From: Fei Gao <gaofei@eswincomputing.com>
To: gcc-patches@gcc.gnu.org
Cc: kito.cheng@gmail.com, palmer@dabbelt.com, jeffreyalaw@gmail.com,
zengxiao@eswincomputing.com, Fei Gao <gaofei@eswincomputing.com>
Subject: [PATCH 1/5][V3][ifcvt] optimize x=c ? (y op z) : y by RISC-V Zicond like insns
Date: Tue, 5 Dec 2023 08:12:44 +0000 [thread overview]
Message-ID: <20231205081248.2106-1-gaofei@eswincomputing.com> (raw)
op=[PLUS, MINUS, IOR, XOR]
Conditional op, if zero
rd = (rc == 0) ? (rs1 op rs2) : rs1
-->
czero.nez rd, rs2, rc
op rd, rs1, rd
Conditional op, if non-zero
rd = (rc != 0) ? (rs1 op rs2) : rs1
-->
czero.eqz rd, rs2, rc
op rd, rs1, rd
Co-authored-by: Xiao Zeng<zengxiao@eswincomputing.com>
gcc/ChangeLog:
* ifcvt.cc (noce_try_cond_zero_arith):handler for condtional zero based ifcvt
(noce_emit_czero): helper for noce_try_cond_zero_arith
(noce_cond_zero_binary_op_supported): check supported OPs for condtional zero based ifcvt
(get_base_reg): get the reg itself or NULL_RTX if not a reg
(noce_bbs_ok_for_cond_zero_arith): check if BBs are OK for condtional zero based ifcvt
(noce_process_if_block): add noce_try_cond_zero_arith
gcc/testsuite/ChangeLog:
* gcc.target/riscv/zicond_ifcvt_opt.c: New test.
---
gcc/ifcvt.cc | 187 ++++++
.../gcc.target/riscv/zicond_ifcvt_opt.c | 566 ++++++++++++++++++
2 files changed, 753 insertions(+)
create mode 100644 gcc/testsuite/gcc.target/riscv/zicond_ifcvt_opt.c
diff --git a/gcc/ifcvt.cc b/gcc/ifcvt.cc
index a0af553b9ff..1f0f5414ea1 100644
--- a/gcc/ifcvt.cc
+++ b/gcc/ifcvt.cc
@@ -787,6 +787,7 @@ static rtx noce_get_alt_condition (struct noce_if_info *, rtx, rtx_insn **);
static bool noce_try_minmax (struct noce_if_info *);
static bool noce_try_abs (struct noce_if_info *);
static bool noce_try_sign_mask (struct noce_if_info *);
+static int noce_try_cond_zero_arith (struct noce_if_info *);
/* Return the comparison code for reversed condition for IF_INFO,
or UNKNOWN if reversing the condition is not possible. */
@@ -1831,6 +1832,35 @@ noce_emit_cmove (struct noce_if_info *if_info, rtx x, enum rtx_code code,
return NULL_RTX;
}
+/* Emit a conditional zero, returning TARGET or NULL_RTX upon failure.
+ IF_INFO describes the if-conversion scenario under consideration.
+ CZERO_CODE selects the condition (EQ/NE).
+ NON_ZERO_OP is the nonzero operand of the conditional move
+ TARGET is the desired output register. */
+
+static rtx
+noce_emit_czero (struct noce_if_info *if_info, enum rtx_code czero_code,
+ rtx non_zero_op, rtx target)
+{
+ machine_mode mode = GET_MODE (target);
+ rtx cond_op0 = XEXP (if_info->cond, 0);
+ rtx czero_cond
+ = gen_rtx_fmt_ee (czero_code, GET_MODE (cond_op0), cond_op0, const0_rtx);
+ rtx if_then_else
+ = gen_rtx_IF_THEN_ELSE (mode, czero_cond, const0_rtx, non_zero_op);
+ rtx set = gen_rtx_SET (target, if_then_else);
+
+ rtx_insn *insn = make_insn_raw (set);
+
+ if (recog_memoized (insn) >= 0)
+ {
+ add_insn (insn);
+ return target;
+ }
+
+ return NULL_RTX;
+}
+
/* Try only simple constants and registers here. More complex cases
are handled in noce_try_cmove_arith after noce_try_store_flag_arith
has had a go at it. */
@@ -2880,6 +2910,160 @@ noce_try_sign_mask (struct noce_if_info *if_info)
return true;
}
+/* Check if OP is supported by conditional zero based if conversion,
+ returning TRUE if satisfied otherwise FALSE.
