nvptx: Expand QI mode operations using SI mode instructions

One of the unusual target features of the Nvidia PTX ISA is that it
doesn't provide QI mode (byte sized) operations or registers.  Somewhat
conventionally, 8-bit quantities are read from/written to memory using
special instructions, but stored internally using SImode (32-bit) registers.
GCC's middle-end accomodates targets without QImode optabs, by widening
operations until suitable support is found, and with the current nvptx
backend this means 16-bit HImode operations.  The inconvenience is that
nvptx is also a TARGET_TRULY_NOOP_TRUNCATION=false target, meaning that
additional instructions are required to convert between the SImode
registers used to hold QImode values, and the HImode registers used to
operate on them (and back again).  This results in a large amount of
shuffling and type conversion in code dealing with bytes, i.e. using
char or Boolean types.

This patch improves the situation by providing expanders in the nvptx
machine description to perform QImode operations natively in SImode
instead of HImode.  An alternate implementation might be to provide
some form of target hook to specify which fallback modes to use during
RTL expansion, but I think this requirement is unusual, and a solution
entirely in the nvptx backend doesn't disturb/affect other targets.

The improvements can be quite dramatic, as shown in the example below:

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

previously with -O2 required 15 instructions:

                mov.u32 %r26, %ar0;
                mov.u32 %r27, %ar1;
                setp.eq.u32     %r31, %r26, 21;
                selp.u32        %r30, 1, 0, %r31;
                mov.u32 %r29, %r30;
                setp.eq.u32     %r34, %r27, 69;
                selp.u32        %r33, 1, 0, %r34;
                mov.u32 %r32, %r33;
                cvt.u16.u8      %r39, %r29;
                mov.u16 %r36, %r39;
                cvt.u16.u8      %r39, %r32;
                mov.u16 %r37, %r39;
                and.b16 %r35, %r36, %r37;
                cvt.u32.u16     %r38, %r35;
                cvt.u32.u8      %value, %r38;

with this patch, now requires only 7 instructions:

                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;

This patch has been tested 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 (cmp<mode>): Renamed from *cmp<mode>.
	(setcc<mode>_from_bi): Additionally support QImode.
	(extendbi<mode>2): Additionally support QImode.
	(zero_extendbi<mode>2): Additionally support QImode.
	(any_sbinary, any_ubinary, any_sunary, any_uunary): New code
	iterators for signed and unsigned, binary and unary operations.
	(<sbinary>qi3, <ubinary>qi3, <sunary>qi2, <uunary>qi2): New
	expanders to perform QImode operations using SImode instructions.
	(cstoreqi4): New define_expand.
	(*ext_truncsi2_qi): New define_insn.
	(*zext_truncsi2_qi): New define_insn.

gcc/testsuite/ChangeLog:

	* gcc.target/nvptx/bool-1.c: New test case.

2 files changed, 123 insertions, 7 deletions

diff --git a/gcc/config/nvptx/nvptx.md b/gcc/config/nvptx/nvptx.md
index e26d24e..f53809ea 100644
--- a/gcc/config/nvptx/nvptx.md
+++ b/gcc/config/nvptx/nvptx.md
@@ -767,7 +767,7 @@
 
 ;; Comparisons and branches
 
-(define_insn "*cmp<mode>"
+(define_insn "cmp<mode>"
   [(set (match_operand:BI 0 "nvptx_register_operand" "=R")
 	(match_operator:BI 1 "nvptx_comparison_operator"
 	   [(match_operand:HSDIM 2 "nvptx_register_operand" "R")
@@ -879,22 +879,22 @@
 ;; Conditional stores
 
 (define_insn "setcc<mode>_from_bi"
-  [(set (match_operand:HSDIM 0 "nvptx_register_operand" "=R")
-	(ne:HSDIM (match_operand:BI 1 "nvptx_register_operand" "R")
+  [(set (match_operand:QHSDIM 0 "nvptx_register_operand" "=R")
+	(ne:QHSDIM (match_operand:BI 1 "nvptx_register_operand" "R")
 		   (const_int 0)))]
   ""
   "%.\\tselp%t0\\t%0, 1, 0, %1;")
 
 (define_insn "extendbi<mode>2"
-  [(set (match_operand:HSDIM 0 "nvptx_register_operand" "=R")
-	(sign_extend:HSDIM
+  [(set (match_operand:QHSDIM 0 "nvptx_register_operand" "=R")
+	(sign_extend:QHSDIM
 	 (match_operand:BI 1 "nvptx_register_operand" "R")))]
   ""
   "%.\\tselp%t0\\t%0, -1, 0, %1;")
 
