nvptx: Fix and use BI mode logic instructions (e.g. and.pred)

This patch adds support for nvptx's BImode and.pred, or.pred and
xor.pred instructions.  Technically, nvptx.md previously defined
andbi3, iorbi3 and xorbi3 instructions, but the assembly language
mnemonic output for these was incorrect (e.g. and.b1) and would be
rejected by the ptxas assembler.  The most significant part of this
patch is the new define_split which teaches the compiler to actually
use these instructions when appropriate (exposing the latent bug above).

After https://gcc.gnu.org/pipermail/gcc-patches/2022-January/587999.html,
the function:

int foo(int x, int y) { return (x==21) && (y==69); }

when compiled with -O2 produces:

                mov.u32 %r26, %ar0;
                mov.u32 %r27, %ar1;
                setp.eq.u32     %r31, %r26, 21;
                setp.eq.u32     %r34, %r27, 69;
                selp.u32        %r37, 1, 0, %r31;
                selp.u32        %r38, 1, 0, %r34;
                and.b32 %value, %r37, %r38;

with this patch we now save an extra instruction and generate:

                mov.u32 %r26, %ar0;
                mov.u32 %r27, %ar1;
                setp.eq.u32     %r31, %r26, 21;
                setp.eq.u32     %r34, %r27, 69;
                and.pred        %r39, %r34, %r31;
                selp.u32        %value, 1, 0, %r39;

This patch has been tested (on top of the patch mentioned above) on
nvptx-none hosted on x86_64-pc-linux-gnu (including newlib) with a
make and make -k check with no new failures.

gcc/ChangeLog:

	* config/nvptx/nvptx.md (any_logic): Move code iterator earlier
	in machine description.
	(logic): Move code attribute earlier in machine description.
	(ilogic): New code attribute, like logic but "ior" for IOR.
	(and<mode>3, ior<mode>3, xor<mode>3): Delete. Replace with...
	(<ilogic><mode>3): New define_insn for HSDIM logic operations.
	(<ilogic>bi3): New define_insn for BI mode logic operations.
	(define_split): Lower logic operations from integer modes to
	BI mode predicate operations.

gcc/testsuite/ChangeLog:

	* gcc.target/nvptx/bool-1.c: Update.
	* gcc.target/nvptx/bool-2.c: New test case for and.pred.
	* gcc.target/nvptx/bool-3.c: New test case for or.pred.
	* gcc.target/nvptx/bool-4.c: New test case for xor.pred.

diff --git a/gcc/config/nvptx/nvptx.md b/gcc/config/nvptx/nvptx.md
index d19a687..107df74 100644 (file)
--- a/gcc/config/nvptx/nvptx.md
+++ b/gcc/config/nvptx/nvptx.md
@@ -801,26 +801,38 @@
 
 ;; Logical operations
 
-(define_insn "and<mode>3"
-  [(set (match_operand:BHSDIM 0 "nvptx_register_operand" "=R")
-       (and:BHSDIM (match_operand:BHSDIM 1 "nvptx_register_operand" "R")
-                   (match_operand:BHSDIM 2 "nvptx_nonmemory_operand" "Ri")))]
-  ""
-  "%.\\tand.b%T0\\t%0, %1, %2;")
+(define_code_iterator any_logic [and ior xor])
+(define_code_attr logic [(and "and") (ior "or") (xor "xor")])
+(define_code_attr ilogic [(and "and") (ior "ior") (xor "xor")])
 
-(define_insn "ior<mode>3"
-  [(set (match_operand:BHSDIM 0 "nvptx_register_operand" "=R")
-       (ior:BHSDIM (match_operand:BHSDIM 1 "nvptx_register_operand" "R")
-                   (match_operand:BHSDIM 2 "nvptx_nonmemory_operand" "Ri")))]
+(define_insn "<ilogic><mode>3"
+  [(set (match_operand:HSDIM 0 "nvptx_register_operand" "=R")
+       (any_logic:HSDIM
+         (match_operand:HSDIM 1 "nvptx_register_operand" "R")
+         (match_operand:HSDIM 2 "nvptx_nonmemory_operand" "Ri")))]
   ""
-  "%.\\tor.b%T0\\t%0, %1, %2;")
+  "%.\\t<logic>.b%T0\\t%0, %1, %2;")
 
