From: Takayuki 'January June' Suwa <jjsuwa_sys3175@yahoo.co.jp>
To: GCC Patches <gcc-patches@gcc.gnu.org>
Subject: [PATCH 4/4] xtensa: Optimize bitwise AND operation with some specific forms of constants
Date: Sun, 12 Jun 2022 15:41:56 +0900 [thread overview]
Message-ID: <fbe8f1b2-1b4c-1e2f-4197-3c4a0407e971@yahoo.co.jp> (raw)
This patch offers several insn-and-split patterns for bitwise AND with
register and constant that cannot fit into a "MOVI Ax, simm12" instruction,
but can be represented as:
i. 1's least significant N bits and the others 0's (17 <= N <= 31)
ii. 1's most significant N bits and the others 0's (12 <= N <= 31)
iii. M 1's sequence of bits and trailing N 0's bits
(1 <= M <= 16, 1 <= N <= 30)
And also offers shortcuts for conditional branch if each of the
abovementioned
operations is (not) equal to zero.
gcc/ChangeLog:
* config/xtensa/predicates.md (shifted_mask_operand):
New predicate.
* config/xtensa/xtensa.md (*andsi3_const_pow2_minus_one):
New insn-and-split pattern.
(*andsi3_const_negative_pow2, *andsi3_const_shifted_mask,
*masktrue_const_pow2_minus_one, *masktrue_const_negative_pow2,
*masktrue_const_shifted_mask): Ditto.
---
gcc/config/xtensa/predicates.md | 11 +++
gcc/config/xtensa/xtensa.md | 165 ++++++++++++++++++++++++++++++++
2 files changed, 176 insertions(+)
diff --git a/gcc/config/xtensa/predicates.md
b/gcc/config/xtensa/predicates.md
index bcc83ada0ae..24c77f343a0 100644
--- a/gcc/config/xtensa/predicates.md
+++ b/gcc/config/xtensa/predicates.md
@@ -52,6 +52,17 @@
(match_test "xtensa_mask_immediate (INTVAL (op))"))
(match_operand 0 "register_operand")))
+(define_predicate "shifted_mask_operand"
+ (and (match_code "const_int")
+ (match_test "!xtensa_simm12b (INTVAL (op))"))
+{
+ HOST_WIDE_INT mask = INTVAL (op);
+ int shift = ctz_hwi (mask);
+
+ return IN_RANGE (shift, 1, 31)
+ && xtensa_mask_immediate ((uint32_t)mask >> shift);
+})
+
(define_predicate "extui_fldsz_operand"
(and (match_code "const_int")
(match_test "IN_RANGE (INTVAL (op), 1, 16)")))
diff --git a/gcc/config/xtensa/xtensa.md b/gcc/config/xtensa/xtensa.md
index 090a2939684..286a1d8c38e 100644
--- a/gcc/config/xtensa/xtensa.md
+++ b/gcc/config/xtensa/xtensa.md
@@ -645,6 +645,78 @@
(set_attr "mode" "SI")
(set_attr "length" "6")])
+(define_insn_and_split "*andsi3_const_pow2_minus_one"
+ [(set (match_operand:SI 0 "register_operand" "=a")
+ (and:SI (match_operand:SI 1 "register_operand" "r")
+ (match_operand:SI 2 "const_int_operand" "i")))]
+ "IN_RANGE (exact_log2 (INTVAL (operands[2]) + 1), 17, 31)"
+ "#"
+ "&& 1"
+ [(set (match_dup 0)
+ (ashift:SI (match_dup 1)
+ (match_dup 2)))
+ (set (match_dup 0)
+ (lshiftrt:SI (match_dup 0)
+ (match_dup 2)))]
+{
+ operands[2] = GEN_INT (32 - floor_log2 (INTVAL (operands[2]) + 1));
+}
+ [(set_attr "type" "arith")
+ (set_attr "mode" "SI")
+ (set (attr "length")
+ (if_then_else (match_test "TARGET_DENSITY
+ && INTVAL (operands[2]) == 0x7FFFFFFF")
+ (const_int 5)
+ (const_int 6)))])
+
+(define_insn_and_split "*andsi3_const_negative_pow2"
+ [(set (match_operand:SI 0 "register_operand" "=a")
+ (and:SI (match_operand:SI 1 "register_operand" "r")
+ (match_operand:SI 2 "const_int_operand" "i")))]
+ "IN_RANGE (exact_log2 (-INTVAL (operands[2])), 12, 31)"
+ "#"
+ "&& 1"
+ [(set (match_dup 0)
+ (lshiftrt:SI (match_dup 1)
+ (match_dup 2)))
+ (set (match_dup 0)
+ (ashift:SI (match_dup 0)
+ (match_dup 2)))]
+{
+ operands[2] = GEN_INT (floor_log2 (-INTVAL (operands[2])));
+}
+ [(set_attr "type" "arith")
+ (set_attr "mode" "SI")
+ (set_attr "length" "6")])
+
+(define_insn_and_split "*andsi3_const_shifted_mask"
+ [(set (match_operand:SI 0 "register_operand" "=a")
+ (and:SI (match_operand:SI 1 "register_operand" "r")
+ (match_operand:SI 2 "shifted_mask_operand" "i")))]
+ ""
+ "#"
