aboutsummaryrefslogtreecommitdiff
path: root/gcc
diff options
context:
space:
mode:
authorJuzhe-Zhong <juzhe.zhong@rivai.ai>2023-08-21 09:04:53 +0800
committerLehua Ding <lehua.ding@rivai.ai>2023-08-21 17:18:14 +0800
commitd5dfba19aee783a6ba90fdba1993d576c7ec310b (patch)
treebb57906f94af9990954c78c500a76c02855a7b04 /gcc
parent966b0a96523fb7adbf498ac71df5e033c70dc546 (diff)
downloadgcc-d5dfba19aee783a6ba90fdba1993d576c7ec310b.zip
gcc-d5dfba19aee783a6ba90fdba1993d576c7ec310b.tar.gz
gcc-d5dfba19aee783a6ba90fdba1993d576c7ec310b.tar.bz2
LCM: Export 2 helpful functions as global for VSETVL PASS use in RISC-V backend
This patch exports 'compute_antinout_edge' and 'compute_earliest' as global scope which is going to be used in VSETVL PASS of RISC-V backend. The demand fusion is the fusion of VSETVL information to emit VSETVL which dominate and pre-config for most of the RVV instructions in order to elide redundant VSETVLs. For exmaple: for for for if (cond} VSETVL demand 1: SEW/LMUL = 16 and TU policy else VSETVL demand 2: SEW = 32 VSETVL pass should be able to fuse demand 1 and demand 2 into new demand: SEW = 32, LMUL = M2, TU policy. Then emit such VSETVL at the outmost of the for loop to get the most optimal codegen and run-time execution. Currenty the VSETVL PASS Phase 3 (demand fusion) is really messy and un-reliable as well as un-maintainable. And, I recently read dragon book and morgan's book again, I found there "earliest" can allow us to do the demand fusion in a very reliable and optimal way. So, this patch exports these 2 functions which are very helpful for VSETVL pass. gcc/ChangeLog: * lcm.cc (compute_antinout_edge): Export as global use. (compute_earliest): Ditto. (compute_rev_insert_delete): Ditto. * lcm.h (compute_antinout_edge): Ditto. (compute_earliest): Ditto.
Diffstat (limited to 'gcc')
-rw-r--r--gcc/lcm.cc7
-rw-r--r--gcc/lcm.h3
2 files changed, 5 insertions, 5 deletions
diff --git a/gcc/lcm.cc b/gcc/lcm.cc
index 94a3ed4..03421e4 100644
--- a/gcc/lcm.cc
+++ b/gcc/lcm.cc
@@ -56,9 +56,6 @@ along with GCC; see the file COPYING3. If not see
#include "lcm.h"
/* Edge based LCM routines. */
-static void compute_antinout_edge (sbitmap *, sbitmap *, sbitmap *, sbitmap *);
-static void compute_earliest (struct edge_list *, int, sbitmap *, sbitmap *,
- sbitmap *, sbitmap *, sbitmap *);
static void compute_laterin (struct edge_list *, sbitmap *, sbitmap *,
sbitmap *, sbitmap *);
static void compute_insert_delete (struct edge_list *edge_list, sbitmap *,
@@ -79,7 +76,7 @@ static void compute_rev_insert_delete (struct edge_list *edge_list, sbitmap *,
This is done based on the flow graph, and not on the pred-succ lists.
Other than that, its pretty much identical to compute_antinout. */
-static void
+void
compute_antinout_edge (sbitmap *antloc, sbitmap *transp, sbitmap *antin,
sbitmap *antout)
{
@@ -170,7 +167,7 @@ compute_antinout_edge (sbitmap *antloc, sbitmap *transp, sbitmap *antin,
/* Compute the earliest vector for edge based lcm. */
-static void
+void
compute_earliest (struct edge_list *edge_list, int n_exprs, sbitmap *antin,
sbitmap *antout, sbitmap *avout, sbitmap *kill,
sbitmap *earliest)
diff --git a/gcc/lcm.h b/gcc/lcm.h
index e083393..7145d6f 100644
--- a/gcc/lcm.h
+++ b/gcc/lcm.h
@@ -31,4 +31,7 @@ extern struct edge_list *pre_edge_rev_lcm (int, sbitmap *,
sbitmap *, sbitmap *,
sbitmap *, sbitmap **,
sbitmap **);
+extern void compute_antinout_edge (sbitmap *, sbitmap *, sbitmap *, sbitmap *);
+extern void compute_earliest (struct edge_list *, int, sbitmap *, sbitmap *,
+ sbitmap *, sbitmap *, sbitmap *);
#endif /* GCC_LCM_H */