From 659f8161f61d3f75c3a47cf646147e8f7b4dcb34 Mon Sep 17 00:00:00 2001
From: Roger Sayle <roger@nextmovesoftware.com>
Date: Fri, 7 Jan 2022 09:57:21 +0000
Subject: [PATCH] nvptx: Add support for PTX's cnot instruction.

This is a simple patch, now that the nvptx backend has transitioned
to STORE_FLAG_VALUE=1, that adds support for NVidia's cnot instruction,
that implements C/C++ style logical negation.

Previously, the simple function:

int foo(int x) { return !x; }

on nvptx-none with -O2 would generate:

	mov.u32 %r24, %ar0;
	setp.eq.u32     %r28, %r24, 0;
	selp.u32        %value, 1, 0, %r28;

with this patch, GCC now generates:

	mov.u32 %r24, %ar0;
	cnot.b32        %value, %r24;

2022-01-07  Roger Sayle  <roger@nextmovesoftware.com>

gcc/ChangeLog
	* config/nvptx/nvptx.md (*cnot<mode>2): New define_insn.

gcc/testsuite/ChangeLog
	* gcc.target/nvptx/cnot-1.c: New test case.
---
 gcc/config/nvptx/nvptx.md               |  7 +++
 gcc/testsuite/gcc.target/nvptx/cnot-1.c | 94 +++++++++++++++++++++++++++++++++
 2 files changed, 101 insertions(+)
 create mode 100644 gcc/testsuite/gcc.target/nvptx/cnot-1.c

diff --git a/gcc/config/nvptx/nvptx.md b/gcc/config/nvptx/nvptx.md
index a4c14a3..ce74672 100644
--- a/gcc/config/nvptx/nvptx.md
+++ b/gcc/config/nvptx/nvptx.md
@@ -592,6 +592,13 @@
   ""
   "%.\\tnot.b%T0\\t%0, %1;")
 
+(define_insn "*cnot<mode>2"
+  [(set (match_operand:HSDIM 0 "nvptx_register_operand" "=R")
+	(eq:HSDIM (match_operand:HSDIM 1 "nvptx_register_operand" "R")
+		  (const_int 0)))]
+  ""
+  "%.\\tcnot.b%T0\\t%0, %1;")
+
 (define_insn "bitrev<mode>2"
   [(set (match_operand:SDIM 0 "nvptx_register_operand" "=R")
 	(unspec:SDIM [(match_operand:SDIM 1 "nvptx_register_operand" "R")]
diff --git a/gcc/testsuite/gcc.target/nvptx/cnot-1.c b/gcc/testsuite/gcc.target/nvptx/cnot-1.c
new file mode 100644
index 0000000..d0bdccd
--- /dev/null
+++ b/gcc/testsuite/gcc.target/nvptx/cnot-1.c
@@ -0,0 +1,94 @@
+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+
+int test1(int x)
+{
+  return !x;
+}
+
+int test2(int x)
+{
+  return x ? 0 : 1;
+}
+
+int test3(int x)
+{
+  return (x == 0) ? 1 : 0;
+}
+
+unsigned int test4(unsigned int x)
+{
+  return !x;
+}
+
+unsigned int test5(unsigned int x)
+{
+  return x ? 0 : 1;
+}
+
+unsigned int test6(unsigned int x)
+{
+  return (x == 0) ? 1 : 0;
+}
+
+short test7(short x)
+{
+  return !x;
+}
+
+short test8(short x)
+{
+  return x ? 0 : 1;
+}
+
+short test9(short x)
+{
+  return (x == 0) ? 1 : 0;
+}
+
+unsigned short test10(unsigned short x)
+{
+  return !x;
+}
+
+unsigned short test11(unsigned short x)
+{
+  return x ? 0 : 1;
+}
+
+unsigned short test12(unsigned short x)
+{
+  return (x == 0) ? 1 : 0;
+}
+
+long test13(long x)
+{
+  return !x;
+}
+
+long test14(long x)
+{
+  return x ? 0 : 1;
+}
+
+long test15(long x)
+{
+  return (x == 0) ? 1: 0;
+}
+
+unsigned long test16(unsigned long x)
+{
+  return !x;
+}
+
+unsigned long test17(unsigned long x)
+{
+  return x ? 0 : 1;
+}
+
+unsigned long test18(unsigned long x)
+{
+  return (x == 0) ? 1 : 0;
+}
+
+/* { dg-final { scan-assembler-times "cnot.b" 18 } } */
-- 
2.7.4