[PATCH] nvptx: Add support for popcount and widening multiply instructions

2020-07-01  Roger Sayle  <roger@nextmovesoftware.com>

gcc/ChangeLog:
	* config/nvptx/nvptx.md (popcount<mode>2): New instructions.
	(mulhishi3, mulsidi3, umulhisi3, umulsidi3): New instructions.

gcc/testsuite/ChangeLog:
	* gcc.target/nvptx/popc-1.c: New test.
	* gcc.target/nvptx/popc-2.c: New test.
	* gcc.target/nvptx/popc-3.c: New test.
	* gcc.target/nvptx/mul-wide.c: New test.
	* gcc.target/nvptx/umul-wide.c: New test.

gcc/config/nvptx/nvptx.md

@@ -493,6 +493,50 @@
   DONE;
 })
 
+(define_insn "popcount<mode>2"
+  [(set (match_operand:SI 0 "nvptx_register_operand" "=R")
+	(popcount:SI (match_operand:SDIM 1 "nvptx_register_operand" "R")))]
+  ""
+  "%.\\tpopc.b%T1\\t%0, %1;")
+
+;; Multiplication variants
+
+(define_insn "mulhisi3"
+  [(set (match_operand:SI 0 "nvptx_register_operand" "=R")
+	(mult:SI (sign_extend:SI
+		  (match_operand:HI 1 "nvptx_register_operand" "R"))
+		 (sign_extend:SI
+		  (match_operand:HI 2 "nvptx_register_operand" "R"))))]
+  ""
+  "%.\\tmul.wide.s16\\t%0, %1, %2;")
+
+(define_insn "mulsidi3"
+  [(set (match_operand:DI 0 "nvptx_register_operand" "=R")
+	(mult:DI (sign_extend:DI
+		  (match_operand:SI 1 "nvptx_register_operand" "R"))
+		 (sign_extend:DI
+		  (match_operand:SI 2 "nvptx_register_operand" "R"))))]
+  ""
+  "%.\\tmul.wide.s32\\t%0, %1, %2;")
+
+(define_insn "umulhisi3"
+  [(set (match_operand:SI 0 "nvptx_register_operand" "=R")
+	(mult:SI (zero_extend:SI
+		  (match_operand:HI 1 "nvptx_register_operand" "R"))
+		 (zero_extend:SI
+		  (match_operand:HI 2 "nvptx_register_operand" "R"))))]
+  ""
+  "%.\\tmul.wide.u16\\t%0, %1, %2;")
+
+(define_insn "umulsidi3"
+  [(set (match_operand:DI 0 "nvptx_register_operand" "=R")
+	(mult:DI (zero_extend:DI
+		  (match_operand:SI 1 "nvptx_register_operand" "R"))
+		 (zero_extend:DI
+		  (match_operand:SI 2 "nvptx_register_operand" "R"))))]
+  ""
+  "%.\\tmul.wide.u32\\t%0, %1, %2;")
+
 ;; Shifts
 
 (define_insn "ashl<mode>3"

gcc/testsuite/gcc.target/nvptx/mul-wide.c

@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+
+int mulhisi3(short x, short y)
+{
+  return (int)x * (int)y;
+}
+
+long mulsidi3(int x, int y)
+{
+  return (long)x * (long)y;
+}
+
+/* { dg-final { scan-assembler-times "mul.wide.s16" 1 } } */
+/* { dg-final { scan-assembler-times "mul.wide.s32" 1 } } */
+

gcc/testsuite/gcc.target/nvptx/popc-1.c

@@ -0,0 +1,9 @@
+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+
+unsigned int foo(unsigned int x)
+{
+  return __builtin_popcount(x);
+}
+
+/* { dg-final { scan-assembler-times "popc.b32" 1 } } */

gcc/testsuite/gcc.target/nvptx/popc-2.c

@@ -0,0 +1,11 @@
+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+
+unsigned long foo(unsigned long x)
+{
+  return __builtin_popcountl(x);
+}
+
+/* { dg-final { scan-assembler-times "popc.b64" 1 } } */
+/* { dg-final { scan-assembler-times "cvt.s64.s32" 1 } } */
+

gcc/testsuite/gcc.target/nvptx/popc-3.c

@@ -0,0 +1,11 @@
+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+
+unsigned int foo(unsigned long x)
+{
+  return __builtin_popcountl(x);
+}
+
+/* { dg-final { scan-assembler-times "popc.b64" 1 } } */
+/* { dg-final { scan-assembler-times "cvt.s64.s32" 0 } } */
+

gcc/testsuite/gcc.target/nvptx/umul-wide.c

@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+
+unsigned int umulhisi3(unsigned short x, unsigned short y)
+{
+  return (unsigned int)x * (unsigned int)y;
+}
+
+unsigned long umulsidi3(unsigned int x, unsigned int y)
+{
+  return (unsigned long)x * (unsigned long)y;
+}
+
+/* { dg-final { scan-assembler-times "mul.wide.u16" 1 } } */
+/* { dg-final { scan-assembler-times "mul.wide.u32" 1 } } */
+