 (define_insn "zero_extendbi<mode>2"
-  [(set (match_operand:HSDIM 0 "nvptx_register_operand" "=R")
-	(zero_extend:HSDIM
+  [(set (match_operand:QHSDIM 0 "nvptx_register_operand" "=R")
+	(zero_extend:QHSDIM
 	 (match_operand:BI 1 "nvptx_register_operand" "R")))]
   ""
   "%.\\tselp%t0\\t%0, 1, 0, %1;")
@@ -2117,3 +2117,103 @@
     return nvptx_output_red_partition (operands[0], operands[1]);
   }
   [(set_attr "predicable" "false")])
+
+;; Expand QI mode operations using SI mode instructions.
+(define_code_iterator any_sbinary [plus minus smin smax])
+(define_code_attr sbinary [(plus "add") (minus "sub") (smin "smin") (smax "smax")])
+
+(define_code_iterator any_ubinary [and ior xor umin umax])
+(define_code_attr ubinary [(and "and") (ior "ior") (xor "xor") (umin "umin")
+			   (umax "umax")])
+
+(define_code_iterator any_sunary [neg abs])
+(define_code_attr sunary [(neg "neg") (abs "abs")])
+
+(define_code_iterator any_uunary [not])
+(define_code_attr uunary [(not "one_cmpl")])
+
+(define_expand "<sbinary>qi3"
+  [(set (match_operand:QI 0 "nvptx_register_operand")
+	(any_sbinary:QI (match_operand:QI 1 "nvptx_nonmemory_operand")
+			(match_operand:QI 2 "nvptx_nonmemory_operand")))]
+  ""
+{
+  rtx reg = gen_reg_rtx (SImode);
+  rtx op0 = convert_modes (SImode, QImode, operands[1], 0);
+  rtx op1 = convert_modes (SImode, QImode, operands[2], 0);
+  if (<CODE> == MINUS)
+    op0 = force_reg (SImode, op0);
+  emit_insn (gen_<sbinary>si3 (reg, op0, op1));
+  emit_insn (gen_truncsiqi2 (operands[0], reg));
+  DONE;
+})
+
+(define_expand "<ubinary>qi3"
+  [(set (match_operand:QI 0 "nvptx_register_operand")
+	(any_ubinary:QI (match_operand:QI 1 "nvptx_nonmemory_operand")
+			(match_operand:QI 2 "nvptx_nonmemory_operand")))]
+  ""
+{
+  rtx reg = gen_reg_rtx (SImode);
+  rtx op0 = convert_modes (SImode, QImode, operands[1], 1);
+  rtx op1 = convert_modes (SImode, QImode, operands[2], 1);
+  emit_insn (gen_<ubinary>si3 (reg, op0, op1));
+  emit_insn (gen_truncsiqi2 (operands[0], reg));
+  DONE;
+})
+
+(define_expand "<sunary>qi2"
+  [(set (match_operand:QI 0 "nvptx_register_operand")
+	(any_sunary:QI (match_operand:QI 1 "nvptx_nonmemory_operand")))]
+  ""
+{
+  rtx reg = gen_reg_rtx (SImode);
+  rtx op0 = convert_modes (SImode, QImode, operands[1], 0);
+  emit_insn (gen_<sunary>si2 (reg, op0));
+  emit_insn (gen_truncsiqi2 (operands[0], reg));
+  DONE;
+})
+
+(define_expand "<uunary>qi2"
+  [(set (match_operand:QI 0 "nvptx_register_operand")
+	(any_uunary:QI (match_operand:QI 1 "nvptx_nonmemory_operand")))]
+  ""
+{
+  rtx reg = gen_reg_rtx (SImode);
+  rtx op0 = convert_modes (SImode, QImode, operands[1], 1);
+  emit_insn (gen_<uunary>si2 (reg, op0));
+  emit_insn (gen_truncsiqi2 (operands[0], reg));
+  DONE;
+})
+
+(define_expand "cstoreqi4"
+  [(set (match_operand:SI 0 "nvptx_register_operand")
+	(match_operator:SI 1 "nvptx_comparison_operator"
+	  [(match_operand:QI 2 "nvptx_nonmemory_operand")
+	   (match_operand:QI 3 "nvptx_nonmemory_operand")]))]
+  ""
+{
+  rtx reg = gen_reg_rtx (BImode);
+  enum rtx_code code = GET_CODE (operands[1]);
+  int unsignedp = unsigned_condition_p (code);
+  rtx op2 = convert_modes (SImode, QImode, operands[2], unsignedp);
+  rtx op3 = convert_modes (SImode, QImode, operands[3], unsignedp);
+  rtx cmp = gen_rtx_fmt_ee (code, SImode, op2, op3);
+  emit_insn (gen_cmpsi (reg, cmp, op2, op3));
+  emit_insn (gen_setccsi_from_bi (operands[0], reg));
+  DONE;
+})
+
+(define_insn "*ext_truncsi2_qi"
+  [(set (match_operand:SI 0 "nvptx_register_operand" "=R")
+	(sign_extend:SI
+	 (truncate:QI (match_operand:SI 1 "nvptx_register_operand" "R"))))]
+  ""
+  "%.\\tcvt.s32.s8\\t%0, %1;")
+
+(define_insn "*zext_truncsi2_qi"
+  [(set (match_operand:SI 0 "nvptx_register_operand" "=R")
+	(zero_extend:SI
+	 (truncate:QI (match_operand:SI 1 "nvptx_register_operand" "R"))))]
+  ""
+  "%.\\tcvt.u32.u8\\t%0, %1;")
diff --git a/gcc/testsuite/gcc.target/nvptx/bool-1.c b/gcc/testsuite/gcc.target/nvptx/bool-1.c
new file mode 100644
index 0000000..58df2b0
--- /dev/null
+++ b/gcc/testsuite/gcc.target/nvptx/bool-1.c
@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+
+int
+foo (int x, int y)
+{
+  return (x == 21) && (y == 69);
+}
+
+/* { dg-final { scan-assembler-not "cvt.u16.u8" } } */
+/* { dg-final { scan-assembler-not "cvt.u32.u16" } } */
+/* { 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 } } */