+
+ OP is the operation to check. */
+
+static bool
+noce_cond_zero_binary_op_supported (rtx op)
+{
+ enum rtx_code opcode = GET_CODE (op);
+
+ if (opcode == PLUS || opcode == MINUS || opcode == IOR || opcode == XOR)
+ return true;
+
+ return false;
+}
+
+/* Helper function to return REG itself,
+ otherwise NULL_RTX for other RTX_CODE. */
+
+static rtx
+get_base_reg (rtx exp)
+{
+ if (REG_P (exp))
+ return exp;
+
+ return NULL_RTX;
+}
+
+/* Check if IF-BB and THEN-BB satisfy the condition for conditional zero
+ based if conversion, returning TRUE if satisfied otherwise FALSE.
+
+ IF_INFO describes the if-conversion scenario under consideration.
+ COMMON_PTR points to the common REG of canonicalized IF_INFO->A and
+ IF_INFO->B.
+ CZERO_CODE_PTR points to the comparison code to use in czero RTX.
+ A_PTR points to the A expression of canonicalized IF_INFO->A.
+ TO_REPLACE points to the RTX to be replaced by czero RTX destnation. */
+
+static bool
+noce_bbs_ok_for_cond_zero_arith (struct noce_if_info *if_info, rtx *common_ptr,
+ enum rtx_code *czero_code_ptr, rtx *a_ptr,
+ rtx **to_replace)
+{
+ rtx common = NULL_RTX;
+ rtx cond = if_info->cond;
+ rtx a = copy_rtx (if_info->a);
+ rtx b = copy_rtx (if_info->b);
+ rtx bin_op1 = NULL_RTX;
+ enum rtx_code czero_code = UNKNOWN;
+ bool reverse = false;
+ rtx op0, op1, bin_exp;
+
+ if (!noce_simple_bbs (if_info))
+ return false;
+
+ /* COND must be EQ or NE comparision of a reg and 0. */
+ if (GET_CODE (cond) != NE && GET_CODE (cond) != EQ)
+ return false;
+ if (!REG_P (XEXP (cond, 0)) || !rtx_equal_p (XEXP (cond, 1), const0_rtx))
+ return false;
+
+ /* Canonicalize x = y : (y op z) to x = (y op z) : y. */
+ if (REG_P (a) && noce_cond_zero_binary_op_supported (b))
+ {
+ std::swap (a, b);
+ reverse = !reverse;
+ }
+
+ /* Check if x = (y op z) : y is supported by czero based ifcvt. */
+ if (!(noce_cond_zero_binary_op_supported (a) && REG_P (b)))
+ return false;
+
+ bin_exp = a;
+
+ /* Canonicalize x = (z op y) : y to x = (y op z) : y */
+ op1 = get_base_reg (XEXP (bin_exp, 1));
+ if (op1 && rtx_equal_p (op1, b) && COMMUTATIVE_ARITH_P (bin_exp))
+ std::swap (XEXP (bin_exp, 0), XEXP (bin_exp, 1));
+
+ op0 = get_base_reg (XEXP (bin_exp, 0));
+ if (op0 && rtx_equal_p (op0, b))
+ {
+ common = b;
+ bin_op1 = XEXP (bin_exp, 1);
+ czero_code = reverse
+ ? noce_reversed_cond_code (if_info)
+ : GET_CODE (cond);
+ }
+ else
+ return false;
+
+ if (czero_code == UNKNOWN)
+ return false;
+
+ if (REG_P (bin_op1))
+ *to_replace = &XEXP (bin_exp, 1);
+ else
+ return false;
+
+ *common_ptr = common;
+ *czero_code_ptr = czero_code;
+ *a_ptr = a;
+
+ return true;
+}
+
+/* Try to covert if-then-else with conditional zero,
+ returning TURE on success or FALSE on failure.
