Hello!
2016-10-25 Uros Bizjak <ubiz...@gmail.com>
Backport from mainline
2016-10-21 Jakub Jelinek <ja...@redhat.com>
PR target/78057
* config/i386/i386.c: Include fold-const-call.h, tree-vrp.h
and tree-ssanames.h.
(ix86_fold_builtin): Fold IX86_BUILTIN_[LT]ZCNT{16,32,64}
with INTEGER_CST argument.
(ix86_gimple_fold_builtin): New function.
(TARGET_GIMPLE_FOLD_BUILTIN): Define.
Backport from mainline
2016-10-20 Uros Bizjak <ubiz...@gmail.com>
PR target/78037
* config/i386/bmiintrin.h (__tzcnt_u16): Call __builtin_ia32_tzcnt_u16.
(__tzcnt_u32, _tzcnt_u32): Call __builtin_ia32_tzcnt_u32.
(__tzcnt_u64, _tzcnt_u64): Call __builtin_ia32_tzcnt_u64.
* config/i386/lzcntintrin.h (__lzcnt_u16): Call
__builtin_ia32_lzcnt_u16.
(__lzcnt_u32, _lzcnt_u32): Call __builtin_ia32_lzcnt_u32.
(__lzcnt_u64, _lzcnt_u64): Call __builtin_ia32_lzcnt_u64.
* config/i386/i386.md (UNSPEC_LZCNT, UNSPEC_TZCNT): New unspecs.
(ctz<mode>2, *ctz<mode>2): Use SWI48 mode iterator.
(bmi_tzcnt_<mode>): New expander.
(*bmi_tzcnt_<mode>_falsedep_1): New define_insn_and_split pattern.
(*bmi_tzcnt_<mode>_falsedep, *bmi_tzcnt_<mode>): New insn patterns.
(clz<mode>2_lzcnt, *clz<mode>2_lzcnt): Use SWI48 mode iterator.
(lzcnt_<mode>): New expander.
(*lzcnt_<mode>_falsedep_1): New define_insn_and_split pattern.
(*lzcnt_<mode>_falsedep, *lzcnt_<mode>): New insn patterns.
* config/i386/i386-builtin-types.def (UINT_FTYPE_UINT): New.
(UINT64_FTYPE_UINT64): New.
* config/i386/i386-builtin.def (__builtin_clzs): Remove description.
(__builtin_ia32_lzcnt_u16): New description.
(__builtin_ia32_lzcnt_u32): Ditto.
(__builtin_ia32_lzcnt_u64): Ditto.
(__builtin_ctzs): Remove description.
(__builtin_ia32_tzcnt_u16): New description.
(__builtin_ia32_tzcnt_u32): Ditto.
(__builtin_ia32_tzcnt_u64): Ditto.
* config/i386/i386.c (ix86_expand_args_builtin): Handle
UINT_FTYPE_UINT and UINT64_FTYPE_UINT64.
testsuite/ChangeLog:
2016-10-25 Uros Bizjak <ubiz...@gmail.com>
* gcc.target/i386/bmi-6.c: XFAIL.
Backport from mainline
2016-10-21 Jakub Jelinek <ja...@redhat.com>
PR target/78057
* gcc.target/i386/pr78057.c: New test.
Backport from mainline
2016-10-20 Uros Bizjak <ubiz...@gmail.com>
PR target/78037
* gcc.target/i386/pr78037.c: New test.
Bootstrapped and regression tested on x86_64-linux-gnu {,-m32}.
Please note that I have to XFAIL bmi-6.c due to insufficient inlining
on gcc-6 branch.
If there are no objections, I plan to commit the patch tomorrow.
Uros.