+ ""
+ [(set (match_dup 0)
+ (zero_extract:SI (match_dup 1)
+ (match_dup 3)
+ (match_dup 2)))
+ (set (match_dup 0)
+ (ashift:SI (match_dup 0)
+ (match_dup 2)))]
+{
+ HOST_WIDE_INT mask = INTVAL (operands[2]);
+ int shift = ctz_hwi (mask);
+ operands[2] = GEN_INT (shift);
+ operands[3] = GEN_INT (floor_log2 (((uint32_t)mask >> shift) + 1));
+}
+ [(set_attr "type" "arith")
+ (set_attr "mode" "SI")
+ (set (attr "length")
+ (if_then_else (match_test "TARGET_DENSITY
+ && ctz_hwi (INTVAL (operands[2])) == 1")
+ (const_int 5)
+ (const_int 6)))])
+
(define_insn "iorsi3"
[(set (match_operand:SI 0 "register_operand" "=a")
(ior:SI (match_operand:SI 1 "register_operand" "%r")
@@ -1648,6 +1720,99 @@
(set_attr "mode" "none")
(set_attr "length" "3")])
+(define_insn_and_split "*masktrue_const_pow2_minus_one"
+ [(set (pc)
+ (if_then_else (match_operator 4 "boolean_operator"
+ [(zero_extract:SI (match_operand:SI 1 "register_operand" "r")
+ (match_operand:SI 2 "const_int_operand" "i")
+ (const_int 0))
+ (const_int 0)])
+ (label_ref (match_operand 3 "" ""))
+ (pc)))
+ (clobber (match_scratch:SI 0 "=&a"))]
+ "IN_RANGE (INTVAL (operands[2]), 17, 31)"
+ "#"
+ "&& reload_completed"
+ [(set (match_dup 0)
+ (ashift:SI (match_dup 1)
+ (match_dup 2)))
+ (set (pc)
+ (if_then_else (match_op_dup 4
+ [(match_dup 0)
+ (const_int 0)])
+ (label_ref (match_dup 3))
+ (pc)))]
+{
+ operands[2] = GEN_INT (32 - INTVAL (operands[2]));
+}
+ [(set_attr "type" "jump")
+ (set_attr "mode" "none")
+ (set (attr "length")
+ (if_then_else (match_test "TARGET_DENSITY
+ && INTVAL (operands[2]) == 31")
+ (const_int 5)
+ (const_int 6)))])
+
+(define_insn_and_split "*masktrue_const_negative_pow2"
+ [(set (pc)
+ (if_then_else (match_operator 4 "boolean_operator"
+ [(and:SI (match_operand:SI 1 "register_operand" "r")
+ (match_operand:SI 2 "const_int_operand" "i"))
+ (const_int 0)])
+ (label_ref (match_operand 3 "" ""))
+ (pc)))
+ (clobber (match_scratch:SI 0 "=&a"))]
+ "IN_RANGE (exact_log2 (-INTVAL (operands[2])), 12, 30)"
+ "#"
+ "&& reload_completed"
+ [(set (match_dup 0)
+ (lshiftrt:SI (match_dup 1)
+ (match_dup 2)))
+ (set (pc)
+ (if_then_else (match_op_dup 4
+ [(match_dup 0)
+ (const_int 0)])
+ (label_ref (match_dup 3))
+ (pc)))]
+{
+ operands[2] = GEN_INT (floor_log2 (-INTVAL (operands[2])));
+}
+ [(set_attr "type" "jump")
+ (set_attr "mode" "none")
+ (set_attr "length" "6")])
+
+(define_insn_and_split "*masktrue_const_shifted_mask"
+ [(set (pc)
+ (if_then_else (match_operator 4 "boolean_operator"
+ [(and:SI (match_operand:SI 1 "register_operand" "r")
+ (match_operand:SI 2 "shifted_mask_operand" "i"))
+ (const_int 0)])
+ (label_ref (match_operand 3 "" ""))
+ (pc)))
+ (clobber (match_scratch:SI 0 "=&a"))]
+ ""
+ "#"
+ "reload_completed"
+ [(set (match_dup 0)
+ (zero_extract:SI (match_dup 1)
+ (match_dup 5)
+ (match_dup 2)))
+ (set (pc)
+ (if_then_else (match_op_dup 4
+ [(match_dup 0)
+ (const_int 0)])
+ (label_ref (match_dup 3))
+ (pc)))]
+{
+ HOST_WIDE_INT mask = INTVAL (operands[2]);
+ int shift = ctz_hwi (mask);
+ operands[2] = GEN_INT (shift);
+ operands[5] = GEN_INT (floor_log2 (((uint32_t)mask >> shift) + 1));
+}
+ [(set_attr "type" "jump")
+ (set_attr "mode" "none")
+ (set_attr "length" "6")])
+
;; Zero-overhead looping support.
--
2.20.1
next reply other threads:[~2022-06-12 6:43 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-06-12 6:41 Takayuki 'January June' Suwa [this message]
2022-06-13 3:49 ` Max Filippov
2022-06-13 16:28 ` [PATCH v2 " Takayuki 'January June' Suwa
2022-06-14 0:33 ` Max Filippov
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=fbe8f1b2-1b4c-1e2f-4197-3c4a0407e971@yahoo.co.jp \
--to=jjsuwa_sys3175@yahoo.co.jp \
--cc=gcc-patches@gcc.gnu.org \
/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).