gcc/
2011-08-01 Kirill Yukhin <kirill.yukhin@intel.com>
PR target/49547
* config.gcc (i[34567]86-*-*): Replace abmintrin.h with
lzcntintrin.h.
(x86_64-*-*): Likewise.
* config/i386/i386.opt (mlzcnt): New.
* config/i386/abmintrin.h: File removed.
(__lzcnt_u16, __lzcnt, __lzcnt_u64): Moved to ...
* config/i386/lzcntintrin.h: ... here. New file.
(__lzcnt): Rename to ...
(__lzcnt32): ... this.
* config/i386/bmiintrin.h (head): Update copyright year.
(__lzcnt_u16): Removed.
(__lzcnt_u32): Likewise.
(__lzcnt_u64): Likewise.
* config/i386/x86intrin.h: Include lzcntintrin.h when __LZCNT__
is defined, remove abmintrin.h.
* config/i386/cpuid.h (bit_LZCNT): New.
* config/i386/driver-i386.c (host_detect_local_cpu): Detect
LZCNT feature.
* config/i386/i386-c.c (ix86_target_macros_internal): Define
__LZCNT__ if needed.
* config/i386/i386.c (ix86_target_string): New option -mlzcnt.
(ix86_option_override_internal): Handle LZCNT option.
(ix86_valid_target_attribute_inner_p): Likewise.
(struct builtin_description bdesc_args) <IX86_BUILTIN_CLZS>: Update.
* config/i386/i386.h (TARGET_LZCNT): New.
(CLZ_DEFINED_VALUE_AT_ZERO): Update.
* config/i386/i386.md (clz<mode>2): Update insn constraint.
(clz<mode>2_lzcnt): Likewise.
* doc/invoke.texi: Mention -mlzcnt option.
* doc/extend.texi: Likewise.
gcc/testsuite/
2011-08-01 Kirill Yukhin <kirill.yukhin@intel.com>
* gcc.target/i386/i386.exp (check_effective_target_lzcnt): New.
* gcc.target/i386/lzcnt-1.c: New test.
* gcc.target/i386/lzcnt-2.c: Likewise.
* gcc.target/i386/lzcnt-2a.c: Likewise.
* gcc.target/i386/lzcnt-3.c: Likewise.
* gcc.target/i386/lzcnt-4.c: Likewise.
* gcc.target/i386/lzcnt-4a.c: Likewise.
* gcc.target/i386/lzcnt-5.c: Likewise.
* gcc.target/i386/lzcnt-6.c: Likewise.
* gcc.target/i386/lzcnt-6a.c: Likewise.
* gcc.target/i386/lzcnt-check.h: Likewise.
* gcc.target/i386/sse-12.c (dg-compile): Add -mlzcnt.
* gcc.target/i386/sse-13.c: Likewise.
* gcc.target/i386/sse-14.c: Likewise.
* g++.dg/other/i386-2.C: Likewise.
* g++.dg/other/i386-3.C: Likewise.
git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@177034
138bc75d-0d04-0410-961f-
82ee72b054a4
+2011-08-01 Kirill Yukhin <kirill.yukhin@intel.com>
+
+ PR target/49547
+ * config.gcc (i[34567]86-*-*): Replace abmintrin.h with
+ lzcntintrin.h.
+ (x86_64-*-*): Likewise.
+ * config/i386/i386.opt (mlzcnt): New.
+ * config/i386/abmintrin.h: File removed.
+ (__lzcnt_u16, __lzcnt, __lzcnt_u64): Moved to ...
+ * config/i386/lzcntintrin.h: ... here. New file.
+ (__lzcnt): Rename to ...
+ (__lzcnt32): ... this.
+ * config/i386/bmiintrin.h (head): Update copyright year.
+ (__lzcnt_u16): Removed.
+ (__lzcnt_u32): Likewise.
+ (__lzcnt_u64): Likewise.
+ * config/i386/x86intrin.h: Include lzcntintrin.h when __LZCNT__
+ is defined, remove abmintrin.h.
+ * config/i386/cpuid.h (bit_LZCNT): New.
+ * config/i386/driver-i386.c (host_detect_local_cpu): Detect
+ LZCNT feature.
+ * config/i386/i386-c.c (ix86_target_macros_internal): Define
+ __LZCNT__ if needed.
