From 37a4c06f3dac9b0b831a8f34af73422aa4f42fbe Mon Sep 17 00:00:00 2001
From: Roger Sayle <roger@nextmovesoftware.com>
Date: Tue, 4 Aug 2020 15:31:42 +0200
Subject: [PATCH] [PATCH] nvptx: Add support for PTX highpart multiplications
 (HI/SI)

This patch adds support for signed and unsigned, HImode and SImode highpart
multiplications to the nvptx backend.

This patch has been tested on nvptx-none hosted on x86_64-pc-linux-gnu
with a "make" and "make -k check" with no new failures with the
above patch.

2020-08-04  Roger Sayle  <roger@nextmovesoftware.com>

gcc/ChangeLog:

	* config/nvptx/nvptx.md (smulhi3_highpart, smulsi3_highpart)
	(umulhi3_highpart, umulsi3_highpart): New instructions.

gcc/testsuite/ChangeLog:

	* gcc.target/nvptx/mul-hi.c: New test.
	* gcc.target/nvptx/umul-hi.c: New test.
---
 gcc/config/nvptx/nvptx.md                | 48 ++++++++++++++++++++++++
 gcc/testsuite/gcc.target/nvptx/mul-hi.c  | 15 ++++++++
 gcc/testsuite/gcc.target/nvptx/umul-hi.c | 15 ++++++++
 3 files changed, 78 insertions(+)
 create mode 100644 gcc/testsuite/gcc.target/nvptx/mul-hi.c
 create mode 100644 gcc/testsuite/gcc.target/nvptx/umul-hi.c

diff --git a/gcc/config/nvptx/nvptx.md b/gcc/config/nvptx/nvptx.md
index c23edcf34bf..4168190fa42 100644
--- a/gcc/config/nvptx/nvptx.md
+++ b/gcc/config/nvptx/nvptx.md
@@ -568,6 +568,54 @@
   ""
   "%.\\tmul.wide.u32\\t%0, %1, %2;")
 
+(define_insn "smulhi3_highpart"
+  [(set (match_operand:HI 0 "nvptx_register_operand" "=R")
+	(truncate:HI
+	 (lshiftrt:SI
+	  (mult:SI (sign_extend:SI
+		    (match_operand:HI 1 "nvptx_register_operand" "R"))
+		   (sign_extend:SI
+		    (match_operand:HI 2 "nvptx_register_operand" "R")))
+	  (const_int 16))))]
+  ""
+  "%.\\tmul.hi.s16\\t%0, %1, %2;")
+
+(define_insn "smulsi3_highpart"
+  [(set (match_operand:SI 0 "nvptx_register_operand" "=R")
+	(truncate:SI
+	 (lshiftrt:DI
+	  (mult:DI (sign_extend:DI
+		    (match_operand:SI 1 "nvptx_register_operand" "R"))
+		   (sign_extend:DI
+		    (match_operand:SI 2 "nvptx_register_operand" "R")))
+	  (const_int 32))))]
+  ""
+  "%.\\tmul.hi.s32\\t%0, %1, %2;")
+
+(define_insn "umulhi3_highpart"
+  [(set (match_operand:HI 0 "nvptx_register_operand" "=R")
+	(truncate:HI
+	 (lshiftrt:SI
+	  (mult:SI (zero_extend:SI
+		    (match_operand:HI 1 "nvptx_register_operand" "R"))
+		   (zero_extend:SI
+		    (match_operand:HI 2 "nvptx_register_operand" "R")))
+	  (const_int 16))))]
+  ""
+  "%.\\tmul.hi.u16\\t%0, %1, %2;")
+
+(define_insn "umulsi3_highpart"
+  [(set (match_operand:SI 0 "nvptx_register_operand" "=R")
+	(truncate:SI
+	 (lshiftrt:DI
+	  (mult:DI (zero_extend:DI
+		    (match_operand:SI 1 "nvptx_register_operand" "R"))
+		   (zero_extend:DI
+		    (match_operand:SI 2 "nvptx_register_operand" "R")))
+	  (const_int 32))))]
+  ""
+  "%.\\tmul.hi.u32\\t%0, %1, %2;")
+
 ;; Shifts
 
 (define_insn "ashl<mode>3"
diff --git a/gcc/testsuite/gcc.target/nvptx/mul-hi.c b/gcc/testsuite/gcc.target/nvptx/mul-hi.c
new file mode 100644
index 00000000000..c66fa38623b
--- /dev/null
+++ b/gcc/testsuite/gcc.target/nvptx/mul-hi.c
@@ -0,0 +1,15 @@
+/* { dg-do assemble } */
+/* { dg-options "-O2 -save-temps" } */
+
+short smulhi3_highpart(short x, short y)
+{
+  return ((int)x * (int)y) >> 16;
+}
+
+int smulsi3_highpart(int x, int y)
+{
+  return ((long)x * (long)y) >> 32;
+}
+
+/* { dg-final { scan-assembler-times "mul.hi.s16" 1 } } */
+/* { dg-final { scan-assembler-times "mul.hi.s32" 1 } } */
diff --git a/gcc/testsuite/gcc.target/nvptx/umul-hi.c b/gcc/testsuite/gcc.target/nvptx/umul-hi.c
new file mode 100644
index 00000000000..3b35d6b50ec
--- /dev/null
+++ b/gcc/testsuite/gcc.target/nvptx/umul-hi.c
@@ -0,0 +1,15 @@
+/* { dg-do assemble } */
+/* { dg-options "-O2 -save-temps" } */
+
+unsigned short umulhi3_highpart(unsigned short x, unsigned short y)
+{
+  return ((unsigned int)x * (unsigned int)y) >> 16;
+}
+
+unsigned int umulsi3_highpart(unsigned int x, unsigned int y)
+{
+  return ((unsigned long)x * (unsigned long)y) >> 32;
+}
+
+/* { dg-final { scan-assembler-times "mul.hi.u16" 1 } } */
+/* { dg-final { scan-assembler-times "mul.hi.u32" 1 } } */
-- 
2.30.2