Index: config/i386/bmiintrin.h
===================================================================
--- config/i386/bmiintrin.h (revision 241451)
+++ config/i386/bmiintrin.h (working copy)
@@ -37,7 +37,7 @@
extern __inline unsigned short __attribute__((__gnu_inline__,
__always_inline__, __artificial__))
__tzcnt_u16 (unsigned short __X)
{
- return __builtin_ctzs (__X);
+ return __builtin_ia32_tzcnt_u16 (__X);
}
extern __inline unsigned int __attribute__((__gnu_inline__, __always_inline__,
__artificial__))
@@ -97,13 +97,13 @@ _blsr_u32 (unsigned int __X)
extern __inline unsigned int __attribute__((__gnu_inline__, __always_inline__,
__artificial__))
__tzcnt_u32 (unsigned int __X)
{
- return __builtin_ctz (__X);
+ return __builtin_ia32_tzcnt_u32 (__X);
}
extern __inline unsigned int __attribute__((__gnu_inline__, __always_inline__,
__artificial__))
_tzcnt_u32 (unsigned int __X)
{
- return __builtin_ctz (__X);
+ return __builtin_ia32_tzcnt_u32 (__X);
}
@@ -165,13 +165,13 @@ _blsr_u64 (unsigned long long __X)
extern __inline unsigned long long __attribute__((__gnu_inline__,
__always_inline__, __artificial__))
__tzcnt_u64 (unsigned long long __X)
{
- return __builtin_ctzll (__X);
+ return __builtin_ia32_tzcnt_u64 (__X);
}
extern __inline unsigned long long __attribute__((__gnu_inline__,
__always_inline__, __artificial__))
_tzcnt_u64 (unsigned long long __X)
{
- return __builtin_ctzll (__X);
+ return __builtin_ia32_tzcnt_u64 (__X);
}
#endif /* __x86_64__ */
Index: config/i386/i386-builtin-types.def
===================================================================
--- config/i386/i386-builtin-types.def (revision 241451)
+++ config/i386/i386-builtin-types.def (working copy)
@@ -201,9 +201,11 @@ DEF_FUNCTION_TYPE (INT, PCCHAR)
DEF_FUNCTION_TYPE (INT64, INT64)
DEF_FUNCTION_TYPE (INT64, V2DF)
DEF_FUNCTION_TYPE (INT64, V4SF)
+DEF_FUNCTION_TYPE (UINT, UINT)
+DEF_FUNCTION_TYPE (UINT16, UINT16)
DEF_FUNCTION_TYPE (UINT64, INT)
-DEF_FUNCTION_TYPE (UINT16, UINT16)
DEF_FUNCTION_TYPE (UINT64, PUNSIGNED)
+DEF_FUNCTION_TYPE (UINT64, UINT64)
DEF_FUNCTION_TYPE (V16QI, PCCHAR)
DEF_FUNCTION_TYPE (V16QI, V16QI)
DEF_FUNCTION_TYPE (V2DF, PCDOUBLE)
Index: config/i386/i386.c
===================================================================
--- config/i386/i386.c (revision 241451)
+++ config/i386/i386.c (working copy)
@@ -76,6 +76,8 @@ along with GCC; see the file COPYING3. If not see
#include "case-cfn-macros.h"
#include "regrename.h"
#include "dojump.h"
+#include "fold-const-call.h"
+#include "tree-ssanames.h"
/* This file should be included last. */
#include "target-def.h"
@@ -32356,7 +32358,10 @@ enum ix86_builtins
