@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.
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
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
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.
@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}
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}}
case CONST_FIXED:
case CLRSB:
case CLOBBER:
+ case SMUL_HIGHPART:
+ case UMUL_HIGHPART:
break;
case CONST_STRING:
/* 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 */
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:
}
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;
}
--- /dev/null
+/* { 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\[0-9\]+" } } */
--- /dev/null
+/* { 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\[0-9\]+" } } */
+
--- /dev/null
+/* { 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\[0-9\]+" } } */
--- /dev/null
+/* { 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\[0-9\]+" } } */
+
projects / thirdparty / gcc.git / commitdiff