-(define_insn "xor<mode>3"
-  [(set (match_operand:BHSDIM 0 "nvptx_register_operand" "=R")
-       (xor:BHSDIM (match_operand:BHSDIM 1 "nvptx_register_operand" "R")
-                   (match_operand:BHSDIM 2 "nvptx_nonmemory_operand" "Ri")))]
+(define_insn "<ilogic>bi3"
+  [(set (match_operand:BI 0 "nvptx_register_operand" "=R")
+       (any_logic:BI (match_operand:BI 1 "nvptx_register_operand" "R")
+                     (match_operand:BI 2 "nvptx_register_operand" "R")))]
   ""
-  "%.\\txor.b%T0\\t%0, %1, %2;")
+  "%.\\t<logic>.pred\\t%0, %1, %2;")
+
+(define_split
+  [(set (match_operand:HSDIM 0 "nvptx_register_operand")
+       (any_logic:HSDIM
+         (ne:HSDIM (match_operand:BI 1 "nvptx_register_operand")
+                   (const_int 0))
+         (ne:HSDIM (match_operand:BI 2 "nvptx_register_operand")
+                   (const_int 0))))]
+  "can_create_pseudo_p ()"
+  [(set (match_dup 3) (any_logic:BI (match_dup 1) (match_dup 2)))
+   (set (match_dup 0) (ne:HSDIM (match_dup 3) (const_int 0)))]
+{
+  operands[3] = gen_reg_rtx (BImode);
+})
 
 ;; Comparisons and branches
 
@@ -2042,9 +2054,6 @@
   }
   [(set_attr "atomic" "true")])
 
-(define_code_iterator any_logic [and ior xor])
-(define_code_attr logic [(and "and") (ior "or") (xor "xor")])
-
 (define_insn "atomic_fetch_<logic><mode>"
   [(set (match_operand:SDIM 1 "memory_operand" "+m")
        (unspec_volatile:SDIM

diff --git a/gcc/testsuite/gcc.target/nvptx/bool-1.c b/gcc/testsuite/gcc.target/nvptx/bool-1.c
index 58df2b0..9b8a2d4 100644 (file)
--- a/gcc/testsuite/gcc.target/nvptx/bool-1.c
+++ b/gcc/testsuite/gcc.target/nvptx/bool-1.c
@@ -12,5 +12,5 @@ foo (int x, int y)
 /* { dg-final { scan-assembler-not "cvt.u32.u8" } } */
 
 /* { dg-final { scan-assembler-times "setp.eq.u32" 2 } } */
-/* { dg-final { scan-assembler-times "selp.u32" 2 } } */
-/* { dg-final { scan-assembler-times "and.b32" 1 } } */
+/* { dg-final { scan-assembler-times "selp.u32" 1 } } */
+/* { dg-final { scan-assembler-times "and.pred" 1 } } */

diff --git a/gcc/testsuite/gcc.target/nvptx/bool-2.c b/gcc/testsuite/gcc.target/nvptx/bool-2.c
new file mode 100644 (file)
index 0000000..b779248
--- /dev/null
+++ b/gcc/testsuite/gcc.target/nvptx/bool-2.c
@@ -0,0 +1,14 @@
+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+
+int foo(int x, int y)
+{
+  return (x==21) && (y==69);
+}
+
+int bar(int x, int y)
+{
+  return (x==21) & (y==69);
+}
+
+/* { dg-final { scan-assembler-times "and.pred" 2 } } */

diff --git a/gcc/testsuite/gcc.target/nvptx/bool-3.c b/gcc/testsuite/gcc.target/nvptx/bool-3.c
new file mode 100644 (file)
index 0000000..ab4206a
--- /dev/null
+++ b/gcc/testsuite/gcc.target/nvptx/bool-3.c
@@ -0,0 +1,14 @@
+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+
+int foo(int x, int y)
+{
+  return (x==21) || (y==69);
+}
+
+int bar(int x, int y)
+{
+  return (x==21) | (y==69);
+}
+
+/* { dg-final { scan-assembler-times "or.pred" 2 } } */

diff --git a/gcc/testsuite/gcc.target/nvptx/bool-4.c b/gcc/testsuite/gcc.target/nvptx/bool-4.c
new file mode 100644 (file)
index 0000000..b588574
--- /dev/null
+++ b/gcc/testsuite/gcc.target/nvptx/bool-4.c
@@ -0,0 +1,9 @@
+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+
+int foo(int x, int y)
+{
+  return (x==21) ^ (y==69);
+}
+
+/* { dg-final { scan-assembler "xor.pred" } } */