IX86_BUILTIN_LWPINS32,
IX86_BUILTIN_LWPINS64,
- IX86_BUILTIN_CLZS,
+ /* LZCNT */
+ IX86_BUILTIN_LZCNT16,
+ IX86_BUILTIN_LZCNT32,
+ IX86_BUILTIN_LZCNT64,
/* RTM */
IX86_BUILTIN_XBEGIN,
@@ -32380,7 +32385,9 @@ enum ix86_builtins
/* BMI instructions. */
IX86_BUILTIN_BEXTR32,
IX86_BUILTIN_BEXTR64,
- IX86_BUILTIN_CTZS,
+ IX86_BUILTIN_TZCNT16,
+ IX86_BUILTIN_TZCNT32,
+ IX86_BUILTIN_TZCNT64,
/* TBM instructions. */
IX86_BUILTIN_BEXTRI32,
@@ -33768,13 +33775,19 @@ static const struct builtin_description bdesc_args
{ OPTION_MASK_ISA_AVX2, CODE_FOR_avx2_lshrvv8si, "__builtin_ia32_psrlv8si",
IX86_BUILTIN_PSRLVV8SI, UNKNOWN, (int) V8SI_FTYPE_V8SI_V8SI },
{ OPTION_MASK_ISA_AVX2, CODE_FOR_avx2_lshrvv4si, "__builtin_ia32_psrlv4si",
IX86_BUILTIN_PSRLVV4SI, UNKNOWN, (int) V4SI_FTYPE_V4SI_V4SI },
- { OPTION_MASK_ISA_LZCNT, CODE_FOR_clzhi2_lzcnt, "__builtin_clzs",
IX86_BUILTIN_CLZS, UNKNOWN, (int) UINT16_FTYPE_UINT16 },
+ /* LZCNT */
+ { OPTION_MASK_ISA_LZCNT, CODE_FOR_lzcnt_hi, "__builtin_ia32_lzcnt_u16",
IX86_BUILTIN_LZCNT16, UNKNOWN, (int) UINT16_FTYPE_UINT16 },
+ { OPTION_MASK_ISA_LZCNT, CODE_FOR_lzcnt_si, "__builtin_ia32_lzcnt_u32",
IX86_BUILTIN_LZCNT32, UNKNOWN, (int) UINT_FTYPE_UINT },
+ { OPTION_MASK_ISA_LZCNT | OPTION_MASK_ISA_64BIT, CODE_FOR_lzcnt_di,
"__builtin_ia32_lzcnt_u64", IX86_BUILTIN_LZCNT64, UNKNOWN, (int)
UINT64_FTYPE_UINT64 },
/* BMI */
{ OPTION_MASK_ISA_BMI, CODE_FOR_bmi_bextr_si, "__builtin_ia32_bextr_u32",
IX86_BUILTIN_BEXTR32, UNKNOWN, (int) UINT_FTYPE_UINT_UINT },
{ OPTION_MASK_ISA_BMI | OPTION_MASK_ISA_64BIT, CODE_FOR_bmi_bextr_di,
"__builtin_ia32_bextr_u64", IX86_BUILTIN_BEXTR64, UNKNOWN, (int)
UINT64_FTYPE_UINT64_UINT64 },
- { OPTION_MASK_ISA_BMI, CODE_FOR_ctzhi2, "__builtin_ctzs",
IX86_BUILTIN_CTZS, UNKNOWN, (int) UINT16_FTYPE_UINT16 },
+ { OPTION_MASK_ISA_BMI, CODE_FOR_bmi_tzcnt_hi, "__builtin_ia32_tzcnt_u16",
IX86_BUILTIN_TZCNT16, UNKNOWN, (int) UINT16_FTYPE_UINT16 },
+ { OPTION_MASK_ISA_BMI, CODE_FOR_bmi_tzcnt_si, "__builtin_ia32_tzcnt_u32",
IX86_BUILTIN_TZCNT32, UNKNOWN, (int) UINT_FTYPE_UINT },
+ { OPTION_MASK_ISA_BMI | OPTION_MASK_ISA_64BIT, CODE_FOR_bmi_tzcnt_di,
"__builtin_ia32_tzcnt_u64", IX86_BUILTIN_TZCNT64, UNKNOWN, (int)
UINT64_FTYPE_UINT64 },
+
/* TBM */
{ OPTION_MASK_ISA_TBM, CODE_FOR_tbm_bextri_si, "__builtin_ia32_bextri_u32",
IX86_BUILTIN_BEXTRI32, UNKNOWN, (int) UINT_FTYPE_UINT_UINT },
{ OPTION_MASK_ISA_TBM | OPTION_MASK_ISA_64BIT, CODE_FOR_tbm_bextri_di,
"__builtin_ia32_bextri_u64", IX86_BUILTIN_BEXTRI64, UNKNOWN, (int)
UINT64_FTYPE_UINT64_UINT64 },
@@ -37546,11 +37559,49 @@ ix86_fold_builtin (tree fndecl, int n_args,
{
enum ix86_builtins fn_code = (enum ix86_builtins)