+ * config/i386/i386.c (ix86_target_string): New option -mlzcnt.
+ (ix86_option_override_internal): Handle LZCNT option.
+ (ix86_valid_target_attribute_inner_p): Likewise.
+ (struct builtin_description bdesc_args) <IX86_BUILTIN_CLZS>: Update.
+ * config/i386/i386.h (TARGET_LZCNT): New.
+ (CLZ_DEFINED_VALUE_AT_ZERO): Update.
+ * config/i386/i386.md (clz<mode>2): Update insn constraint.
+ (clz<mode>2_lzcnt): Likewise.
+ * doc/invoke.texi: Mention -mlzcnt option.
+ * doc/extend.texi: Likewise.
+
2011-08-01 Julian Brown <julian@codesourcery.com>
* configure.ac (fixed-point): Add ARM support.
nmmintrin.h bmmintrin.h fma4intrin.h wmmintrin.h
immintrin.h x86intrin.h avxintrin.h xopintrin.h
ia32intrin.h cross-stdarg.h lwpintrin.h popcntintrin.h
- abmintrin.h bmiintrin.h tbmintrin.h"
+ lzcntintrin.h bmiintrin.h tbmintrin.h"
;;
x86_64-*-*)
cpu_type=i386
nmmintrin.h bmmintrin.h fma4intrin.h wmmintrin.h
immintrin.h x86intrin.h avxintrin.h xopintrin.h
ia32intrin.h cross-stdarg.h lwpintrin.h popcntintrin.h
- abmintrin.h bmiintrin.h tbmintrin.h"
+ lzcntintrin.h bmiintrin.h tbmintrin.h"
need_64bit_hwint=yes
;;
ia64-*-*)
-/* Copyright (C) 2010 Free Software Foundation, Inc.
+/* Copyright (C) 2010, 2011 Free Software Foundation, Inc.
This file is part of GCC.
#define _BMIINTRIN_H_INCLUDED
extern __inline unsigned short __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-__lzcnt_u16 (unsigned short __X)
-{
- return __builtin_clzs (__X);
-}
-
-extern __inline unsigned short __attribute__((__gnu_inline__, __always_inline__, __artificial__))
__tzcnt_u16 (unsigned short __X)
{
return __builtin_ctzs (__X);
return tmp;
}
-extern __inline unsigned int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-__lzcnt_u32 (unsigned int __X)
-{
- return __builtin_clz (__X);
-}
-
extern __inline unsigned int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
__tzcnt_u32 (unsigned int __X)
}
extern __inline unsigned long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-__lzcnt_u64 (unsigned long long __X)
-{
- return __builtin_clzll (__X);
-}
-
-extern __inline unsigned long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
__tzcnt_u64 (unsigned long long __X)
{
return __builtin_ctzll (__X);
/* %ecx */
#define bit_SSE3 (1 << 0)
#define bit_PCLMUL (1 << 1)
+#define bit_LZCNT (1 << 5)
#define bit_SSSE3 (1 << 9)
#define bit_FMA (1 << 12)
#define bit_CMPXCHG16B (1 << 13)
unsigned int has_popcnt = 0, has_aes = 0, has_avx = 0;
unsigned int has_pclmul = 0, has_abm = 0, has_lwp = 0;
unsigned int has_fma = 0, has_fma4 = 0, has_xop = 0;
- unsigned int has_bmi = 0, has_tbm = 0;
+ unsigned int has_bmi = 0, has_tbm = 0, has_lzcnt = 0;
bool arch;
has_fma4 = ecx & bit_FMA4;
has_xop = ecx & bit_XOP;
has_tbm = ecx & bit_TBM;
+ has_lzcnt = ecx & bit_LZCNT;
has_longmode = edx & bit_LM;
has_3dnowp = edx & bit_3DNOWP;
const char *avx = has_avx ? " -mavx" : " -mno-avx";
