gcc-4.6-source 4.6.4-6ubuntu2 / usr / src / gcc-4.6 / debian / patches / gcc-linaro-doc.diff

# DP: Changes for the Linaro 4.6-2013.04 release (documentation).

--- a/src/gcc/doc/invoke.texi
+++ b/src/gcc/doc/invoke.texi
@@ -8728,6 +8728,10 @@
 The maximum number of best instructions in the ready list that are considered
 for renaming in the selective scheduler.  The default value is 2.
 
+@item sms-min-sc
+The minimum value of stage count that swing modulo scheduler will
+generate.  The default value is 2.
+
 @item max-last-value-rtl
 The maximum size measured as number of RTLs that can be recorded in an expression
 in combiner for a pseudo register as last known value of that register.  The default
@@ -8907,6 +8911,11 @@
 The maximum number of namespaces to consult for suggestions when C++
 name lookup fails for an identifier.  The default is 1000.
 
+@item max-stores-to-sink
+The maximum number of conditional stores paires that can be sunk.  Set to 0
+if either vectorization (@option{-ftree-vectorize}) or if-conversion
+(@option{-ftree-loop-if-convert}) is disabled.  The default is 2.
+
 @end table
 @end table
 
@@ -10196,12 +10205,23 @@
 @samp{arm10e}, @samp{arm1020e}, @samp{arm1022e},
 @samp{arm1136j-s}, @samp{arm1136jf-s}, @samp{mpcore}, @samp{mpcorenovfp},
 @samp{arm1156t2-s}, @samp{arm1156t2f-s}, @samp{arm1176jz-s}, @samp{arm1176jzf-s},
-@samp{cortex-a5}, @samp{cortex-a8}, @samp{cortex-a9}, @samp{cortex-a15},
-@samp{cortex-r4}, @samp{cortex-r4f}, @samp{cortex-m4}, @samp{cortex-m3},
+@samp{cortex-a5}, @samp{cortex-a7}, @samp{cortex-a8}, @samp{cortex-a9}, 
+@samp{cortex-a15}, @samp{cortex-r4}, @samp{cortex-r4f}, @samp{cortex-r5},
+@samp{cortex-m4}, @samp{cortex-m3},
 @samp{cortex-m1},
 @samp{cortex-m0},
 @samp{xscale}, @samp{iwmmxt}, @samp{iwmmxt2}, @samp{ep9312}.
 
+
+@option{-mcpu=generic-@var{arch}} is also permissible, and is
+equivalent to @option{-march=@var{arch} -mtune=generic-@var{arch}}.
+See @option{-mtune} for more information.
+
+@option{-mcpu=native} causes the compiler to auto-detect the CPU
+of the build computer.  At present, this feature is only supported on
+Linux, and not all architectures are recognised.  If the auto-detect is
+unsuccessful the option has no effect.
+
 @item -mtune=@var{name}
 @opindex mtune
 This option is very similar to the @option{-mcpu=} option, except that
@@ -10213,6 +10233,18 @@
 For some ARM implementations better performance can be obtained by using
 this option.
 
+@option{-mtune=generic-@var{arch}} specifies that GCC should tune the
+performance for a blend of processors within architecture @var{arch}.
+The aim is to generate code that run well on the current most popular
+processors, balancing between optimizations that benefit some CPUs in the
+range, and avoiding performance pitfalls of other CPUs.  The effects of
+this option may change in future GCC versions as CPU models come and go.
+
+@option{-mtune=native} causes the compiler to auto-detect the CPU
+of the build computer.  At present, this feature is only supported on
+Linux, and not all architectures are recognised.  If the auto-detect is
+unsuccessful the option has no effect.
+
 @item -march=@var{name}
 @opindex march
 This specifies the name of the target ARM architecture.  GCC uses this
@@ -10226,6 +10258,11 @@
 @samp{armv7}, @samp{armv7-a}, @samp{armv7-r}, @samp{armv7-m},
 @samp{iwmmxt}, @samp{iwmmxt2}, @samp{ep9312}.
 
+@option{-march=native} causes the compiler to auto-detect the architecture
+of the build computer.  At present, this feature is only supported on
+Linux, and not all architectures are recognised.  If the auto-detect is
+unsuccessful the option has no effect.
+
 @item -mfpu=@var{name}
 @itemx -mfpe=@var{number}
 @itemx -mfp=@var{number}
--- a/src/gcc/doc/md.texi
+++ b/src/gcc/doc/md.texi
@@ -3935,6 +3935,48 @@
 consecutive memory locations, operand 1 is the first register, and
 operand 2 is a constant: the number of consecutive registers.
 
+@cindex @code{vec_load_lanes@var{m}@var{n}} instruction pattern
+@item @samp{vec_load_lanes@var{m}@var{n}}
+Perform an interleaved load of several vectors from memory operand 1
+into register operand 0.  Both operands have mode @var{m}.  The register
+operand is viewed as holding consecutive vectors of mode @var{n},
+while the memory operand is a flat array that contains the same number
+of elements.  The operation is equivalent to:
+
+@smallexample
+int c = GET_MODE_SIZE (@var{m}) / GET_MODE_SIZE (@var{n});
+for (j = 0; j < GET_MODE_NUNITS (@var{n}); j++)
+  for (i = 0; i < c; i++)
+    operand0[i][j] = operand1[j * c + i];
+@end smallexample
+
+For example, @samp{vec_load_lanestiv4hi} loads 8 16-bit values
+from memory into a register of mode @samp{TI}@.  The register
+contains two consecutive vectors of mode @samp{V4HI}@.
+
+This pattern can only be used if:
+@smallexample
+TARGET_ARRAY_MODE_SUPPORTED_P (@var{n}, @var{c})
+@end smallexample
+is true.  GCC assumes that, if a target supports this kind of
+instruction for some mode @var{n}, it also supports unaligned
+loads for vectors of mode @var{n}.
+
+@cindex @code{vec_store_lanes@var{m}@var{n}} instruction pattern
+@item @samp{vec_store_lanes@var{m}@var{n}}
+Equivalent to @samp{vec_load_lanes@var{m}@var{n}}, with the memory
+and register operands reversed.  That is, the instruction is
+equivalent to:
+
+@smallexample
+int c = GET_MODE_SIZE (@var{m}) / GET_MODE_SIZE (@var{n});
+for (j = 0; j < GET_MODE_NUNITS (@var{n}); j++)
+  for (i = 0; i < c; i++)
+    operand0[j * c + i] = operand1[i][j];
+@end smallexample
+
+for a memory operand 0 and register operand 1.
+
 @cindex @code{vec_set@var{m}} instruction pattern
 @item @samp{vec_set@var{m}}
 Set given field in the vector value.  Operand 0 is the vector to modify,
@@ -4188,6 +4230,17 @@
 elements of the two vectors, and put the N/2 products of size 2*S in the
 output vector (operand 0).
 
+@cindex @code{vec_widen_ushiftl_hi_@var{m}} instruction pattern
+@cindex @code{vec_widen_ushiftl_lo_@var{m}} instruction pattern
+@cindex @code{vec_widen_sshiftl_hi_@var{m}} instruction pattern
+@cindex @code{vec_widen_sshiftl_lo_@var{m}} instruction pattern
+@item @samp{vec_widen_ushiftl_hi_@var{m}}, @samp{vec_widen_ushiftl_lo_@var{m}}
+@itemx @samp{vec_widen_sshiftl_hi_@var{m}}, @samp{vec_widen_sshiftl_lo_@var{m}}
+Signed/Unsigned widening shift left.  The first input (operand 1) is a vector
+with N signed/unsigned elements of size S@.  Operand 2 is a constant.  Shift
+the high/low elements of operand 1, and put the N/2 results of size 2*S in the
+output vector (operand 0).
+
 @cindex @code{mulhisi3} instruction pattern
 @item @samp{mulhisi3}
 Multiply operands 1 and 2, which have mode @code{HImode}, and store
@@ -5891,6 +5944,23 @@
 will be written using @code{zero_extract} rather than the equivalent
 @code{and} or @code{sign_extract} operations.
 
+@cindex @code{mult}, canonicalization of
+@item
+@code{(sign_extend:@var{m1} (mult:@var{m2} (sign_extend:@var{m2} @var{x})
+(sign_extend:@var{m2} @var{y})))} is converted to @code{(mult:@var{m1}
+(sign_extend:@var{m1} @var{x}) (sign_extend:@var{m1} @var{y}))}, and likewise
+for @code{zero_extend}.
+
+@item
+@code{(sign_extend:@var{m1} (mult:@var{m2} (ashiftrt:@var{m2}
+@var{x} @var{s}) (sign_extend:@var{m2} @var{y})))} is converted
+to @code{(mult:@var{m1} (sign_extend:@var{m1} (ashiftrt:@var{m2}
+@var{x} @var{s})) (sign_extend:@var{m1} @var{y}))}, and likewise for
+patterns using @code{zero_extend} and @code{lshiftrt}.  If the second
+operand of @code{mult} is also a shift, then that is extended also.
+This transformation is only applied when it can be proven that the
+original operation had sufficient precision to prevent overflow.
+
 @end itemize
 
 Further canonicalization rules are defined in the function
--- a/src/gcc/doc/tm.texi
+++ b/src/gcc/doc/tm.texi
@@ -2541,7 +2541,7 @@
 register, so @code{TARGET_PREFERRED_RELOAD_CLASS} returns @code{NO_REGS} when
 @var{x} is a floating-point constant.  If the constant can't be loaded
 into any kind of register, code generation will be better if
-@code{LEGITIMATE_CONSTANT_P} makes the constant illegitimate instead
+@code{TARGET_LEGITIMATE_CONSTANT_P} makes the constant illegitimate instead
 of using @code{TARGET_PREFERRED_RELOAD_CLASS}.
 
 If an insn has pseudos in it after register allocation, reload will go
@@ -2578,8 +2578,8 @@
 register, so @code{PREFERRED_RELOAD_CLASS} returns @code{NO_REGS} when
 @var{x} is a floating-point constant.  If the constant can't be loaded
 into any kind of register, code generation will be better if
-@code{LEGITIMATE_CONSTANT_P} makes the constant illegitimate instead
-of using @code{PREFERRED_RELOAD_CLASS}.
+@code{TARGET_LEGITIMATE_CONSTANT_P} makes the constant illegitimate instead
+of using @code{TARGET_PREFERRED_RELOAD_CLASS}.
 
 If an insn has pseudos in it after register allocation, reload will go
 through the alternatives and call repeatedly @code{PREFERRED_RELOAD_CLASS}
@@ -4327,6 +4327,34 @@
 must have move patterns for this mode.
 @end deftypefn
 
+@deftypefn {Target Hook} bool TARGET_ARRAY_MODE_SUPPORTED_P (enum machine_mode @var{mode}, unsigned HOST_WIDE_INT @var{nelems})
+Return true if GCC should try to use a scalar mode to store an array
+of @var{nelems} elements, given that each element has mode @var{mode}.
+Returning true here overrides the usual @code{MAX_FIXED_MODE} limit
+and allows GCC to use any defined integer mode.
+
+One use of this hook is to support vector load and store operations
+that operate on several homogeneous vectors.  For example, ARM NEON
+has operations like:
+
+@smallexample
+int8x8x3_t vld3_s8 (const int8_t *)
+@end smallexample
+
+where the return type is defined as:
+
+@smallexample
+typedef struct int8x8x3_t
+@{
+  int8x8_t val[3];
+@} int8x8x3_t;
+@end smallexample
+
+If this hook allows @code{val} to have a scalar mode, then
+@code{int8x8x3_t} can have the same mode.  GCC can then store
+@code{int8x8x3_t}s in registers rather than forcing them onto the stack.
+@end deftypefn
+
 @deftypefn {Target Hook} bool TARGET_SMALL_REGISTER_CLASSES_FOR_MODE_P (enum machine_mode @var{mode})
 Define this to return nonzero for machine modes for which the port has
 small register classes.  If this target hook returns nonzero for a given
@@ -5585,13 +5613,13 @@
 @code{TARGET_MODE_DEPENDENT_ADDRESS_P} target hook.
 @end defmac
 
-@defmac LEGITIMATE_CONSTANT_P (@var{x})
-A C expression that is nonzero if @var{x} is a legitimate constant for
-an immediate operand on the target machine.  You can assume that
-@var{x} satisfies @code{CONSTANT_P}, so you need not check this.  In fact,
-@samp{1} is a suitable definition for this macro on machines where
-anything @code{CONSTANT_P} is valid.
-@end defmac
+@deftypefn {Target Hook} bool TARGET_LEGITIMATE_CONSTANT_P (enum machine_mode @var{mode}, rtx @var{x})
+This hook returns true if @var{x} is a legitimate constant for a
+@var{mode}-mode immediate operand on the target machine.  You can assume that
+@var{x} satisfies @code{CONSTANT_P}, so you need not check this.
+
+The default definition returns true.
+@end deftypefn
 
 @deftypefn {Target Hook} rtx TARGET_DELEGITIMIZE_ADDRESS (rtx @var{x})
 This hook is used to undo the possibly obfuscating effects of the
--- a/src/gcc/doc/tm.texi.in
+++ b/src/gcc/doc/tm.texi.in
@@ -2523,7 +2523,7 @@
 register, so @code{TARGET_PREFERRED_RELOAD_CLASS} returns @code{NO_REGS} when
 @var{x} is a floating-point constant.  If the constant can't be loaded
 into any kind of register, code generation will be better if
-@code{LEGITIMATE_CONSTANT_P} makes the constant illegitimate instead
+@code{TARGET_LEGITIMATE_CONSTANT_P} makes the constant illegitimate instead
 of using @code{TARGET_PREFERRED_RELOAD_CLASS}.
 
 If an insn has pseudos in it after register allocation, reload will go
@@ -2560,8 +2560,8 @@
 register, so @code{PREFERRED_RELOAD_CLASS} returns @code{NO_REGS} when
 @var{x} is a floating-point constant.  If the constant can't be loaded
 into any kind of register, code generation will be better if
-@code{LEGITIMATE_CONSTANT_P} makes the constant illegitimate instead
-of using @code{PREFERRED_RELOAD_CLASS}.
+@code{TARGET_LEGITIMATE_CONSTANT_P} makes the constant illegitimate instead
+of using @code{TARGET_PREFERRED_RELOAD_CLASS}.
 
 If an insn has pseudos in it after register allocation, reload will go
 through the alternatives and call repeatedly @code{PREFERRED_RELOAD_CLASS}
@@ -4307,6 +4307,8 @@
 must have move patterns for this mode.
 @end deftypefn
 
+@hook TARGET_ARRAY_MODE_SUPPORTED_P
+
 @hook TARGET_SMALL_REGISTER_CLASSES_FOR_MODE_P
 Define this to return nonzero for machine modes for which the port has
 small register classes.  If this target hook returns nonzero for a given
@@ -5557,13 +5559,13 @@
 @code{TARGET_MODE_DEPENDENT_ADDRESS_P} target hook.
 @end defmac
 
-@defmac LEGITIMATE_CONSTANT_P (@var{x})
-A C expression that is nonzero if @var{x} is a legitimate constant for
-an immediate operand on the target machine.  You can assume that
-@var{x} satisfies @code{CONSTANT_P}, so you need not check this.  In fact,
-@samp{1} is a suitable definition for this macro on machines where
-anything @code{CONSTANT_P} is valid.
-@end defmac
+@hook TARGET_LEGITIMATE_CONSTANT_P
+This hook returns true if @var{x} is a legitimate constant for a
+@var{mode}-mode immediate operand on the target machine.  You can assume that
+@var{x} satisfies @code{CONSTANT_P}, so you need not check this.
+
+The default definition returns true.
+@end deftypefn
 
 @hook TARGET_DELEGITIMIZE_ADDRESS
 This hook is used to undo the possibly obfuscating effects of the