DECL_FUNCTION_CODE (fndecl);
- if (fn_code == IX86_BUILTIN_CPU_IS
- || fn_code == IX86_BUILTIN_CPU_SUPPORTS)
+ switch (fn_code)
{
+ case IX86_BUILTIN_CPU_IS:
+ case IX86_BUILTIN_CPU_SUPPORTS:
gcc_assert (n_args == 1);
return fold_builtin_cpu (fndecl, args);
+
+ case IX86_BUILTIN_TZCNT16:
+ case IX86_BUILTIN_TZCNT32:
+ case IX86_BUILTIN_TZCNT64:
+ gcc_assert (n_args == 1);
+ if (TREE_CODE (args[0]) == INTEGER_CST)
+ {
+ tree type = TREE_TYPE (TREE_TYPE (fndecl));
+ tree arg = args[0];
+ if (fn_code == IX86_BUILTIN_TZCNT16)
+ arg = fold_convert (short_unsigned_type_node, arg);
+ if (integer_zerop (arg))
+ return build_int_cst (type, TYPE_PRECISION (TREE_TYPE (arg)));
+ else
+ return fold_const_call (CFN_CTZ, type, arg);
+ }
+ break;
+
+ case IX86_BUILTIN_LZCNT16:
+ case IX86_BUILTIN_LZCNT32:
+ case IX86_BUILTIN_LZCNT64:
+ gcc_assert (n_args == 1);
+ if (TREE_CODE (args[0]) == INTEGER_CST)
+ {
+ tree type = TREE_TYPE (TREE_TYPE (fndecl));
+ tree arg = args[0];
+ if (fn_code == IX86_BUILTIN_LZCNT16)
+ arg = fold_convert (short_unsigned_type_node, arg);
+ if (integer_zerop (arg))
+ return build_int_cst (type, TYPE_PRECISION (TREE_TYPE (arg)));
+ else
+ return fold_const_call (CFN_CLZ, type, arg);
+ }
+ break;
+
+ default:
+ break;
}
}
@@ -37561,6 +37612,70 @@ ix86_fold_builtin (tree fndecl, int n_args,
return NULL_TREE;
}
+/* Fold a MD builtin (use ix86_fold_builtin for folding into
+ constant) in GIMPLE. */
+
+bool
+ix86_gimple_fold_builtin (gimple_stmt_iterator *gsi)
+{
+ gimple *stmt = gsi_stmt (*gsi);
+ tree fndecl = gimple_call_fndecl (stmt);
+ gcc_checking_assert (fndecl && DECL_BUILT_IN_CLASS (fndecl) == BUILT_IN_MD);
+ int n_args = gimple_call_num_args (stmt);
+ enum ix86_builtins fn_code = (enum ix86_builtins) DECL_FUNCTION_CODE
(fndecl);
+ tree decl = NULL_TREE;
+ tree arg0;
+
+ switch (fn_code)
+ {
+ case IX86_BUILTIN_TZCNT32:
+ decl = builtin_decl_implicit (BUILT_IN_CTZ);
+ goto fold_tzcnt_lzcnt;
+
+ case IX86_BUILTIN_TZCNT64:
+ decl = builtin_decl_implicit (BUILT_IN_CTZLL);
+ goto fold_tzcnt_lzcnt;
+
+ case IX86_BUILTIN_LZCNT32:
+ decl = builtin_decl_implicit (BUILT_IN_CLZ);
+ goto fold_tzcnt_lzcnt;
+
+ case IX86_BUILTIN_LZCNT64:
+ decl = builtin_decl_implicit (BUILT_IN_CLZLL);
+ goto fold_tzcnt_lzcnt;
+
+ fold_tzcnt_lzcnt:
+ gcc_assert (n_args == 1);
+ arg0 = gimple_call_arg (stmt, 0);
+ if (TREE_CODE (arg0) == SSA_NAME && decl && gimple_call_lhs (stmt))
+ {
+ int prec = TYPE_PRECISION (TREE_TYPE (arg0));
+ /* If arg0 is provably non-zero, optimize into generic
+ __builtin_c[tl]z{,ll} function the middle-end handles
+ better. */
+ if (!expr_not_equal_to (arg0, wi::zero (prec)))
+ return false;