const char *sse4_2 = has_sse4_2 ? " -msse4.2" : " -mno-sse4.2";
const char *sse4_1 = has_sse4_1 ? " -msse4.1" : " -mno-sse4.1";
+ const char *lzcnt = has_lzcnt ? " -mlzcnt" : " -mnolzcnt";
options = concat (options, cx16, sahf, movbe, ase, pclmul,
popcnt, abm, lwp, fma, fma4, xop, bmi, tbm,
- avx, sse4_2, sse4_1, NULL);
+ avx, sse4_2, sse4_1, lzcnt, NULL);
}
done:
def_or_undef (parse_in, "__ABM__");
if (isa_flag & OPTION_MASK_ISA_BMI)
def_or_undef (parse_in, "__BMI__");
+ if (isa_flag & OPTION_MASK_ISA_LZCNT)
+ def_or_undef (parse_in, "__LZCNT__");
if (isa_flag & OPTION_MASK_ISA_TBM)
def_or_undef (parse_in, "__TBM__");
if (isa_flag & OPTION_MASK_ISA_POPCNT)
{ "-mmmx", OPTION_MASK_ISA_MMX },
{ "-mabm", OPTION_MASK_ISA_ABM },
{ "-mbmi", OPTION_MASK_ISA_BMI },
+ { "-mlzcnt", OPTION_MASK_ISA_LZCNT },
{ "-mtbm", OPTION_MASK_ISA_TBM },
{ "-mpopcnt", OPTION_MASK_ISA_POPCNT },
{ "-mmovbe", OPTION_MASK_ISA_MOVBE },
PTA_RDRND = 1 << 25,
PTA_F16C = 1 << 26,
PTA_BMI = 1 << 27,
- PTA_TBM = 1 << 28
+ PTA_TBM = 1 << 28,
+ PTA_LZCNT = 1 << 29
/* if this reaches 32, need to widen struct pta flags below */
};
if (processor_alias_table[i].flags & PTA_BMI
&& !(ix86_isa_flags_explicit & OPTION_MASK_ISA_BMI))
ix86_isa_flags |= OPTION_MASK_ISA_BMI;
+ if (processor_alias_table[i].flags & (PTA_LZCNT | PTA_ABM)
+ && !(ix86_isa_flags_explicit & OPTION_MASK_ISA_LZCNT))
+ ix86_isa_flags |= OPTION_MASK_ISA_LZCNT;
if (processor_alias_table[i].flags & PTA_TBM
&& !(ix86_isa_flags_explicit & OPTION_MASK_ISA_TBM))
ix86_isa_flags |= OPTION_MASK_ISA_TBM;
if (TARGET_SSE4_2 || TARGET_ABM)
ix86_isa_flags |= OPTION_MASK_ISA_POPCNT & ~ix86_isa_flags_explicit;
+ /* Turn on lzcnt instruction for -mabm. */
+ if (TARGET_ABM)
+ ix86_isa_flags |= OPTION_MASK_ISA_LZCNT & ~ix86_isa_flags_explicit;
+
/* Validate -mpreferred-stack-boundary= value or default it to
PREFERRED_STACK_BOUNDARY_DEFAULT. */
ix86_preferred_stack_boundary = PREFERRED_STACK_BOUNDARY_DEFAULT;
IX86_ATTR_ISA ("3dnow", OPT_m3dnow),
IX86_ATTR_ISA ("abm", OPT_mabm),
IX86_ATTR_ISA ("bmi", OPT_mbmi),
+ IX86_ATTR_ISA ("lzcnt", OPT_mlzcnt),
IX86_ATTR_ISA ("tbm", OPT_mtbm),
IX86_ATTR_ISA ("aes", OPT_maes),
IX86_ATTR_ISA ("avx", OPT_mavx),
{ OPTION_MASK_ISA_AVX, CODE_FOR_copysignv8sf3, "__builtin_ia32_copysignps256", IX86_BUILTIN_CPYSGNPS256, UNKNOWN, (int) V8SF_FTYPE_V8SF_V8SF },
{ OPTION_MASK_ISA_AVX, CODE_FOR_copysignv4df3, "__builtin_ia32_copysignpd256", IX86_BUILTIN_CPYSGNPD256, UNKNOWN, (int) V4DF_FTYPE_V4DF_V4DF },
- { OPTION_MASK_ISA_ABM, CODE_FOR_clzhi2_abm, "__builtin_clzs", IX86_BUILTIN_CLZS, UNKNOWN, (int) UINT16_FTYPE_UINT16 },
+ { OPTION_MASK_ISA_LZCNT, CODE_FOR_clzhi2_lzcnt, "__builtin_clzs", IX86_BUILTIN_CLZS, UNKNOWN, (int) UINT16_FTYPE_UINT16 },
/* BMI */
{ OPTION_MASK_ISA_BMI, CODE_FOR_bmi_bextr_si, "__builtin_ia32_bextr_u32", IX86_BUILTIN_BEXTR32, UNKNOWN, (int) UINT_FTYPE_UINT_UINT },
#define TARGET_ROUND OPTION_ISA_ROUND