+ IF_INFO describes the if-conversion scenario under consideration. */
+
+static int
+noce_try_cond_zero_arith (struct noce_if_info *if_info)
+{
+ rtx target, a;
+ rtx_insn *seq;
+ machine_mode mode = GET_MODE (if_info->x);
+ rtx common = NULL_RTX;
+ enum rtx_code czero_code = UNKNOWN;
+ rtx non_zero_op = NULL_RTX;
+ rtx *to_replace = NULL;
+
+ if (!noce_bbs_ok_for_cond_zero_arith (if_info, &common, &czero_code, &a,
+ &to_replace))
+ return false;
+
+ non_zero_op = *to_replace;
+
+ start_sequence ();
+
+ /* If x is used in both input and out like x = c ? x + z : x,
+ use a new reg to avoid modifying x */
+ if (common && rtx_equal_p (common, if_info->x))
+ target = gen_reg_rtx (mode);
+ else
+ target = if_info->x;
+
+ target = noce_emit_czero (if_info, czero_code, non_zero_op, target);
+ if (!target || !to_replace)
+ {
+ end_sequence ();
+ return false;
+ }
+
+ *to_replace = target;
+ noce_emit_move_insn (if_info->x, a);
+
+ seq = end_ifcvt_sequence (if_info);
+ if (!seq || !targetm.noce_conversion_profitable_p (seq, if_info))
+ return false;
+
+ emit_insn_before_setloc (seq, if_info->jump, INSN_LOCATION (if_info->insn_a));
+ if_info->transform_name = "noce_try_cond_zero_arith";
+ return true;
+}
/* Optimize away "if (x & C) x |= C" and similar bit manipulation
transformations. */
@@ -3975,6 +4159,9 @@ noce_process_if_block (struct noce_if_info *if_info)
goto success;
if (noce_try_store_flag_mask (if_info))
goto success;
+ if (HAVE_conditional_move
+ && noce_try_cond_zero_arith (if_info))
+ goto success;
if (HAVE_conditional_move
&& noce_try_cmove_arith (if_info))
goto success;
diff --git a/gcc/testsuite/gcc.target/riscv/zicond_ifcvt_opt.c b/gcc/testsuite/gcc.target/riscv/zicond_ifcvt_opt.c
new file mode 100644
index 00000000000..dcb21c15d1a
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/zicond_ifcvt_opt.c
@@ -0,0 +1,566 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gc_zbb_zicond -mabi=lp64d -O2 " } */
+/* { dg-skip-if "" { *-*-* } {"-O0" "-O1" "-Os" "-Og" "-O3" "-Oz" "-flto"} } */
+
+long
+test_ADD_ceqz (long x, long y, long z, long c)
+{
+ if (c)
+ x = y + z;
+ else
+ x = y;
+ return x;
+}
+
+long
+test_ADD_ceqz_x (long x, long z, long c)
+{
+ if (c)
+ x = x + z;
+
+ return x;
+}
+
+long
+test_ADD_nez (long x, long y, long z, long c)
+{
+ if (c)
+ x = y;
+ else
+ x = y + z;
+ return x;
+}
+
+long
+test_ADD_nez_x (long x, long z, long c)
+{
+ if (c)
+ {
+ }
+ else
+ x = x + z;
+ return x;
+}
+
+long
+test_ADD_nez_2 (long x, long y, long z, long c)
+{
+ if (!c)
+ x = y + z;
+ else
+ x = y;
+ return x;
+}
+
+long
+test_ADD_nez_x_2 (long x, long z, long c)
+{
+ if (!c)
+ x = x + z;
+
+ return x;
+}
+
+long
+test_ADD_eqz_2 (long x, long y, long z, long c)
+{
+ if (!c)
+ x = y;
+ else
+ x = y + z;
+ return x;
+}
+
+long
+test_ADD_eqz_x_2 (long x, long z, long c)
+{
+ if (!c)
+ {
+ }
+ else
+ x = x + z;
+ return x;
+}
+
+long
+test_SUB_ceqz (long x, long y, long z, long c)
+{
+ if (c)
+ x = y - z;
+ else
+ x = y;
+ return x;
+}
+
+long
+test_SUB_ceqz_x (long x, long z, long c)
+{
+ if (c)
+ x = x - z;
+
+ return x;
+}
+
+long
+test_SUB_nez (long x, long y, long z, long c)
+{
+ if (c)
+ x = y;
+ else
+ x = y - z;
+ return x;
+}
+
+long