+
+ location_t loc = gimple_location (stmt);
+ gimple *g = gimple_build_call (decl, 1, arg0);
+ gimple_set_location (g, loc);
+ tree lhs = make_ssa_name (integer_type_node);
+ gimple_call_set_lhs (g, lhs);
+ gsi_insert_before (gsi, g, GSI_SAME_STMT);
+ g = gimple_build_assign (gimple_call_lhs (stmt), NOP_EXPR, lhs);
+ gimple_set_location (g, loc);
+ gsi_replace (gsi, g, true);
+ return true;
+ }
+ break;
+
+ default:
+ break;
+ }
+
+ return false;
+}
+
/* Make builtins to detect cpu type and features supported. NAME is
the builtin name, CODE is the builtin code, and FTYPE is the function
type of the builtin. */
@@ -38522,8 +38637,10 @@ ix86_expand_args_builtin (const struct builtin_des
case FLOAT128_FTYPE_FLOAT128:
case FLOAT_FTYPE_FLOAT:
case INT_FTYPE_INT:
+ case UINT_FTYPE_UINT:
+ case UINT16_FTYPE_UINT16:
case UINT64_FTYPE_INT:
- case UINT16_FTYPE_UINT16:
+ case UINT64_FTYPE_UINT64:
case INT64_FTYPE_INT64:
case INT64_FTYPE_V4SF:
case INT64_FTYPE_V2DF:
@@ -54588,6 +54705,9 @@ ix86_addr_space_zero_address_valid (addr_space_t a
#undef TARGET_FOLD_BUILTIN
#define TARGET_FOLD_BUILTIN ix86_fold_builtin
+#undef TARGET_GIMPLE_FOLD_BUILTIN
+#define TARGET_GIMPLE_FOLD_BUILTIN ix86_gimple_fold_builtin
+
#undef TARGET_COMPARE_VERSION_PRIORITY
#define TARGET_COMPARE_VERSION_PRIORITY ix86_compare_version_priority
Index: config/i386/i386.md
===================================================================
--- config/i386/i386.md (revision 241451)
+++ config/i386/i386.md (working copy)
@@ -174,7 +174,11 @@
;; For CRC32 support
UNSPEC_CRC32
+ ;; For LZCNT suppoprt
+ UNSPEC_LZCNT
+
;; For BMI support
+ UNSPEC_TZCNT
UNSPEC_BEXTR
;; For BMI2 support
@@ -12810,9 +12814,9 @@
(define_expand "ctz<mode>2"
[(parallel
- [(set (match_operand:SWI248 0 "register_operand")
- (ctz:SWI248
- (match_operand:SWI248 1 "nonimmediate_operand")))
+ [(set (match_operand:SWI48 0 "register_operand")
+ (ctz:SWI48
+ (match_operand:SWI48 1 "nonimmediate_operand")))
(clobber (reg:CC FLAGS_REG))])])
; False dependency happens when destination is only updated by tzcnt,
@@ -12860,8 +12864,8 @@
(set_attr "mode" "<MODE>")])
(define_insn "*ctz<mode>2"
- [(set (match_operand:SWI248 0 "register_operand" "=r")
- (ctz:SWI248 (match_operand:SWI248 1 "nonimmediate_operand" "rm")))
+ [(set (match_operand:SWI48 0 "register_operand" "=r")
+ (ctz:SWI48 (match_operand:SWI48 1 "nonimmediate_operand" "rm")))
(clobber (reg:CC FLAGS_REG))]
""
{
@@ -12886,15 +12890,78 @@
(const_string "0")))
(set_attr "mode" "<MODE>")])
+;; Version of tzcnt that is expanded from intrinsics. This version provides
+;; operand size as output when source operand is zero.