#define TARGET_ABM OPTION_ISA_ABM
#define TARGET_BMI OPTION_ISA_BMI
+#define TARGET_LZCNT OPTION_ISA_LZCNT
#define TARGET_TBM OPTION_ISA_TBM
#define TARGET_POPCNT OPTION_ISA_POPCNT
#define TARGET_SAHF OPTION_ISA_SAHF
#define CTZ_DEFINED_VALUE_AT_ZERO(MODE, VALUE) \
((VALUE) = GET_MODE_BITSIZE (MODE), TARGET_BMI)
#define CLZ_DEFINED_VALUE_AT_ZERO(MODE, VALUE) \
- ((VALUE) = GET_MODE_BITSIZE (MODE), TARGET_BMI)
+ ((VALUE) = GET_MODE_BITSIZE (MODE), TARGET_LZCNT)
/* Flags returned by ix86_get_callcvt (). */
(clobber (reg:CC FLAGS_REG))])]
""
{
- if (TARGET_ABM)
+ if (TARGET_LZCNT)
{
- emit_insn (gen_clz<mode>2_abm (operands[0], operands[1]));
+ emit_insn (gen_clz<mode>2_lzcnt (operands[0], operands[1]));
DONE;
}
operands[2] = GEN_INT (GET_MODE_BITSIZE (<MODE>mode)-1);
})
-(define_insn "clz<mode>2_abm"
+(define_insn "clz<mode>2_lzcnt"
[(set (match_operand:SWI248 0 "register_operand" "=r")
(clz:SWI248 (match_operand:SWI248 1 "nonimmediate_operand" "rm")))
(clobber (reg:CC FLAGS_REG))]
- "TARGET_ABM || TARGET_BMI"
+ "TARGET_LZCNT"
"lzcnt{<imodesuffix>}\t{%1, %0|%0, %1}"
[(set_attr "prefix_rep" "1")
(set_attr "type" "bitmanip")
Target Report Mask(ISA_BMI) Var(ix86_isa_flags) Save
Support BMI built-in functions and code generation
+mlzcnt
+Target Report Mask(ISA_LZCNT) Var(ix86_isa_flags) Save
+Support LZCNT built-in function and code generation
+
mtbm
Target Report Mask(ISA_TBM) Var(ix86_isa_flags) Save
Support TBM built-in functions and code generation
<http://www.gnu.org/licenses/>. */
#ifndef _X86INTRIN_H_INCLUDED
-# error "Never use <abmintrin.h> directly; include <x86intrin.h> instead."
+# error "Never use <lzcntintrin.h> directly; include <x86intrin.h> instead."
#endif
-#ifndef __ABM__
-# error "ABM instruction set not enabled"
-#endif /* __ABM__ */
+#ifndef __LZCNT__
+# error "LZCNT instruction is not enabled"
+#endif /* __LZCNT__ */
-#ifndef _ABMINTRIN_H_INCLUDED
-#define _ABMINTRIN_H_INCLUDED
+#ifndef _LZCNTINTRIN_H_INCLUDED
+#define _LZCNTINTRIN_H_INCLUDED
extern __inline unsigned short __attribute__((__gnu_inline__, __always_inline__, __artificial__))
__lzcnt16 (unsigned short __X)
}
extern __inline unsigned int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
-__lzcnt (unsigned int __X)
+__lzcnt32 (unsigned int __X)
{
return __builtin_clz (__X);
}
}
#endif
-#endif /* _ABMINTRIN_H_INCLUDED */
+#endif /* _LZCNTINTRIN_H_INCLUDED */
#include <lwpintrin.h>
#endif
-#ifdef __ABM__
-#include <abmintrin.h>
-#endif
-
#ifdef __BMI__
#include <bmiintrin.h>
#endif
#include <tbmintrin.h>
#endif
+#ifdef __LZCNT__
+#include <lzcntintrin.h>
+#endif
+
#ifdef __POPCNT__
#include <popcntintrin.h>
#endif
@smallexample
unsigned int __builtin_ia32_bextr_u32(unsigned int, unsigned int);
unsigned long long __builtin_ia32_bextr_u64 (unsigned long long, unsigned long long);
+@end smallexample
+
+The following built-in functions are available when @option{-mlzcnt} is used.
