From 76d599c6d8f9cf78b51cd76a7ca8fbe11e2cda2b Mon Sep 17 00:00:00 2001
From: Xi Ruoyao <xry111@xry111.site>
Date: Sun, 6 Nov 2022 23:16:49 +0800
Subject: [PATCH 028/124] LoongArch: Add ftint{,rm,rp}.{w,l}.{s,d} instructions

This allows to optimize the following builtins if -fno-math-errno:

- __builtin_lrint{,f}
- __builtin_lfloor{,f}
- __builtin_lceil{,f}

Inspired by
https://gcc.gnu.org/pipermail/gcc-patches/2022-November/605287.html.

ANYFI is added so the compiler won't try ftint.l.s if -mfpu=32.  If we
simply used GPR here an ICE would be triggered with __builtin_lrintf
and -mfpu=32.

ftint{rm,rp} instructions may raise inexact exception, so they can't be
used if -fno-trapping-math -fno-fp-int-builtin-inexact.

Note that the .w.{s,d} variants are not tested because we don't support
ILP32 for now.

gcc/ChangeLog:

	* config/loongarch/loongarch.md (UNSPEC_FTINT): New unspec.
	(UNSPEC_FTINTRM): Likewise.
	(UNSPEC_FTINTRP): Likewise.
	(LRINT): New define_int_iterator.
	(lrint_pattern): New define_int_attr.
	(lrint_submenmonic): Likewise.
	(lrint_allow_inexact): Likewise.
	(ANYFI): New define_mode_iterator.
	(lrint<ANYF><ANYFI>): New instruction template.

gcc/testsuite/ChangeLog:

	* gcc.target/loongarch/ftint.c: New test.
	* gcc.target/loongarch/ftint-no-inexact.c: New test.

Signed-off-by: Peng Fan <fanpeng@loongson.cn>
Signed-off-by: ticat_fp <fanpeng@loongson.cn>
---
 gcc/config/loongarch/loongarch.md             | 34 ++++++++++++++
 .../gcc.target/loongarch/ftint-no-inexact.c   | 44 +++++++++++++++++++
 gcc/testsuite/gcc.target/loongarch/ftint.c    | 44 +++++++++++++++++++
 3 files changed, 122 insertions(+)
 create mode 100644 gcc/testsuite/gcc.target/loongarch/ftint-no-inexact.c
 create mode 100644 gcc/testsuite/gcc.target/loongarch/ftint.c

diff --git a/gcc/config/loongarch/loongarch.md b/gcc/config/loongarch/loongarch.md
index a14ab14ac..eb127c346 100644
--- a/gcc/config/loongarch/loongarch.md
+++ b/gcc/config/loongarch/loongarch.md
@@ -38,6 +38,9 @@
   UNSPEC_FMAX
   UNSPEC_FMIN
   UNSPEC_FCOPYSIGN
+  UNSPEC_FTINT
+  UNSPEC_FTINTRM
+  UNSPEC_FTINTRP
 
   ;; Override return address for exception handling.
   UNSPEC_EH_RETURN
@@ -374,6 +377,11 @@
 (define_mode_iterator ANYF [(SF "TARGET_HARD_FLOAT")
 			    (DF "TARGET_DOUBLE_FLOAT")])
 
+;; Iterator for fixed-point modes which can be hold by a hardware
+;; floating-point register.
+(define_mode_iterator ANYFI [(SI "TARGET_HARD_FLOAT")
+			     (DI "TARGET_DOUBLE_FLOAT")])
+
 ;; A mode for which moves involving FPRs may need to be split.
 (define_mode_iterator SPLITF
   [(DF "!TARGET_64BIT && TARGET_DOUBLE_FLOAT")
@@ -515,6 +523,19 @@
 (define_code_attr sel [(eq "masknez") (ne "maskeqz")])
 (define_code_attr selinv [(eq "maskeqz") (ne "masknez")])
 
+;; Iterator and attributes for floating-point to fixed-point conversion
+;; instructions.
+(define_int_iterator LRINT [UNSPEC_FTINT UNSPEC_FTINTRM UNSPEC_FTINTRP])
+(define_int_attr lrint_pattern [(UNSPEC_FTINT "lrint")
+				(UNSPEC_FTINTRM "lfloor")
+				(UNSPEC_FTINTRP "lceil")])
+(define_int_attr lrint_submenmonic [(UNSPEC_FTINT "")
+				    (UNSPEC_FTINTRM "rm")
+				    (UNSPEC_FTINTRP "rp")])
+(define_int_attr lrint_allow_inexact [(UNSPEC_FTINT "1")
+				      (UNSPEC_FTINTRM "0")
+				      (UNSPEC_FTINTRP "0")])
+
 ;;
 ;;  ....................
 ;;
@@ -2022,6 +2043,19 @@
   [(set_attr "type" "fcvt")
    (set_attr "mode" "<MODE>")])
 
