Introduce smul_highpart and umul_highpart RTX for high-part multiplications

This patch introduces new RTX codes to allow the RTL passes and
backends to consistently represent high-part multiplications.
Currently, the RTL used by different backends for expanding
smul<mode>3_highpart and umul<mode>3_highpart varies greatly,
with many but not all choosing to express this something like:

(define_insn "smuldi3_highpart"
  [(set (match_operand:DI 0 "nvptx_register_operand" "=R")
       (truncate:DI
        (lshiftrt:TI
         (mult:TI (sign_extend:TI
                   (match_operand:DI 1 "nvptx_register_operand" "R"))
                  (sign_extend:TI
                   (match_operand:DI 2 "nvptx_register_operand" "R")))
         (const_int 64))))]
  ""
  "%.\\tmul.hi.s64\\t%0, %1, %2;")

One complication with using this "widening multiplication" representation
is that it requires an intermediate in a wider mode, making it difficult
or impossible to encode a high-part multiplication of the widest supported
integer mode.  A second is that it can interfere with optimization; for
example simplify-rtx.c contains the comment:

   case TRUNCATE:
      /* Don't optimize (lshiftrt (mult ...)) as it would interfere
         with the umulXi3_highpart patterns.  */

Hopefully these problems are solved (or reduced) by introducing a
new canonical form for high-part multiplications in RTL passes.
This also simplifies insn patterns when one operand is constant.

Whilst implementing some constant folding simplifications and
compile-time evaluation of these new RTX codes, I noticed that
this functionality could also be added for the existing saturating
arithmetic RTX codes.  Then likewise when documenting these new RTX
codes, I also took the opportunity to silence the @xref warnings in
invoke.texi.

2021-10-07  Roger Sayle  <roger@nextmovesoftware.com>

gcc/ChangeLog
	* rtl.def (SMUL_HIGHPART, UMUL_HIGHPART): New RTX codes for
	representing signed and unsigned high-part multiplication resp.
	* simplify-rtx.c (simplify_binary_operation_1) [SMUL_HIGHPART,
	UMUL_HIGHPART]: Simplify high-part multiplications by zero.
	[SS_PLUS, US_PLUS, SS_MINUS, US_MINUS, SS_MULT, US_MULT,
	SS_DIV, US_DIV]: Similar simplifications for saturating
	arithmetic.
	(simplify_const_binary_operation) [SS_PLUS, US_PLUS, SS_MINUS,
	US_MINUS, SS_MULT, US_MULT, SMUL_HIGHPART, UMUL_HIGHPART]:
	Implement compile-time evaluation for constant operands.

	* dwarf2out.c (mem_loc_descriptor): Skip SMUL_HIGHPART and
	UMUL_HIGHPART.
	* doc/rtl.texi (smul_highpart, umul_highpart): Document RTX codes.
	* doc/md.texi (smul@var{m}3_highpart, umul@var{m3}_highpart):
	Mention the new smul_highpart and umul_highpart RTX codes.
	* doc/invoke.texi: Silence @xref "compilation" warnings.

gcc/testsuite/ChangeLog
	* gcc.target/i386/sse2-mmx-paddsb-2.c: New test case.
	* gcc.target/i386/sse2-mmx-paddusb-2.c: New test case.
	* gcc.target/i386/sse2-mmx-psubsb-2.c: New test case.
	* gcc.target/i386/sse2-mmx-psubusb-2.c: New test case.

gcc/doc/invoke.texi

@@ -3126,7 +3126,7 @@ errors if these functions are not inlined everywhere they are called.
 @itemx -fno-modules-ts
 @opindex fmodules-ts
 @opindex fno-modules-ts
-Enable support for C++20 modules (@xref{C++ Modules}).  The
+Enable support for C++20 modules (@pxref{C++ Modules}).  The
 @option{-fno-modules-ts} is usually not needed, as that is the
 default.  Even though this is a C++20 feature, it is not currently
 implicitly enabled by selecting that standard version.
@@ -33608,7 +33608,7 @@ version selected, although in pre-C++20 versions, it is of course an
 extension.
 
 No new source file suffixes are required or supported.  If you wish to
-use a non-standard suffix (@xref{Overall Options}), you also need
+use a non-standard suffix (@pxref{Overall Options}), you also need
 to provide a @option{-x c++} option too.@footnote{Some users like to
 distinguish module interface files with a new suffix, such as naming
 the source @code{module.cppm}, which involves
@@ -33670,8 +33670,8 @@ to be resolved at the end of compilation.  Without this, imported
 macros are only resolved when expanded or (re)defined.  This option
 detects conflicting import definitions for all macros.
 
-@xref{C++ Module Mapper} for details of the @option{-fmodule-mapper}
-family of options.
+For details of the @option{-fmodule-mapper} family of options,
+@pxref{C++ Module Mapper}.
 
 @menu
 * C++ Module Mapper::       Module Mapper
@@ -33888,8 +33888,8 @@ dialect used and imports of the module.@footnote{The precise contents
 of this output may change.} The timestamp is the same value as that
 provided by the @code{__DATE__} & @code{__TIME__} macros, and may be
 explicitly specified with the environment variable
-@code{SOURCE_DATE_EPOCH}.  @xref{Environment Variables} for further
-details.
+@code{SOURCE_DATE_EPOCH}.  For further details
+@pxref{Environment Variables}.
 
 A set of related CMIs may be copied, provided the relative pathnames
 are preserved.

gcc/doc/md.texi

@@ -5776,11 +5776,13 @@ multiplication.
 @item @samp{smul@var{m}3_highpart}
 Perform a signed multiplication of operands 1 and 2, which have mode
 @var{m}, and store the most significant half of the product in operand 0.
-The least significant half of the product is discarded.
+The least significant half of the product is discarded.  This may be
+represented in RTL using a @code{smul_highpart} RTX expression.
 
 @cindex @code{umul@var{m}3_highpart} instruction pattern
 @item @samp{umul@var{m}3_highpart}
-Similar, but the multiplication is unsigned.
+Similar, but the multiplication is unsigned.  This may be represented
+in RTL using an @code{umul_highpart} RTX expression.
 
 @cindex @code{madd@var{m}@var{n}4} instruction pattern
 @item @samp{madd@var{m}@var{n}4}

gcc/doc/rtl.texi

@@ -2524,7 +2524,19 @@ not be the same.
 For unsigned widening multiplication, use the same idiom, but with
 @code{zero_extend} instead of @code{sign_extend}.
 
+@findex smul_highpart
+@findex umul_highpart
+@cindex high-part multiplication
+@cindex multiplication high part
+@item (smul_highpart:@var{m} @var{x} @var{y})
+@itemx (umul_highpart:@var{m} @var{x} @var{y})
+Represents the high-part multiplication of @var{x} and @var{y} carried
+out in machine mode @var{m}.  @code{smul_highpart} returns the high part
+of a signed multiplication, @code{umul_highpart} returns the high part
+of an unsigned multiplication.
+
 @findex fma
+@cindex fused multiply-add
 @item (fma:@var{m} @var{x} @var{y} @var{z})
 Represents the @code{fma}, @code{fmaf}, and @code{fmal} builtin
 functions, which compute @samp{@var{x} * @var{y} + @var{z}}

gcc/dwarf2out.c

@@ -16809,6 +16809,8 @@ mem_loc_descriptor (rtx rtl, machine_mode mode,
     case CONST_FIXED:
     case CLRSB:
     case CLOBBER:
+    case SMUL_HIGHPART:
+    case UMUL_HIGHPART:
       break;
 
     case CONST_STRING:

gcc/rtl.def

@@ -467,6 +467,11 @@ DEF_RTL_EXPR(SS_MULT, "ss_mult", "ee", RTX_COMM_ARITH)
 /* Multiplication with unsigned saturation */
 DEF_RTL_EXPR(US_MULT, "us_mult", "ee", RTX_COMM_ARITH)
 
+/* Signed high-part multiplication.  */
+DEF_RTL_EXPR(SMUL_HIGHPART, "smul_highpart", "ee", RTX_COMM_ARITH)
+/* Unsigned high-part multiplication.  */
+DEF_RTL_EXPR(UMUL_HIGHPART, "umul_highpart", "ee", RTX_COMM_ARITH)
+
 /* Operand 0 divided by operand 1.  */
 DEF_RTL_EXPR(DIV, "div", "ee", RTX_BIN_ARITH)
 /* Division with signed saturation */