+test_SUB_nez_x (long x, long z, long c)
+{
+ if (c)
+ {
+ }
+ else
+ x = x - z;
+ return x;
+}
+
+long
+test_SUB_nez_2 (long x, long y, long z, long c)
+{
+ if (!c)
+ x = y - z;
+ else
+ x = y;
+ return x;
+}
+
+long
+test_SUB_nez_x_2 (long x, long z, long c)
+{
+ if (!c)
+ x = x - z;
+
+ return x;
+}
+
+long
+test_SUB_eqz_2 (long x, long y, long z, long c)
+{
+ if (!c)
+ x = y;
+ else
+ x = y - z;
+ return x;
+}
+
+long
+test_SUB_eqz_x_2 (long x, long z, long c)
+{
+ if (!c)
+ {
+ }
+ else
+ x = x - z;
+ return x;
+}
+
+long
+test_IOR_ceqz (long x, long y, long z, long c)
+{
+ if (c)
+ x = y | z;
+ else
+ x = y;
+ return x;
+}
+
+long
+test_IOR_ceqz_x (long x, long z, long c)
+{
+ if (c)
+ x = x | z;
+
+ return x;
+}
+
+long
+test_IOR_nez (long x, long y, long z, long c)
+{
+ if (c)
+ x = y;
+ else
+ x = y | z;
+ return x;
+}
+
+long
+test_IOR_nez_x (long x, long z, long c)
+{
+ if (c)
+ {
+ }
+ else
+ x = x | z;
+ return x;
+}
+
+long
+test_IOR_nez_2 (long x, long y, long z, long c)
+{
+ if (!c)
+ x = y | z;
+ else
+ x = y;
+ return x;
+}
+
+long
+test_IOR_nez_x_2 (long x, long z, long c)
+{
+ if (!c)
+ x = x | z;
+
+ return x;
+}
+
+long
+test_IOR_eqz_2 (long x, long y, long z, long c)
+{
+ if (!c)
+ x = y;
+ else
+ x = y | z;
+ return x;
+}
+
+long
+test_IOR_eqz_x_2 (long x, long z, long c)
+{
+ if (!c)
+ {
+ }
+ else
+ x = x | z;
+ return x;
+}
+
+long
+test_XOR_ceqz (long x, long y, long z, long c)
+{
+ if (c)
+ x = y ^ z;
+ else
+ x = y;
+ return x;
+}
+
+long
+test_XOR_ceqz_x (long x, long z, long c)
+{
+ if (c)
+ x = x ^ z;
+
+ return x;
+}
+
+long
+test_XOR_nez (long x, long y, long z, long c)
+{
+ if (c)
+ x = y;
+ else
+ x = y ^ z;
+ return x;
+}
+
+long
+test_XOR_nez_x (long x, long z, long c)
+{
+ if (c)
+ {
+ }
+ else
+ x = x ^ z;
+ return x;
+}
+
+long
+test_XOR_nez_2 (long x, long y, long z, long c)
+{
+ if (!c)
+ x = y ^ z;
+ else
+ x = y;
+ return x;
+}
+
+long
+test_XOR_nez_x_2 (long x, long z, long c)
+{
+ if (!c)
+ x = x ^ z;
+
+ return x;
+}
+
+long
+test_XOR_eqz_2 (long x, long y, long z, long c)
+{
+ if (!c)
+ x = y;
+ else
+ x = y ^ z;
+ return x;
+}
+
+long
+test_XOR_eqz_x_2 (long x, long z, long c)
+{
+ if (!c)
+ {
+ }
+ else
+ x = x ^ z;
+ return x;
+}
+
+long
+test_ADD_ceqz_reverse_bin_oprands (long x, long y, long z, long c)
+{
+ if (c)
+ x = z + y;
+ else
+ x = y;
+ return x;
+}
+
+long
+test_ADD_ceqz_x_reverse_bin_oprands (long x, long z, long c)
+{
+ if (c)
+ x = z + x;
+
+ return x;
+}
+
+long
+test_ADD_nez_reverse_bin_oprands (long x, long y, long z, long c)
+{
+ if (c)
+ x = y;
+ else
+ x = z + y;
+ return x;
+}
+
+long
+test_ADD_nez_x_reverse_bin_oprands (long x, long z, long c)
+{
+ if (c)
+ {
+ }
+ else
+ x = z + x;
+ return x;
+}
+
+long
+test_ADD_nez_2_reverse_bin_oprands (long x, long y, long z, long c)
+{
+ if (!c)
+ x = z + y;
+ else
+ x = y;
+ return x;
+}
+
+long
+test_ADD_nez_x_2_reverse_bin_oprands (long x, long z, long c)
+{
+ if (!c)
+ x = z + x;
+
+ return x;
+}
+
+long
+test_ADD_eqz_2_reverse_bin_oprands (long x, long y, long z, long c)
+{
+ if (!c)
+ x = y;
+ else
+ x = z + y;
+ return x;
+}
+
+long
+test_ADD_eqz_x_2_reverse_bin_oprands (long x, long z, long c)
+{
+ if (!c)
+ {
+ }
+ else
+ x = z + x;
+ return x;
+}
+
+long