+
+(define_expand "bmi_tzcnt_<mode>"
+ [(parallel
+ [(set (match_operand:SWI248 0 "register_operand")
+ (unspec:SWI248
+ [(match_operand:SWI248 1 "nonimmediate_operand")]
+ UNSPEC_TZCNT))
+ (clobber (reg:CC FLAGS_REG))])]
+ "TARGET_BMI")
+
+; False dependency happens when destination is only updated by tzcnt,
+; lzcnt or popcnt. There is no false dependency when destination is
+; also used in source.
+(define_insn_and_split "*bmi_tzcnt_<mode>_falsedep_1"
+ [(set (match_operand:SWI48 0 "register_operand" "=r")
+ (unspec:SWI48
+ [(match_operand:SWI48 1 "nonimmediate_operand" "rm")]
+ UNSPEC_TZCNT))
+ (clobber (reg:CC FLAGS_REG))]
+ "TARGET_BMI
+ && TARGET_AVOID_FALSE_DEP_FOR_BMI && optimize_function_for_speed_p (cfun)"
+ "#"
+ "&& reload_completed"
+ [(parallel
+ [(set (match_dup 0)
+ (unspec:SWI48 [(match_dup 1)] UNSPEC_TZCNT))
+ (unspec [(match_dup 0)] UNSPEC_INSN_FALSE_DEP)
+ (clobber (reg:CC FLAGS_REG))])]
+{
+ if (!reg_mentioned_p (operands[0], operands[1]))
+ ix86_expand_clear (operands[0]);
+})
+
+(define_insn "*bmi_tzcnt_<mode>_falsedep"
+ [(set (match_operand:SWI48 0 "register_operand" "=r")
+ (unspec:SWI48
+ [(match_operand:SWI48 1 "nonimmediate_operand" "rm")]
+ UNSPEC_TZCNT))
+ (unspec [(match_operand:SWI48 2 "register_operand" "0")]
+ UNSPEC_INSN_FALSE_DEP)
+ (clobber (reg:CC FLAGS_REG))]
+ "TARGET_BMI"
+ "tzcnt{<imodesuffix>}\t{%1, %0|%0, %1}"
+ [(set_attr "type" "alu1")
+ (set_attr "prefix_0f" "1")
+ (set_attr "prefix_rep" "1")
+ (set_attr "mode" "<MODE>")])
+
+(define_insn "*bmi_tzcnt_<mode>"
+ [(set (match_operand:SWI248 0 "register_operand" "=r")
+ (unspec:SWI248
+ [(match_operand:SWI248 1 "nonimmediate_operand" "rm")]
+ UNSPEC_TZCNT))
+ (clobber (reg:CC FLAGS_REG))]
+ "TARGET_BMI"
+ "tzcnt{<imodesuffix>}\t{%1, %0|%0, %1}"
+ [(set_attr "type" "alu1")
+ (set_attr "prefix_0f" "1")
+ (set_attr "prefix_rep" "1")
+ (set_attr "mode" "<MODE>")])
+
(define_expand "clz<mode>2"
[(parallel
- [(set (match_operand:SWI248 0 "register_operand")
- (minus:SWI248
+ [(set (match_operand:SWI48 0 "register_operand")
+ (minus:SWI48
(match_dup 2)
- (clz:SWI248 (match_operand:SWI248 1 "nonimmediate_operand"))))
+ (clz:SWI48 (match_operand:SWI48 1 "nonimmediate_operand"))))
(clobber (reg:CC FLAGS_REG))])
(parallel
- [(set (match_dup 0) (xor:SWI248 (match_dup 0) (match_dup 2)))
+ [(set (match_dup 0) (xor:SWI48 (match_dup 0) (match_dup 2)))
(clobber (reg:CC FLAGS_REG))])]
""
{
@@ -12908,9 +12975,9 @@
(define_expand "clz<mode>2_lzcnt"
[(parallel
- [(set (match_operand:SWI248 0 "register_operand")
- (clz:SWI248
- (match_operand:SWI248 1 "nonimmediate_operand")))
+ [(set (match_operand:SWI48 0 "register_operand")