gcc/simplify-rtx.c

@@ -4142,11 +4142,36 @@ simplify_context::simplify_binary_operation_1 (rtx_code code,
     case US_PLUS:
     case SS_MINUS:
     case US_MINUS:
+      /* Simplify x +/- 0 to x, if possible.  */
+      if (trueop1 == CONST0_RTX (mode))
+	return op0;
+      return 0;
+
     case SS_MULT:
     case US_MULT:
+      /* Simplify x * 0 to 0, if possible.  */
+      if (trueop1 == CONST0_RTX (mode)
+	  && !side_effects_p (op0))
+	return op1;
+
+      /* Simplify x * 1 to x, if possible.  */
+      if (trueop1 == CONST1_RTX (mode))
+	return op0;
+      return 0;
+
+    case SMUL_HIGHPART:
+    case UMUL_HIGHPART:
+      /* Simplify x * 0 to 0, if possible.  */
+      if (trueop1 == CONST0_RTX (mode)
+	  && !side_effects_p (op0))
+	return op1;
+      return 0;
+
     case SS_DIV:
     case US_DIV:
-      /* ??? There are simplifications that can be done.  */
+      /* Simplify x / 1 to x, if possible.  */
+      if (trueop1 == CONST1_RTX (mode))
+	return op0;
       return 0;
 
     case VEC_SERIES:
@@ -5012,6 +5037,51 @@ simplify_const_binary_operation (enum rtx_code code, machine_mode mode,
 	      }
 	    break;
 	  }
+
+	case SS_PLUS:
+	  result = wi::add (pop0, pop1, SIGNED, &overflow);
+ clamp_signed_saturation:
+	  if (overflow == wi::OVF_OVERFLOW)
+	    result = wi::max_value (GET_MODE_PRECISION (int_mode), SIGNED);
+	  else if (overflow == wi::OVF_UNDERFLOW)
+	    result = wi::min_value (GET_MODE_PRECISION (int_mode), SIGNED);
+	  else if (overflow != wi::OVF_NONE)
+	    return NULL_RTX;
+	  break;
+
+	case US_PLUS:
+	  result = wi::add (pop0, pop1, UNSIGNED, &overflow);
+ clamp_unsigned_saturation: 
+	  if (overflow != wi::OVF_NONE)
+	    result = wi::max_value (GET_MODE_PRECISION (int_mode), UNSIGNED);
+	  break;
+
+	case SS_MINUS:
+	  result = wi::sub (pop0, pop1, SIGNED, &overflow);
+	  goto clamp_signed_saturation;
+
+	case US_MINUS:
+	  result = wi::sub (pop0, pop1, UNSIGNED, &overflow);
+	  if (overflow != wi::OVF_NONE)
+	    result = wi::min_value (GET_MODE_PRECISION (int_mode), UNSIGNED);
+	  break;
+
+	case SS_MULT:
+	  result = wi::mul (pop0, pop1, SIGNED, &overflow);
+	  goto clamp_signed_saturation;
+
+	case US_MULT:
+	  result = wi::mul (pop0, pop1, UNSIGNED, &overflow);
+	  goto clamp_unsigned_saturation;
+
+	case SMUL_HIGHPART:
+	  result = wi::mul_high (pop0, pop1, SIGNED);
+	  break;
+
+	case UMUL_HIGHPART:
+	  result = wi::mul_high (pop0, pop1, UNSIGNED);
+	  break;
+
 	default:
 	  return NULL_RTX;
 	}

gcc/testsuite/gcc.target/i386/sse2-mmx-paddsb-2.c

@@ -0,0 +1,33 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -msse2" } */
+
+typedef char v8qi __attribute__ ((vector_size (8)));
+
+char foo()
+{
+  v8qi tx = { 1, 0, 0, 0, 0, 0, 0, 0 };
+  v8qi ty = { 2, 0, 0, 0, 0, 0, 0, 0 };
+  v8qi t = __builtin_ia32_paddsb(tx, ty);
+  return t[0];
+}
+
+char bar()
+{
+  v8qi tx = { 100, 0, 0, 0, 0, 0, 0, 0 };
+  v8qi ty = { 100, 0, 0, 0, 0, 0, 0, 0 };
+  v8qi t = __builtin_ia32_paddsb(tx, ty);
+  return t[0];
+}
+
+char baz()
+{
+  v8qi tx = { -100, 0, 0, 0, 0, 0, 0, 0 };
+  v8qi ty = { -100, 0, 0, 0, 0, 0, 0, 0 };
+  v8qi t = __builtin_ia32_paddsb(tx, ty);
+  return t[0];
+}
+
+/* { dg-final { scan-assembler-times "movl\[ \\t\]+\\\$3," 1 } } */
+/* { dg-final { scan-assembler-times "movl\[ \\t\]+\\\$127," 1 } } */
+/* { dg-final { scan-assembler-times "movl\[ \\t\]+\\\$-128," 1 } } */
+/* { dg-final { scan-assembler-not "paddsb\[ \\t\]+%xmm\[0-9\]+" } } */

gcc/testsuite/gcc.target/i386/sse2-mmx-paddusb-2.c

@@ -0,0 +1,25 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -msse2" } */
+
+typedef char v8qi __attribute__ ((vector_size (8)));
+
+char foo()
+{
+  v8qi tx = { 1, 0, 0, 0, 0, 0, 0, 0 };
+  v8qi ty = { 2, 0, 0, 0, 0, 0, 0, 0 };
+  v8qi t = __builtin_ia32_paddusb(tx, ty);
+  return t[0];
+}
+
+char bar()
+{
+  v8qi tx = { 200, 0, 0, 0, 0, 0, 0, 0 };
+  v8qi ty = { 200, 0, 0, 0, 0, 0, 0, 0 };
+  v8qi t = __builtin_ia32_paddusb(tx, ty);
+  return t[0];
+}
+
+/* { dg-final { scan-assembler-times "movl\[ \\t\]+\\\$3," 1 } } */
+/* { dg-final { scan-assembler-times "movl\[ \\t\]+\\\$-1," 1 } } */
+/* { dg-final { scan-assembler-not "paddusb\[ \\t\]+%xmm\[0-9\]+" } } */
+

gcc/testsuite/gcc.target/i386/sse2-mmx-psubsb-2.c

@@ -0,0 +1,33 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -msse2" } */
+
+typedef char v8qi __attribute__ ((vector_size (8)));
+
+char foo()
+{
+  v8qi tx = { 5, 0, 0, 0, 0, 0, 0, 0 };
+  v8qi ty = { 2, 0, 0, 0, 0, 0, 0, 0 };
+  v8qi t = __builtin_ia32_psubsb(tx, ty);
+  return t[0];
+}
+
+char bar()
+{
+  v8qi tx = { -100, 0, 0, 0, 0, 0, 0, 0 };
+  v8qi ty = { 100, 0, 0, 0, 0, 0, 0, 0 };
+  v8qi t = __builtin_ia32_psubsb(tx, ty);
+  return t[0];
+}
+
+char baz()
+{
+  v8qi tx = { 100, 0, 0, 0, 0, 0, 0, 0 };
+  v8qi ty = { -100, 0, 0, 0, 0, 0, 0, 0 };
+  v8qi t = __builtin_ia32_psubsb(tx, ty);
+  return t[0];
+}
+
+/* { dg-final { scan-assembler-times "movl\[ \\t\]+\\\$3," 1 } } */
+/* { dg-final { scan-assembler-times "movl\[ \\t\]+\\\$-128," 1 } } */
+/* { dg-final { scan-assembler-times "movl\[ \\t\]+\\\$127," 1 } } */
+/* { dg-final { scan-assembler-not "paddsb\[ \\t\]+%xmm\[0-9\]+" } } */

gcc/testsuite/gcc.target/i386/sse2-mmx-psubusb-2.c

@@ -0,0 +1,25 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -msse2" } */
+
+typedef char v8qi __attribute__ ((vector_size (8)));
+
+char foo()
+{
+  v8qi tx = { 5, 0, 0, 0, 0, 0, 0, 0 };
+  v8qi ty = { 2, 0, 0, 0, 0, 0, 0, 0 };
+  v8qi t = __builtin_ia32_psubusb(tx, ty);
+  return t[0];
+}
+
+char bar()
+{
+  v8qi tx = { 100, 0, 0, 0, 0, 0, 0, 0 };
+  v8qi ty = { 200, 0, 0, 0, 0, 0, 0, 0 };
+  v8qi t = __builtin_ia32_psubusb(tx, ty);
+  return t[0];
+}
+
+/* { dg-final { scan-assembler-times "movl\[ \\t\]+\\\$3," 1 } } */
+/* { dg-final { scan-assembler-times "xorl\[ \\t\]+" 1 } } */
+/* { dg-final { scan-assembler-not "psubusb\[ \\t\]+%xmm\[0-9\]+" } } */
+