop_align. */
@@ -941,7 +941,7 @@ static const struct tune_params thunderx_tunings =
SVE_NOT_IMPLEMENTED, /* sve_width */
6, /* memmov_cost */
2, /* issue_rate */
- AARCH64_FUSE_CMP_BRANCH, /* fusible_ops */
+ AARCH64_FUSE_ALU_BRANCH, /* fusible_ops */
"8", /* function_align. */
"8", /* jump_align. */
"8", /* loop_align. */
@@ -968,8 +968,8 @@ static const struct tune_params tsv110_tunings =
SVE_NOT_IMPLEMENTED, /* sve_width */
4, /* memmov_cost */
4, /* issue_rate */
- (AARCH64_FUSE_AES_AESMC | AARCH64_FUSE_CMP_BRANCH
- | AARCH64_FUSE_ALU_BRANCH), /* fusible_ops */
+ (AARCH64_FUSE_AES_AESMC | AARCH64_FUSE_ALU_BRANCH
+ | AARCH64_FUSE_ALU_CBZ), /* fusible_ops */
"16", /* function_align. */
"4", /* jump_align. */
"8", /* loop_align. */
@@ -1103,8 +1103,8 @@ static const struct tune_params thunderx2t99_tunings =
SVE_NOT_IMPLEMENTED, /* sve_width */
4, /* memmov_cost. */
4, /* issue_rate. */
- (AARCH64_FUSE_CMP_BRANCH | AARCH64_FUSE_AES_AESMC
- | AARCH64_FUSE_ALU_BRANCH), /* fusible_ops */
+ (AARCH64_FUSE_ALU_BRANCH | AARCH64_FUSE_AES_AESMC
+ | AARCH64_FUSE_ALU_CBZ), /* fusible_ops */
"16", /* function_align. */
"8", /* jump_align. */
"16", /* loop_align. */
@@ -20363,7 +20363,14 @@ aarch_macro_fusion_pair_p (rtx_insn *prev, rtx_insn
*curr)
}
}
+ /* Fuse compare (CMP/CMN/TST/BICS) and conditional branch. */
if (aarch64_fusion_enabled_p (AARCH64_FUSE_CMP_BRANCH)
+ && prev_set && curr_set && any_condjump_p (curr)
+ && reg_referenced_p (SET_DEST (curr_set), PATTERN (curr)))
+ return true;
+
+ /* Fuse flag-setting ALU instructions and conditional branch. */
+ if (aarch64_fusion_enabled_p (AARCH64_FUSE_ALU_BRANCH)
&& any_condjump_p (curr))
{
unsigned int condreg1, condreg2;
@@ -20387,9 +20394,10 @@ aarch_macro_fusion_pair_p (rtx_insn *prev, rtx_insn
*curr)
}
}
+ /* Fuse ALU instructions and CBZ/CBNZ. */
if (prev_set
&& curr_set
- && aarch64_fusion_enabled_p (AARCH64_FUSE_ALU_BRANCH)
+ && aarch64_fusion_enabled_p (AARCH64_FUSE_ALU_CBZ)
&& any_condjump_p (curr))
{
/* We're trying to match:
