x86: optimize EVEX packed integer logical instructions

[deliverable/binutils-gdb.git] / gas / doc / c-i386.texi

diff --git a/gas/doc/c-i386.texi b/gas/doc/c-i386.texi
index 7d503495411d89717779589d38a60c1c0d61e5a5..ba2006743851df93654755fb29a04a419a4fbb53 100644 (file)
--- a/gas/doc/c-i386.texi
+++ b/gas/doc/c-i386.texi
@@ -1,4 +1,4 @@
-@c Copyright (C) 1991-2016 Free Software Foundation, Inc.
+@c Copyright (C) 1991-2019 Free Software Foundation, Inc.

 @c This is part of the GAS manual.
 @c For copying conditions, see the file as.texinfo.
 @c man end
 @c This is part of the GAS manual.
 @c For copying conditions, see the file as.texinfo.
 @c man end


@@ -74,7 +74,8 @@ usage and use x86-64 as target platform).
 @item -n
 By default, x86 GAS replaces multiple nop instructions used for
 alignment within code sections with multi-byte nop instructions such
 @item -n
 By default, x86 GAS replaces multiple nop instructions used for
 alignment within code sections with multi-byte nop instructions such

-as leal 0(%esi,1),%esi.  This switch disables the optimization.
+as leal 0(%esi,1),%esi.  This switch disables the optimization if a single
+byte nop (0x90) is explicitly specified as the fill byte for alignment.

 
 @cindex @samp{--divide} option, i386
 @item --divide
 
 @cindex @samp{--divide} option, i386
 @item --divide


@@ -122,6 +123,7 @@ processor names are recognized:
 @code{bdver3},
 @code{bdver4},
 @code{znver1},
 @code{bdver3},
 @code{bdver4},
 @code{znver1},

+@code{znver2},

 @code{btver1},
 @code{btver2},
 @code{generic32} and
 @code{btver1},
 @code{btver2},
 @code{generic32} and


@@ -134,7 +136,15 @@ accept various extension mnemonics.  For example,
 @code{8087},
 @code{287},
 @code{387},
 @code{8087},
 @code{287},
 @code{387},

+@code{687},

 @code{no87},
 @code{no87},

+@code{no287},
+@code{no387},
+@code{no687},
+@code{cmov},
+@code{nocmov},
+@code{fxsr},
+@code{nofxsr},

 @code{mmx},
 @code{nommx},
 @code{sse},
 @code{mmx},
 @code{nommx},
 @code{sse},


@@ -145,19 +155,35 @@ accept various extension mnemonics.  For example,
 @code{sse4.2},
 @code{sse4},
 @code{nosse},
 @code{sse4.2},
 @code{sse4},
 @code{nosse},

+@code{nosse2},
+@code{nosse3},
+@code{nossse3},
+@code{nosse4.1},
+@code{nosse4.2},
+@code{nosse4},

 @code{avx},
 @code{avx2},
 @code{avx},
 @code{avx2},

+@code{noavx},
+@code{noavx2},

 @code{adx},
 @code{rdseed},
 @code{prfchw},
 @code{smap},
 @code{mpx},
 @code{sha},
 @code{adx},
 @code{rdseed},
 @code{prfchw},
 @code{smap},
 @code{mpx},
 @code{sha},

+@code{rdpid},
+@code{ptwrite},
+@code{cet},
+@code{gfni},
+@code{vaes},
+@code{vpclmulqdq},

 @code{prefetchwt1},
 @code{clflushopt},
 @code{se1},
 @code{clwb},
 @code{prefetchwt1},
 @code{clflushopt},
 @code{se1},
 @code{clwb},

-@code{pcommit},
+@code{movdiri},
+@code{movdir64b},
+@code{enqcmd},

 @code{avx512f},
 @code{avx512cd},
 @code{avx512er},
 @code{avx512f},
 @code{avx512cd},
 @code{avx512er},


@@ -167,7 +193,31 @@ accept various extension mnemonics.  For example,
 @code{avx512dq},
 @code{avx512ifma},
 @code{avx512vbmi},
 @code{avx512dq},
 @code{avx512ifma},
 @code{avx512vbmi},

-@code{noavx},
+@code{avx512_4fmaps},
+@code{avx512_4vnniw},
+@code{avx512_vpopcntdq},
+@code{avx512_vbmi2},
+@code{avx512_vnni},
+@code{avx512_bitalg},
+@code{avx512_bf16},
+@code{noavx512f},
+@code{noavx512cd},
+@code{noavx512er},
+@code{noavx512pf},
+@code{noavx512vl},
+@code{noavx512bw},
+@code{noavx512dq},
+@code{noavx512ifma},
+@code{noavx512vbmi},
+@code{noavx512_4fmaps},
+@code{noavx512_4vnniw},
+@code{noavx512_vpopcntdq},
+@code{noavx512_vbmi2},
+@code{noavx512_vnni},
+@code{noavx512_bitalg},
+@code{noavx512_vp2intersect},
+@code{noavx512_bf16},
+@code{noenqcmd},

 @code{vmx},
 @code{vmfunc},
 @code{smx},
 @code{vmx},
 @code{vmfunc},
 @code{smx},


@@ -191,6 +241,10 @@ accept various extension mnemonics.  For example,
 @code{clflush},
 @code{mwaitx},
 @code{clzero},
 @code{clflush},
 @code{mwaitx},
 @code{clzero},

+@code{wbnoinvd},
+@code{pconfig},
+@code{waitpkg},
+@code{cldemote},

 @code{lwp},
 @code{fma4},
 @code{xop},
 @code{lwp},
 @code{fma4},
 @code{xop},


@@ -249,6 +303,22 @@ AVX instructions with 128bit vector length, which is the default.
 @option{-mavxscalar=@var{256}} will encode scalar AVX instructions
 with 256bit vector length.
 
 @option{-mavxscalar=@var{256}} will encode scalar AVX instructions
 with 256bit vector length.
 

+WARNING: Don't use this for production code - due to CPU errata the
+resulting code may not work on certain models.
+
+@cindex @samp{-mvexwig=} option, i386
+@cindex @samp{-mvexwig=} option, x86-64
+@item -mvexwig=@var{0}
+@itemx -mvexwig=@var{1}
+These options control how the assembler should encode VEX.W-ignored (WIG)
+VEX instructions.  @option{-mvexwig=@var{0}} will encode WIG VEX
+instructions with vex.w = 0, which is the default.
+@option{-mvexwig=@var{1}} will encode WIG EVEX instructions with
+vex.w = 1.
+
+WARNING: Don't use this for production code - due to CPU errata the
+resulting code may not work on certain models.
+

 @cindex @samp{-mevexlig=} option, i386
 @cindex @samp{-mevexlig=} option, x86-64
 @item -mevexlig=@var{128}
 @cindex @samp{-mevexlig=} option, i386
 @cindex @samp{-mevexlig=} option, x86-64
 @item -mevexlig=@var{128}


@@ -290,7 +360,7 @@ take precedent.
 @cindex @samp{-mnaked-reg} option, i386
 @cindex @samp{-mnaked-reg} option, x86-64
 @item -mnaked-reg
 @cindex @samp{-mnaked-reg} option, i386
 @cindex @samp{-mnaked-reg} option, x86-64
 @item -mnaked-reg

-This opetion specifies that registers don't require a @samp{%} prefix.
+This option specifies that registers don't require a @samp{%} prefix.

 The @code{.att_syntax} and @code{.intel_syntax} directives will take precedent.
 
 @cindex @samp{-madd-bnd-prefix} option, i386
 The @code{.att_syntax} and @code{.intel_syntax} directives will take precedent.
 
 @cindex @samp{-madd-bnd-prefix} option, i386


@@ -351,6 +421,15 @@ R_X86_64_REX_GOTPCRELX, in 64-bit mode.
 relocations.  The default can be controlled by a configure option
 @option{--enable-x86-relax-relocations}.
 
 relocations.  The default can be controlled by a configure option
 @option{--enable-x86-relax-relocations}.
 

+@cindex @samp{-mx86-used-note=} option, i386
+@cindex @samp{-mx86-used-note=} option, x86-64
+@item -mx86-used-note=@var{no}
+@itemx -mx86-used-note=@var{yes}
+These options control whether the assembler should generate
+GNU_PROPERTY_X86_ISA_1_USED and GNU_PROPERTY_X86_FEATURE_2_USED
+GNU property notes.  The default can be controlled by the
+@option{--enable-x86-used-note} configure option.
+

 @cindex @samp{-mevexrcig=} option, i386
 @cindex @samp{-mevexrcig=} option, x86-64
 @item -mevexrcig=@var{rne}
 @cindex @samp{-mevexrcig=} option, i386
 @cindex @samp{-mevexrcig=} option, x86-64
 @item -mevexrcig=@var{rne}


@@ -371,6 +450,36 @@ with 01, 10 and 11 RC bits, respectively.
 This option specifies that the assembler should accept only AMD64 or
 Intel64 ISA in 64-bit mode.  The default is to accept both.
 
 This option specifies that the assembler should accept only AMD64 or
 Intel64 ISA in 64-bit mode.  The default is to accept both.
 

+@cindex @samp{-O0} option, i386
+@cindex @samp{-O0} option, x86-64
+@cindex @samp{-O} option, i386
+@cindex @samp{-O} option, x86-64
+@cindex @samp{-O1} option, i386
+@cindex @samp{-O1} option, x86-64
+@cindex @samp{-O2} option, i386
+@cindex @samp{-O2} option, x86-64
+@cindex @samp{-Os} option, i386
+@cindex @samp{-Os} option, x86-64
+@item -O0 | -O | -O1 | -O2 | -Os
+Optimize instruction encoding with smaller instruction size.  @samp{-O}
+and @samp{-O1} encode 64-bit register load instructions with 64-bit
+immediate as 32-bit register load instructions with 31-bit or 32-bits
+immediates, encode 64-bit register clearing instructions with 32-bit
+register clearing instructions, encode 256-bit/512-bit VEX/EVEX vector
+register clearing instructions with 128-bit VEX vector register
+clearing instructions, encode 128-bit/256-bit EVEX vector
+register load/store instructions with VEX vector register load/store
+instructions, and encode 128-bit/256-bit EVEX packed integer logical
+instructions with 128-bit/256-bit VEX packed integer logical.
+
+@samp{-O2} includes @samp{-O1} optimization plus encodes
+256-bit/512-bit EVEX vector register clearing instructions with 128-bit
+EVEX vector register clearing instructions.
+
+@samp{-Os} includes @samp{-O2} optimization plus encodes 16-bit, 32-bit
+and 64-bit register tests with immediate as 8-bit register test with
+immediate.  @samp{-O0} turns off this optimization.
+

 @end table
 @c man end
 
 @end table
 @c man end
 


@@ -393,8 +502,17 @@ specifies the desired alignment of the symbol in the bss section.
 
 This directive is only available for COFF based x86 targets.
 
 
 This directive is only available for COFF based x86 targets.
 

+@cindex @code{largecomm} directive, ELF
+@item .largecomm @var{symbol} , @var{length}[, @var{alignment}]
+This directive behaves in the same way as the @code{comm} directive
+except that the data is placed into the @var{.lbss} section instead of
+the @var{.bss} section @ref{Comm}.
+
+The directive is intended to be used for data which requires a large
+amount of space, and it is only available for ELF based x86_64
+targets.
+

 @c FIXME: Document other x86 specific directives ?  Eg: .code16gcc,
 @c FIXME: Document other x86 specific directives ?  Eg: .code16gcc,

-@c .largecomm

 
 @end table
 
 
 @end table
 


@@ -476,11 +594,16 @@ instruction, do @emph{not} have reversed order.  @ref{i386-Bugs}.
 In AT&T syntax the size of memory operands is determined from the last
 character of the instruction mnemonic.  Mnemonic suffixes of @samp{b},
 @samp{w}, @samp{l} and @samp{q} specify byte (8-bit), word (16-bit), long
 In AT&T syntax the size of memory operands is determined from the last
 character of the instruction mnemonic.  Mnemonic suffixes of @samp{b},
 @samp{w}, @samp{l} and @samp{q} specify byte (8-bit), word (16-bit), long

-(32-bit) and quadruple word (64-bit) memory references.  Intel syntax accomplishes
-this by prefixing memory operands (@emph{not} the instruction mnemonics) with
-@samp{byte ptr}, @samp{word ptr}, @samp{dword ptr} and @samp{qword ptr}.  Thus,
-Intel @samp{mov al, byte ptr @var{foo}} is @samp{movb @var{foo}, %al} in AT&T
-syntax.
+(32-bit) and quadruple word (64-bit) memory references.  Mnemonic suffixes
+of @samp{x}, @samp{y} and @samp{z} specify xmm (128-bit vector), ymm
+(256-bit vector) and zmm (512-bit vector) memory references, only when there's
+no other way to disambiguate an instruction.  Intel syntax accomplishes this by
+prefixing memory operands (@emph{not} the instruction mnemonics) with
+@samp{byte ptr}, @samp{word ptr}, @samp{dword ptr}, @samp{qword ptr},
+@samp{xmmword ptr}, @samp{ymmword ptr} and @samp{zmmword ptr}.  Thus, Intel
+syntax @samp{mov al, byte ptr @var{foo}} is @samp{movb @var{foo}, %al} in AT&T
+syntax.  In Intel syntax, @samp{fword ptr}, @samp{tbyte ptr} and
+@samp{oword ptr} specify 48-bit, 80-bit and 128-bit memory references.

 
 In 64-bit code, @samp{movabs} can be used to encode the @samp{mov}
 instruction with the 64-bit displacement or immediate operand.
 
 In 64-bit code, @samp{movabs} can be used to encode the @samp{mov}
 instruction with the 64-bit displacement or immediate operand.


@@ -520,7 +643,7 @@ line is treated as a comment, but in this case the line can also be a
 logical line number directive (@pxref{Comments}) or a preprocessor
 control command (@pxref{Preprocessing}).
 
 logical line number directive (@pxref{Comments}) or a preprocessor
 control command (@pxref{Preprocessing}).
 

-If the @option{--divide} command line option has not been specified
+If the @option{--divide} command-line option has not been specified

 then the @samp{/} character appearing anywhere on a line also
 introduces a line comment.
 
 then the @samp{/} character appearing anywhere on a line also
 introduces a line comment.
 


@@ -570,10 +693,38 @@ quadruple word).
 @cindex encoding options, i386
 @cindex encoding options, x86-64
 
 @cindex encoding options, i386
 @cindex encoding options, x86-64
 

-Different encoding options can be specified via optional mnemonic
-suffix.  @samp{.s} suffix swaps 2 register operands in encoding when
-moving from one register to another.  @samp{.d8} or @samp{.d32} suffix
-prefers 8bit or 32bit displacement in encoding.
+Different encoding options can be specified via pseudo prefixes:
+
+@itemize @bullet
+@item
+@samp{@{disp8@}} -- prefer 8-bit displacement.
+
+@item
+@samp{@{disp32@}} -- prefer 32-bit displacement.
+
+@item
+@samp{@{load@}} -- prefer load-form instruction.
+
+@item
+@samp{@{store@}} -- prefer store-form instruction.
+
+@item
+@samp{@{vex2@}} -- prefer 2-byte VEX prefix for VEX instruction.
+
+@item
+@samp{@{vex3@}} -- prefer 3-byte VEX prefix for VEX instruction.
+
+@item
+@samp{@{evex@}} --  encode with EVEX prefix.
+
+@item
+@samp{@{rex@}} -- prefer REX prefix for integer and legacy vector
+instructions (x86-64 only).  Note that this differs from the @samp{rex}
+prefix which generates REX prefix unconditionally.
+
+@item
+@samp{@{nooptimize@}} -- disable instruction size optimization.
+@end itemize

 
 @cindex conversion instructions, i386
 @cindex i386 conversion instructions
 
 @cindex conversion instructions, i386
 @cindex i386 conversion instructions


@@ -663,8 +814,8 @@ the 6 section registers @samp{%cs} (code section), @samp{%ds}
 and @samp{%gs}.
 
 @item
 and @samp{%gs}.
 
 @item

-the 3 processor control registers @samp{%cr0}, @samp{%cr2}, and
-@samp{%cr3}.
+the 5 processor control registers @samp{%cr0}, @samp{%cr2},
+@samp{%cr3}, @samp{%cr4}, and @samp{%cr8}.

 
 @item
 the 6 debug registers @samp{%db0}, @samp{%db1}, @samp{%db2},
 
 @item
 the 6 debug registers @samp{%db0}, @samp{%db1}, @samp{%db2},


@@ -682,7 +833,7 @@ These registers are overloaded by 8 MMX registers @samp{%mm0},
 @samp{%mm6} and @samp{%mm7}.
 
 @item
 @samp{%mm6} and @samp{%mm7}.
 
 @item

-the 8 SSE registers registers @samp{%xmm0}, @samp{%xmm1}, @samp{%xmm2},
+the 8 128-bit SSE registers registers @samp{%xmm0}, @samp{%xmm1}, @samp{%xmm2},

 @samp{%xmm3}, @samp{%xmm4}, @samp{%xmm5}, @samp{%xmm6} and @samp{%xmm7}.
 @end itemize
 
 @samp{%xmm3}, @samp{%xmm4}, @samp{%xmm5}, @samp{%xmm6} and @samp{%xmm7}.
 @end itemize
 


@@ -699,13 +850,13 @@ pointer)
 the 8 extended registers @samp{%r8}--@samp{%r15}.
 
 @item
 the 8 extended registers @samp{%r8}--@samp{%r15}.
 
 @item

-the 8 32-bit low ends of the extended registers: @samp{%r8d}--@samp{%r15d}
+the 8 32-bit low ends of the extended registers: @samp{%r8d}--@samp{%r15d}.

 
 @item
 
 @item

-the 8 16-bit low ends of the extended registers: @samp{%r8w}--@samp{%r15w}
+the 8 16-bit low ends of the extended registers: @samp{%r8w}--@samp{%r15w}.

 
 @item
 
 @item

-the 8 8-bit low ends of the extended registers: @samp{%r8b}--@samp{%r15b}
+the 8 8-bit low ends of the extended registers: @samp{%r8b}--@samp{%r15b}.

 
 @item
 the 4 8-bit registers: @samp{%sil}, @samp{%dil}, @samp{%bpl}, @samp{%spl}.
 
 @item
 the 4 8-bit registers: @samp{%sil}, @samp{%dil}, @samp{%bpl}, @samp{%spl}.


@@ -714,7 +865,43 @@ the 4 8-bit registers: @samp{%sil}, @samp{%dil}, @samp{%bpl}, @samp{%spl}.
 the 8 debug registers: @samp{%db8}--@samp{%db15}.
 
 @item
 the 8 debug registers: @samp{%db8}--@samp{%db15}.
 
 @item

-the 8 SSE registers: @samp{%xmm8}--@samp{%xmm15}.
+the 8 128-bit SSE registers: @samp{%xmm8}--@samp{%xmm15}.
+@end itemize
+
+With the AVX extensions more registers were made available:
+
+@itemize @bullet
+
+@item
+the 16 256-bit SSE @samp{%ymm0}--@samp{%ymm15} (only the first 8
+available in 32-bit mode).  The bottom 128 bits are overlaid with the
+@samp{xmm0}--@samp{xmm15} registers.
+
+@end itemize
+
+The AVX2 extensions made in 64-bit mode more registers available:
+
+@itemize @bullet
+
+@item
+the 16 128-bit registers @samp{%xmm16}--@samp{%xmm31} and the 16 256-bit
+registers @samp{%ymm16}--@samp{%ymm31}.
+
+@end itemize
+
+The AVX512 extensions added the following registers:
+
+@itemize @bullet
+
+@item
+the 32 512-bit registers @samp{%zmm0}--@samp{%zmm31} (only the first 8
+available in 32-bit mode).  The bottom 128 bits are overlaid with the
+@samp{%xmm0}--@samp{%xmm31} registers and the first 256 bits are
+overlaid with the @samp{%ymm0}--@samp{%ymm31} registers.
+
+@item
+the 8 mask registers @samp{%k0}--@samp{%k7}.
+

 @end itemize
 
 @node i386-Prefixes
 @end itemize
 
 @node i386-Prefixes


@@ -1116,12 +1303,13 @@ supported on the CPU specified.  The choices for @var{cpu_type} are:
 @item @samp{i486} @tab @samp{i586} @tab @samp{i686} @tab @samp{pentium}
 @item @samp{pentiumpro} @tab @samp{pentiumii} @tab @samp{pentiumiii} @tab @samp{pentium4}
 @item @samp{prescott} @tab @samp{nocona} @tab @samp{core} @tab @samp{core2}
 @item @samp{i486} @tab @samp{i586} @tab @samp{i686} @tab @samp{pentium}
 @item @samp{pentiumpro} @tab @samp{pentiumii} @tab @samp{pentiumiii} @tab @samp{pentium4}
 @item @samp{prescott} @tab @samp{nocona} @tab @samp{core} @tab @samp{core2}

-@item @samp{corei7} @tab @samp{l1om} @tab @samp{k1om} @samp{iamcu}
+@item @samp{corei7} @tab @samp{l1om} @tab @samp{k1om} @tab @samp{iamcu}

 @item @samp{k6} @tab @samp{k6_2} @tab @samp{athlon} @tab @samp{k8}
 @item @samp{amdfam10} @tab @samp{bdver1} @tab @samp{bdver2} @tab @samp{bdver3}
 @item @samp{k6} @tab @samp{k6_2} @tab @samp{athlon} @tab @samp{k8}
 @item @samp{amdfam10} @tab @samp{bdver1} @tab @samp{bdver2} @tab @samp{bdver3}

-@item @samp{bdver4} @tab @samp{znver1} @tab @samp{btver1} @tab @samp{btver2}
-@item @samp{generic32} @tab @samp{generic64}
-@item @samp{.mmx} @tab @samp{.sse} @tab @samp{.sse2} @tab @samp{.sse3}
+@item @samp{bdver4} @tab @samp{znver1} @tab @samp{znver2} @tab @samp{btver1}
+@item @samp{btver2} @tab @samp{generic32} @tab @samp{generic64}
+@item @samp{.cmov} @tab @samp{.fxsr} @tab @samp{.mmx}
+@item @samp{.sse} @tab @samp{.sse2} @tab @samp{.sse3}

 @item @samp{.ssse3} @tab @samp{.sse4.1} @tab @samp{.sse4.2} @tab @samp{.sse4}
 @item @samp{.avx} @tab @samp{.vmx} @tab @samp{.smx} @tab @samp{.ept}
 @item @samp{.clflush} @tab @samp{.movbe} @tab @samp{.xsave} @tab @samp{.xsaveopt}
 @item @samp{.ssse3} @tab @samp{.sse4.1} @tab @samp{.sse4.2} @tab @samp{.sse4}
 @item @samp{.avx} @tab @samp{.vmx} @tab @samp{.smx} @tab @samp{.ept}
 @item @samp{.clflush} @tab @samp{.movbe} @tab @samp{.xsave} @tab @samp{.xsaveopt}


@@ -1133,7 +1321,13 @@ supported on the CPU specified.  The choices for @var{cpu_type} are:
 @item @samp{.clflushopt} @tab @samp{.xsavec} @tab @samp{.xsaves} @tab @samp{.se1}
 @item @samp{.avx512f} @tab @samp{.avx512cd} @tab @samp{.avx512er} @tab @samp{.avx512pf}
 @item @samp{.avx512vl} @tab @samp{.avx512bw} @tab @samp{.avx512dq} @tab @samp{.avx512ifma}
 @item @samp{.clflushopt} @tab @samp{.xsavec} @tab @samp{.xsaves} @tab @samp{.se1}
 @item @samp{.avx512f} @tab @samp{.avx512cd} @tab @samp{.avx512er} @tab @samp{.avx512pf}
 @item @samp{.avx512vl} @tab @samp{.avx512bw} @tab @samp{.avx512dq} @tab @samp{.avx512ifma}

-@item @samp{.avx512vbmi} @tab @samp{.clwb} @tab @samp{.pcommit}
+@item @samp{.avx512vbmi} @tab @samp{.avx512_4fmaps} @tab @samp{.avx512_4vnniw}
+@item @samp{.avx512_vpopcntdq} @tab @samp{.avx512_vbmi2} @tab @samp{.avx512_vnni}
+@item @samp{.avx512_bitalg} @tab @samp{.avx512_bf16} @tab @samp{.avx512_vp2intersect}
+@item @samp{.clwb} @tab @samp{.rdpid} @tab @samp{.ptwrite} @tab @item @samp{.ibt}
+@item @samp{.wbnoinvd} @tab @samp{.pconfig} @tab @samp{.waitpkg} @tab @samp{.cldemote}
+@item @samp{.shstk} @tab @samp{.gfni} @tab @samp{.vaes} @tab @samp{.vpclmulqdq}
+@item @samp{.movdiri} @tab @samp{.movdir64b} @tab @samp{.enqcmd}

 @item @samp{.3dnow} @tab @samp{.3dnowa} @tab @samp{.sse4a} @tab @samp{.sse5}
 @item @samp{.syscall} @tab @samp{.rdtscp} @tab @samp{.svme} @tab @samp{.abm}
 @item @samp{.lwp} @tab @samp{.fma4} @tab @samp{.xop} @tab @samp{.cx16}
 @item @samp{.3dnow} @tab @samp{.3dnowa} @tab @samp{.sse4a} @tab @samp{.sse5}
 @item @samp{.syscall} @tab @samp{.rdtscp} @tab @samp{.svme} @tab @samp{.abm}
 @item @samp{.lwp} @tab @samp{.fma4} @tab @samp{.xop} @tab @samp{.cx16}