+All of them generate the machine instruction that is part of the name.
+@smallexample
unsigned short __builtin_ia32_lzcnt_16(unsigned short);
unsigned int __builtin_ia32_lzcnt_u32(unsigned int);
unsigned long long __builtin_ia32_lzcnt_u64 (unsigned long long);
-mcld -mcx16 -msahf -mmovbe -mcrc32 -mrecip -mvzeroupper @gol
-mmmx -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4 -mavx @gol
-maes -mpclmul -mfsgsbase -mrdrnd -mf16c -mfma @gol
--msse4a -m3dnow -mpopcnt -mabm -mbmi -mtbm -mfma4 -mxop -mlwp @gol
--mthreads -mno-align-stringops -minline-all-stringops @gol
+-msse4a -m3dnow -mpopcnt -mabm -mbmi -mtbm -mfma4 -mxop -mlzcnt @gol
+-mlwp -mthreads -mno-align-stringops -minline-all-stringops @gol
-minline-stringops-dynamically -mstringop-strategy=@var{alg} @gol
-mpush-args -maccumulate-outgoing-args -m128bit-long-double @gol
-m96bit-long-double -mregparm=@var{num} -msseregparm @gol
@itemx -mno-abm
@itemx -mbmi
@itemx -mno-bmi
+@itemx -mlzcnt
+@itemx -mno-lzcnt
@itemx -mtbm
@itemx -mno-tbm
@opindex mmmx
@opindex mno-3dnow
These switches enable or disable the use of instructions in the MMX, SSE,
SSE2, SSE3, SSSE3, SSE4.1, AVX, AES, PCLMUL, FSGSBASE, RDRND, F16C, FMA,
-SSE4A, FMA4, XOP, LWP, ABM, BMI, or 3DNow!@: extended instruction sets.
+SSE4A, FMA4, XOP, LWP, ABM, BMI, LZCNT or 3DNow!@: extended instruction sets.
These extensions are also available as built-in functions: see
@ref{X86 Built-in Functions}, for details of the functions enabled and
disabled by these switches.
+2011-08-01 Kirill Yukhin <kirill.yukhin@intel.com>
+
+ * gcc.target/i386/i386.exp (check_effective_target_lzcnt): New.
+ * gcc.target/i386/lzcnt-1.c: New test.
+ * gcc.target/i386/lzcnt-2.c: Likewise.
+ * gcc.target/i386/lzcnt-2a.c: Likewise.
+ * gcc.target/i386/lzcnt-3.c: Likewise.
+ * gcc.target/i386/lzcnt-4.c: Likewise.
+ * gcc.target/i386/lzcnt-4a.c: Likewise.
+ * gcc.target/i386/lzcnt-5.c: Likewise.
+ * gcc.target/i386/lzcnt-6.c: Likewise.
+ * gcc.target/i386/lzcnt-6a.c: Likewise.
+ * gcc.target/i386/lzcnt-check.h: Likewise.
+
+ * gcc.target/i386/sse-12.c (dg-compile): Add -mlzcnt.
+ * gcc.target/i386/sse-13.c: Likewise.
+ * gcc.target/i386/sse-14.c: Likewise.
+ * g++.dg/other/i386-2.C: Likewise.
+ * g++.dg/other/i386-3.C: Likewise.
+
2011-08-01 Julian Brown <julian@codesourcery.com>
* gcc.target/arm/fixed-point-exec.c: New test.
/* { dg-do compile { target i?86-*-* x86_64-*-* } } */
-/* { dg-options "-O -pedantic-errors -march=k8 -msse4a -m3dnow -mavx -mfma4 -mxop -maes -mpclmul -mpopcnt -mabm -mbmi -mtbm -mlwp -mfsgsbase -mrdrnd -mf16c" } */
+/* { dg-options "-O -pedantic-errors -march=k8 -msse4a -m3dnow -mavx -mfma4 -mxop -maes -mpclmul -mpopcnt -mabm -mlzcnt -mbmi -mtbm -mlwp -mfsgsbase -mrdrnd -mf16c" } */
/* Test that {,x,e,p,t,s,w,a,b,i}mmintrin.h, mm3dnow.h, fma4intrin.h,
xopintrin.h, abmintrin.h, bmiintrin.h, tbmintrin.h, lwpintrin.h,
/* { dg-do compile { target i?86-*-* x86_64-*-* } } */
-/* { dg-options "-O -fkeep-inline-functions -march=k8 -msse4a -m3dnow -mavx -mfma4 -mxop -maes -mpclmul -mpopcnt -mabm -mbmi -mtbm -mlwp -mfsgsbase -mrdrnd -mf16c" } */
+/* { dg-options "-O -fkeep-inline-functions -march=k8 -msse4a -m3dnow -mavx -mfma4 -mxop -maes -mpclmul -mpopcnt -mabm -mlzcnt -mbmi -mtbm -mlwp -mfsgsbase -mrdrnd -mf16c" } */
/* Test that {,x,e,p,t,s,w,a,b,i}mmintrin.h, mm3dnow.h, fma4intrin.h,
xopintrin.h, abmintrin.h, bmiintrin.h, tbmintrin.h, lwpintrin.h,
} "-O2 -mxop" ]
}
+# Return 1 if lzcnt instruction can be compiled.
+proc check_effective_target_lzcnt { } {
+ return [check_no_compiler_messages lzcnt object {
+ unsigned short _lzcnt (unsigned short __X)
+ {
+ return __builtin_clzs (__X);
+ }
+ } "-mlzcnt" ]
+}
+
# Return 1 if bmi instructions can be compiled.
proc check_effective_target_bmi { } {
return [check_no_compiler_messages bmi object {
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-O2 -mlzcnt " } */
+/* { dg-final { scan-assembler "lzcntw\[^\\n]*(%|)ax" } } */
+
+#include <x86intrin.h>
+
+unsigned int
+func_lzcnt16 (unsigned int X)
+{
+ return __lzcnt16(X);
+}
--- /dev/null
+/* { dg-do run { target { lzcnt } } } */
+/* { dg-options "-O2 -mlzcnt -fno-inline" } */
+
+#include <x86intrin.h>
+
+#include "lzcnt-check.h"
+
+short calc_lzcnt_u16 (short src)
+{
+ int i;
+ short res = 0;
+
+ while ((res < 16) && (((src >> (15 - res)) & 1) == 0))
+ ++res;
+
+ return res;
+}
+
+static void
+lzcnt_test ()
+{
+ unsigned i;
+ short src = 0x7ace;
+ short res, res_ref;
+
+ for (i=0; i<5; ++i) {
+ src = src >> i;
+
+ res_ref = calc_lzcnt_u16 (src);
+ res = __lzcnt16 (src);
+
+ if (res != res_ref)
+ abort();
+ }
+}
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-O2 -mlzcnt" } */
+
+#include "lzcnt-2.c"
+
+/* { dg-final { scan-assembler "lzcntw" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-O0 -mlzcnt " } */
+/* { dg-final { scan-assembler "lzcntl\[^\\n]*(%|)eax" } } */
+
+#include <x86intrin.h>
+
+unsigned int
+func_lzcnt32 (unsigned int X)
+{
+ return __lzcnt32(X);
+}
--- /dev/null
+/* { dg-do run { target { lzcnt } } } */
+/* { dg-options "-O2 -mlzcnt -fno-inline" } */
+
+#include <x86intrin.h>
+
+#include "lzcnt-check.h"
+
+int calc_lzcnt_u32 (int src)
+{
+ int i;
+ int res = 0;
+
+ while ((res < 32) && (((src >> (31 - res)) & 1) == 0))
+ ++res;
+
+ return res;
+}
+
+static void
+lzcnt_test ()
+{
+ unsigned i;
+ int src = 0xce7ace0;
+ int res, res_ref;
+
+ for (i=0; i<5; ++i) {
+ src = src >> i;
+
+ res_ref = calc_lzcnt_u32 (src);