+;; Convert floating-point numbers to integers
+(define_insn "<lrint_pattern><ANYF:mode><ANYFI:mode>2"
+  [(set (match_operand:ANYFI 0 "register_operand" "=f")
+	(unspec:ANYFI [(match_operand:ANYF 1 "register_operand" "f")]
+		      LRINT))]
+  "TARGET_HARD_FLOAT &&
+   (<lrint_allow_inexact>
+    || flag_fp_int_builtin_inexact
+    || !flag_trapping_math)"
+  "ftint<lrint_submenmonic>.<ANYFI:ifmt>.<ANYF:fmt> %0,%1"
+  [(set_attr "type" "fcvt")
+   (set_attr "mode" "<ANYF:MODE>")])
+
 ;; Load the low word of operand 0 with operand 1.
 (define_insn "load_low<mode>"
   [(set (match_operand:SPLITF 0 "register_operand" "=f,f")
diff --git a/gcc/testsuite/gcc.target/loongarch/ftint-no-inexact.c b/gcc/testsuite/gcc.target/loongarch/ftint-no-inexact.c
new file mode 100644
index 000000000..88b83a9c0
--- /dev/null
+++ b/gcc/testsuite/gcc.target/loongarch/ftint-no-inexact.c
@@ -0,0 +1,44 @@
+/* { dg-do compile } */
+/* { dg-options "-mabi=lp64d -mdouble-float -fno-math-errno -fno-fp-int-builtin-inexact" } */
+/* { dg-final { scan-assembler "ftint\\.l\\.s" } } */
+/* { dg-final { scan-assembler "ftint\\.l\\.d" } } */
+/* { dg-final { scan-assembler-not "ftintrm\\.l\\.s" } } */
+/* { dg-final { scan-assembler-not "ftintrm\\.l\\.d" } } */
+/* { dg-final { scan-assembler-not "ftintrp\\.l\\.s" } } */
+/* { dg-final { scan-assembler-not "ftintrp\\.l\\.d" } } */
+
+long
+my_lrint (double a)
+{
+  return __builtin_lrint (a);
+}
+
+long
+my_lrintf (float a)
+{
+  return __builtin_lrintf (a);
+}
+
+long
+my_lfloor (double a)
+{
+  return __builtin_lfloor (a);
+}
+
+long
+my_lfloorf (float a)
+{
+  return __builtin_lfloorf (a);
+}
+
+long
+my_lceil (double a)
+{
+  return __builtin_lceil (a);
+}
+
+long
+my_lceilf (float a)
+{
+  return __builtin_lceilf (a);
+}
diff --git a/gcc/testsuite/gcc.target/loongarch/ftint.c b/gcc/testsuite/gcc.target/loongarch/ftint.c
new file mode 100644
index 000000000..7a326a454
--- /dev/null
+++ b/gcc/testsuite/gcc.target/loongarch/ftint.c
@@ -0,0 +1,44 @@
+/* { dg-do compile } */
+/* { dg-options "-mabi=lp64d -mdouble-float -fno-math-errno -ffp-int-builtin-inexact" } */
+/* { dg-final { scan-assembler "ftint\\.l\\.s" } } */
+/* { dg-final { scan-assembler "ftint\\.l\\.d" } } */
+/* { dg-final { scan-assembler "ftintrm\\.l\\.s" } } */
+/* { dg-final { scan-assembler "ftintrm\\.l\\.d" } } */
+/* { dg-final { scan-assembler "ftintrp\\.l\\.s" } } */
+/* { dg-final { scan-assembler "ftintrp\\.l\\.d" } } */
+
+long
+my_lrint (double a)
+{
+  return __builtin_lrint (a);
+}
+
+long
+my_lrintf (float a)
+{
+  return __builtin_lrintf (a);
+}
+
+long
+my_lfloor (double a)
+{
+  return __builtin_lfloor (a);
+}
+
+long
+my_lfloorf (float a)
+{
+  return __builtin_lfloorf (a);
+}
+
+long
+my_lceil (double a)
+{
+  return __builtin_lceil (a);
+}
+
+long
+my_lceilf (float a)
+{
+  return __builtin_lceilf (a);
+}
-- 
2.33.0