+ (clz:SWI48
+ (match_operand:SWI48 1 "nonimmediate_operand")))
(clobber (reg:CC FLAGS_REG))])]
"TARGET_LZCNT")
@@ -12947,8 +13014,8 @@
(set_attr "mode" "<MODE>")])
(define_insn "*clz<mode>2_lzcnt"
- [(set (match_operand:SWI248 0 "register_operand" "=r")
- (clz:SWI248 (match_operand:SWI248 1 "nonimmediate_operand" "rm")))
+ [(set (match_operand:SWI48 0 "register_operand" "=r")
+ (clz:SWI48 (match_operand:SWI48 1 "nonimmediate_operand" "rm")))
(clobber (reg:CC FLAGS_REG))]
"TARGET_LZCNT"
"lzcnt{<imodesuffix>}\t{%1, %0|%0, %1}"
@@ -12956,6 +13023,69 @@
(set_attr "type" "bitmanip")
(set_attr "mode" "<MODE>")])
+;; Version of lzcnt that is expanded from intrinsics. This version provides
+;; operand size as output when source operand is zero.
+
+(define_expand "lzcnt_<mode>"
+ [(parallel
+ [(set (match_operand:SWI248 0 "register_operand")
+ (unspec:SWI248
+ [(match_operand:SWI248 1 "nonimmediate_operand")]
+ UNSPEC_LZCNT))
+ (clobber (reg:CC FLAGS_REG))])]
+ "TARGET_LZCNT")
+
+; False dependency happens when destination is only updated by tzcnt,
+; lzcnt or popcnt. There is no false dependency when destination is
+; also used in source.
+(define_insn_and_split "*lzcnt_<mode>_falsedep_1"
+ [(set (match_operand:SWI48 0 "register_operand" "=r")
+ (unspec:SWI48
+ [(match_operand:SWI48 1 "nonimmediate_operand" "rm")]
+ UNSPEC_LZCNT))
+ (clobber (reg:CC FLAGS_REG))]
+ "TARGET_LZCNT
+ && TARGET_AVOID_FALSE_DEP_FOR_BMI && optimize_function_for_speed_p (cfun)"
+ "#"
+ "&& reload_completed"
+ [(parallel
+ [(set (match_dup 0)
+ (unspec:SWI48 [(match_dup 1)] UNSPEC_LZCNT))
+ (unspec [(match_dup 0)] UNSPEC_INSN_FALSE_DEP)
+ (clobber (reg:CC FLAGS_REG))])]
+{
+ if (!reg_mentioned_p (operands[0], operands[1]))
+ ix86_expand_clear (operands[0]);
+})
+
+(define_insn "*lzcnt_<mode>_falsedep"
+ [(set (match_operand:SWI48 0 "register_operand" "=r")
+ (unspec:SWI48
+ [(match_operand:SWI48 1 "nonimmediate_operand" "rm")]
+ UNSPEC_LZCNT))
+ (unspec [(match_operand:SWI48 2 "register_operand" "0")]
+ UNSPEC_INSN_FALSE_DEP)
+ (clobber (reg:CC FLAGS_REG))]
+ "TARGET_LZCNT"
+ "lzcnt{<imodesuffix>}\t{%1, %0|%0, %1}"
+ [(set_attr "type" "alu1")
+ (set_attr "prefix_0f" "1")
+ (set_attr "prefix_rep" "1")
+ (set_attr "mode" "<MODE>")])
+
+(define_insn "*lzcnt_<mode>"
+ [(set (match_operand:SWI248 0 "register_operand" "=r")
+ (unspec:SWI248
+ [(match_operand:SWI248 1 "nonimmediate_operand" "rm")]
+ UNSPEC_LZCNT))
+ (clobber (reg:CC FLAGS_REG))]
+ "TARGET_LZCNT"
+ "lzcnt{<imodesuffix>}\t{%1, %0|%0, %1}"
+ [(set_attr "type" "alu1")
+ (set_attr "prefix_0f" "1")
+ (set_attr "prefix_rep" "1")
+ (set_attr "mode" "<MODE>")])
+
;; BMI instructions.
