From: juzhe.zhong@rivai.ai
To: gcc-patches@gcc.gnu.org
Cc: rguenther@suse.de, richard.sandiford@arm.com,
Ju-Zhe Zhong <juzhe.zhong@rivai.ai>
Subject: [PATCH] VECT: Add mask_len_fold_left_plus for in-order floating-point reduction
Date: Sat, 15 Jul 2023 07:45:00 +0800 [thread overview]
Message-ID: <20230714234500.75826-1-juzhe.zhong@rivai.ai> (raw)
From: Ju-Zhe Zhong <juzhe.zhong@rivai.ai>
Hi, Richard and Richi.
This patch adds mask_len_fold_left_plus pattern to support in-order floating-point
reduction for target support len loop control.
Consider this following case:
double
foo2 (double *__restrict a,
double init,
int *__restrict cond,
int n)
{
for (int i = 0; i < n; i++)
if (cond[i])
init += a[i];
return init;
}
ARM SVE:
...
vec_mask_and_60 = loop_mask_54 & mask__23.33_57;
vect__ifc__35.37_64 = .VCOND_MASK (vec_mask_and_60, vect__8.36_61, { 0.0, ... });
_36 = .MASK_FOLD_LEFT_PLUS (init_20, vect__ifc__35.37_64, loop_mask_54);
...
For RVV, we want to see:
...
_36 = .MASK_LEN_FOLD_LEFT_PLUS (init_20, vect__ifc__35.37_64, control_mask, loop_len, bias);
...
gcc/ChangeLog:
* doc/md.texi: Add mask_len_fold_left_plus.
* internal-fn.cc (mask_len_fold_left_direct): Ditto.
(expand_mask_len_fold_left_optab_fn): Ditto.
(direct_mask_len_fold_left_optab_supported_p): Ditto.
* internal-fn.def (MASK_LEN_FOLD_LEFT_PLUS): Ditto.
* optabs.def (OPTAB_D): Ditto.
---
gcc/doc/md.texi | 13 +++++++++++++
gcc/internal-fn.cc | 5 +++++
gcc/internal-fn.def | 3 +++
gcc/optabs.def | 1 +
4 files changed, 22 insertions(+)
diff --git a/gcc/doc/md.texi b/gcc/doc/md.texi
index cbcb992e5d7..6f44e66399d 100644
--- a/gcc/doc/md.texi
+++ b/gcc/doc/md.texi
@@ -5615,6 +5615,19 @@ no reassociation.
Like @samp{fold_left_plus_@var{m}}, but takes an additional mask operand
(operand 3) that specifies which elements of the source vector should be added.
+@cindex @code{mask_len_fold_left_plus_@var{m}} instruction pattern
+@item @code{mask_len_fold_left_plus_@var{m}}
+Like @samp{fold_left_plus_@var{m}}, but takes an additional mask operand
+(operand 3), len operand (operand 4) and bias operand (operand 5) that
+performs following operations strictly in-order (no reassociation):
+
+@smallexample
+operand0 = operand1;
+for (i = 0; i < LEN + BIAS; i++)
+ if (operand3[i])
+ operand0 += operand2[i];
+@end smallexample
+
@cindex @code{sdot_prod@var{m}} instruction pattern
@item @samp{sdot_prod@var{m}}
diff --git a/gcc/internal-fn.cc b/gcc/internal-fn.cc
index e698f0bffc7..2bf4fc492fe 100644
--- a/gcc/internal-fn.cc
+++ b/gcc/internal-fn.cc
@@ -190,6 +190,7 @@ init_internal_fns ()
#define fold_extract_direct { 2, 2, false }
#define fold_left_direct { 1, 1, false }
#define mask_fold_left_direct { 1, 1, false }
+#define mask_len_fold_left_direct { 1, 1, false }
#define check_ptrs_direct { 0, 0, false }
const direct_internal_fn_info direct_internal_fn_array[IFN_LAST + 1] = {
@@ -3890,6 +3891,9 @@ expand_convert_optab_fn (internal_fn fn, gcall *stmt, convert_optab optab,
#define expand_mask_fold_left_optab_fn(FN, STMT, OPTAB) \
expand_direct_optab_fn (FN, STMT, OPTAB, 3)
+#define expand_mask_len_fold_left_optab_fn(FN, STMT, OPTAB) \
+ expand_direct_optab_fn (FN, STMT, OPTAB, 5)
+
#define expand_check_ptrs_optab_fn(FN, STMT, OPTAB) \
expand_direct_optab_fn (FN, STMT, OPTAB, 4)
@@ -3997,6 +4001,7 @@ multi_vector_optab_supported_p (convert_optab optab, tree_pair types,
#define direct_fold_extract_optab_supported_p direct_optab_supported_p
#define direct_fold_left_optab_supported_p direct_optab_supported_p
#define direct_mask_fold_left_optab_supported_p direct_optab_supported_p
+#define direct_mask_len_fold_left_optab_supported_p direct_optab_supported_p
#define direct_check_ptrs_optab_supported_p direct_optab_supported_p
#define direct_vec_set_optab_supported_p direct_optab_supported_p
#define direct_vec_extract_optab_supported_p direct_optab_supported_p
diff --git a/gcc/internal-fn.def b/gcc/internal-fn.def
index ea750a921ed..d3aec51b1f2 100644
--- a/gcc/internal-fn.def
+++ b/gcc/internal-fn.def
@@ -319,6 +319,9 @@ DEF_INTERNAL_OPTAB_FN (FOLD_LEFT_PLUS, ECF_CONST | ECF_NOTHROW,
DEF_INTERNAL_OPTAB_FN (MASK_FOLD_LEFT_PLUS, ECF_CONST | ECF_NOTHROW,
mask_fold_left_plus, mask_fold_left)
+DEF_INTERNAL_OPTAB_FN (MASK_LEN_FOLD_LEFT_PLUS, ECF_CONST | ECF_NOTHROW,
+ mask_len_fold_left_plus, mask_len_fold_left)
+
/* Unary math functions. */
DEF_INTERNAL_FLT_FN (ACOS, ECF_CONST, acos, unary)
DEF_INTERNAL_FLT_FN (ACOSH, ECF_CONST, acosh, unary)
diff --git a/gcc/optabs.def b/gcc/optabs.def
index 3dae228fba6..7023392979e 100644
--- a/gcc/optabs.def
+++ b/gcc/optabs.def
@@ -385,6 +385,7 @@ OPTAB_D (reduc_ior_scal_optab, "reduc_ior_scal_$a")
OPTAB_D (reduc_xor_scal_optab, "reduc_xor_scal_$a")
OPTAB_D (fold_left_plus_optab, "fold_left_plus_$a")
OPTAB_D (mask_fold_left_plus_optab, "mask_fold_left_plus_$a")
+OPTAB_D (mask_len_fold_left_plus_optab, "mask_len_fold_left_plus_$a")
OPTAB_D (extract_last_optab, "extract_last_$a")
OPTAB_D (fold_extract_last_optab, "fold_extract_last_$a")
--
2.36.1
next reply other threads:[~2023-07-14 23:45 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-07-14 23:45 juzhe.zhong [this message]
2023-07-19 8:17 ` Richard Biener
2023-07-19 13:37 ` Li, Pan2
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20230714234500.75826-1-juzhe.zhong@rivai.ai \
--to=juzhe.zhong@rivai.ai \
--cc=gcc-patches@gcc.gnu.org \
--cc=rguenther@suse.de \
--cc=richard.sandiford@arm.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).