+test_IOR_ceqz_reverse_bin_oprands (long x, long y, long z, long c)
+{
+ if (c)
+ x = z | y;
+ else
+ x = y;
+ return x;
+}
+
+long
+test_IOR_ceqz_x_reverse_bin_oprands (long x, long z, long c)
+{
+ if (c)
+ x = z | x;
+
+ return x;
+}
+
+long
+test_IOR_nez_reverse_bin_oprands (long x, long y, long z, long c)
+{
+ if (c)
+ x = y;
+ else
+ x = z | y;
+ return x;
+}
+
+long
+test_IOR_nez_x_reverse_bin_oprands (long x, long z, long c)
+{
+ if (c)
+ {
+ }
+ else
+ x = z | x;
+ return x;
+}
+
+long
+test_IOR_nez_2_reverse_bin_oprands (long x, long y, long z, long c)
+{
+ if (!c)
+ x = z | y;
+ else
+ x = y;
+ return x;
+}
+
+long
+test_IOR_nez_x_2_reverse_bin_oprands (long x, long z, long c)
+{
+ if (!c)
+ x = z | x;
+
+ return x;
+}
+
+long
+test_IOR_eqz_2_reverse_bin_oprands (long x, long y, long z, long c)
+{
+ if (!c)
+ x = y;
+ else
+ x = z | y;
+ return x;
+}
+
+long
+test_IOR_eqz_x_2_reverse_bin_oprands (long x, long z, long c)
+{
+ if (!c)
+ {
+ }
+ else
+ x = z | x;
+ return x;
+}
+
+long
+test_XOR_ceqz_reverse_bin_oprands (long x, long y, long z, long c)
+{
+ if (c)
+ x = z ^ y;
+ else
+ x = y;
+ return x;
+}
+
+long
+test_XOR_ceqz_x_reverse_bin_oprands (long x, long z, long c)
+{
+ if (c)
+ x = z ^ x;
+
+ return x;
+}
+
+long
+test_XOR_nez_reverse_bin_oprands (long x, long y, long z, long c)
+{
+ if (c)
+ x = y;
+ else
+ x = z ^ y;
+ return x;
+}
+
+long
+test_XOR_nez_x_reverse_bin_oprands (long x, long z, long c)
+{
+ if (c)
+ {
+ }
+ else
+ x = z ^ x;
+ return x;
+}
+
+long
+test_XOR_nez_2_reverse_bin_oprands (long x, long y, long z, long c)
+{
+ if (!c)
+ x = z ^ y;
+ else
+ x = y;
+ return x;
+}
+
+long
+test_XOR_nez_x_2_reverse_bin_oprands (long x, long z, long c)
+{
+ if (!c)
+ x = z ^ x;
+
+ return x;
+}
+
+long
+test_XOR_eqz_2_reverse_bin_oprands (long x, long y, long z, long c)
+{
+ if (!c)
+ x = y;
+ else
+ x = z ^ y;
+ return x;
+}
+
+long
+test_XOR_eqz_x_2_reverse_bin_oprands (long x, long z, long c)
+{
+ if (!c)
+ {
+ }
+ else
+ x = z ^ x;
+ return x;
+}
+
+/* { dg-final { scan-assembler-times {czero\.eqz} 28 } } */
+/* { dg-final { scan-assembler-times {czero\.nez} 28 } } */
--
2.17.1
next reply other threads:[~2023-12-05 8:13 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-12-05 8:12 Fei Gao [this message]
2023-12-05 8:12 ` [PATCH 2/5] [ifcvt] optimize x=c ? (y shift_op z):y " Fei Gao
2023-12-10 20:43 ` Jeff Law
2023-12-11 4:01 ` Fei Gao
2023-12-11 6:15 ` Jeff Law
2023-12-05 8:12 ` [PATCH 3/5] [ifcvt] optimize x=c ? (y AND z) : y " Fei Gao
2023-12-11 5:16 ` Jeff Law
2023-12-05 8:12 ` [PATCH 4/5] [ifcvt] optimize x=c ? (y op const_int) " Fei Gao
2023-12-11 5:38 ` Jeff Law
2023-12-14 8:42 ` Fei Gao
2023-12-05 8:12 ` [PATCH 5/5] [ifcvt] optimize extension for x=c ? (y op z) " Fei Gao
2023-12-11 5:46 ` Jeff Law
2023-12-14 9:32 ` Fei Gao
2023-12-08 0:49 ` [PATCH 1/5][V3][ifcvt] optimize " Jeff Law
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=20231205081248.2106-1-gaofei@eswincomputing.com \
--to=gaofei@eswincomputing.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=jeffreyalaw@gmail.com \
--cc=kito.cheng@gmail.com \
--cc=palmer@dabbelt.com \
--cc=zengxiao@eswincomputing.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).