+ res = __lzcnt32 (src);
+
+ if (res != res_ref)
+ abort();
+ }
+}
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-O2 -mlzcnt" } */
+
+#include "lzcnt-4.c"
+
+/* { dg-final { scan-assembler "lzcntl" } } */
--- /dev/null
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O2 -mlzcnt" } */
+/* { dg-final { scan-assembler "lzcntq\[^\\n]*(%|)rax" } } */
+
+#include <x86intrin.h>
+
+unsigned int
+func_lzcnt64 (unsigned long long X)
+{
+ return __lzcnt64(X);
+}
--- /dev/null
+/* { dg-do run { target { lzcnt && { ! ia32 } } } } */
+/* { dg-options "-O2 -mlzcnt -fno-inline" } */
+
+#include <x86intrin.h>
+
+#include "lzcnt-check.h"
+
+long long calc_lzcnt_u64 (long long src)
+{
+ int i;
+ int res = 0;
+
+ while ((res < 64) && (((src >> (63 - res)) & 1) == 0))
+ ++res;
+
+ return res;
+}
+
+static void
+lzcnt_test ()
+{
+ unsigned i;
+ long long src = 0xce7ace0ce7ace0;
+ long long res, res_ref;
+
+ for (i=0; i<5; ++i) {
+ src = src >> i;
+
+ res_ref = calc_lzcnt_u64 (src);
+ res = __lzcnt64 (src);
+
+ if (res != res_ref)
+ abort();
+ }
+}
--- /dev/null
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O2 -mlzcnt" } */
+
+#include "lzcnt-6.c"
+
+/* { dg-final { scan-assembler "lzcntq" } } */
--- /dev/null
+#include <stdio.h>
+#include <stdlib.h>
+
+#include "cpuid.h"
+
+static void lzcnt_test (void);
+
+static void
+__attribute__ ((noinline))
+do_test (void)
+{
+ lzcnt_test ();
+}
+
+int
+main ()
+{
+ unsigned int eax, ebx, ecx, edx;
+
+ if (!__get_cpuid (0x80000001, &eax, &ebx, &ecx, &edx))
+ return 0;
+
+ /* Run LZCNT test only if host has LZCNT support. */
+ if (ecx & bit_LZCNT)
+ {
+ do_test ();
+#ifdef DEBUG
+ printf ("PASSED\n");
+#endif
+ }
+#ifdef DEBUG
+ else
+ printf ("SKIPPED\n");
+#endif
+
+ return 0;
+}
popcntintrin.h and mm_malloc.h are usable
with -O -std=c89 -pedantic-errors. */
/* { dg-do compile } */
-/* { dg-options "-O -std=c89 -pedantic-errors -march=k8 -msse4a -m3dnow -mavx -mfma4 -mxop -maes -mpclmul -mpopcnt -mabm -mbmi -mtbm -mlwp -mfsgsbase -mrdrnd -mf16c" } */
+/* { dg-options "-O -std=c89 -pedantic-errors -march=k8 -msse4a -m3dnow -mavx -mfma4 -mxop -maes -mpclmul -mpopcnt -mabm -mlzcnt -mbmi -mtbm -mlwp -mfsgsbase -mrdrnd -mf16c" } */
#include <x86intrin.h>
/* { dg-do compile } */
-/* { dg-options "-O2 -Werror-implicit-function-declaration -march=k8 -msse4a -m3dnow -mavx -mfma4 -mxop -maes -mpclmul -mpopcnt -mabm -mbmi -mtbm -mlwp -mfsgsbase -mrdrnd -mf16c" } */
+/* { dg-options "-O2 -Werror-implicit-function-declaration -march=k8 -msse4a -m3dnow -mavx -mfma4 -mxop -maes -mpclmul -mpopcnt -mabm -mlzcnt -mbmi -mtbm -mlwp -mfsgsbase -mrdrnd -mf16c" } */
#include <mm_malloc.h>
/* { dg-do compile } */
-/* { dg-options "-O0 -Werror-implicit-function-declaration -march=k8 -msse4a -m3dnow -mavx -mfma4 -mxop -maes -mpclmul -mpopcnt -mabm -mbmi -mtbm -mlwp -mfsgsbase -mrdrnd -mf16c" } */
+/* { dg-options "-O0 -Werror-implicit-function-declaration -march=k8 -msse4a -m3dnow -mavx -mfma4 -mxop -maes -mpclmul -mpopcnt -mabm -mlzcnt -mbmi -mtbm -mlwp -mfsgsbase -mrdrnd -mf16c" } */
#include <mm_malloc.h>