(define_insn "*bmi_andn_<mode>"
[(set (match_operand:SWI48 0 "register_operand" "=r,r")
Index: config/i386/lzcntintrin.h
===================================================================
--- config/i386/lzcntintrin.h (revision 241451)
+++ config/i386/lzcntintrin.h (working copy)
@@ -38,19 +38,19 @@
extern __inline unsigned short __attribute__((__gnu_inline__,
__always_inline__, __artificial__))
__lzcnt16 (unsigned short __X)
{
- return __builtin_clzs (__X);
+ return __builtin_ia32_lzcnt_u16 (__X);
}
extern __inline unsigned int __attribute__((__gnu_inline__, __always_inline__,
__artificial__))
__lzcnt32 (unsigned int __X)
{
- return __builtin_clz (__X);
+ return __builtin_ia32_lzcnt_u32 (__X);
}
extern __inline unsigned int __attribute__((__gnu_inline__, __always_inline__,
__artificial__))
_lzcnt_u32 (unsigned int __X)
{
- return __builtin_clz (__X);
+ return __builtin_ia32_lzcnt_u32 (__X);
}
#ifdef __x86_64__
@@ -57,13 +57,13 @@ _lzcnt_u32 (unsigned int __X)
extern __inline unsigned long long __attribute__((__gnu_inline__,
__always_inline__, __artificial__))
__lzcnt64 (unsigned long long __X)
{
- return __builtin_clzll (__X);
+ return __builtin_ia32_lzcnt_u64 (__X);
}
extern __inline unsigned long long __attribute__((__gnu_inline__,
__always_inline__, __artificial__))
_lzcnt_u64 (unsigned long long __X)
{
- return __builtin_clzll (__X);
+ return __builtin_ia32_lzcnt_u64 (__X);
}
#endif
Index: testsuite/gcc.target/i386/bmi-6.c
===================================================================
--- testsuite/gcc.target/i386/bmi-6.c (revision 241451)
+++ testsuite/gcc.target/i386/bmi-6.c (working copy)
@@ -1,4 +1,5 @@
/* { dg-do link } */
+/* { dg-xfail-if "PR 78057" { "*-*-*" } { "*" } { "" } } */
/* { dg-options "-O2 -mbmi" } */
#include <x86intrin.h>
Index: testsuite/gcc.target/i386/pr78037.c
===================================================================
--- testsuite/gcc.target/i386/pr78037.c (nonexistent)
+++ testsuite/gcc.target/i386/pr78037.c (working copy)
@@ -0,0 +1,21 @@
+/* { dg-do run } */
+/* { dg-require-effective-target bmi } */
+/* { dg-options "-O2 -mbmi" } */
+
+#include <x86intrin.h>
+
+#include "bmi-check.h"
+
+int
+__attribute__((noinline, noclone))
+foo (int x)
+{
+ return __tzcnt_u32 (x) & 0x1f;
+}
+
+static void
+bmi_test ()
+{
+ if (foo (0) != 0)
+ abort ();
+}
Index: testsuite/gcc.target/i386/pr78057.c
===================================================================
--- testsuite/gcc.target/i386/pr78057.c (nonexistent)
+++ testsuite/gcc.target/i386/pr78057.c (working copy)
@@ -0,0 +1,42 @@
+/* PR target/78057 */
+/* { dg-do compile } */
+/* { dg-options "-O2 -mbmi -mlzcnt -fdump-tree-optimized" } */
+
+extern void link_error (void);
+
+int
+foo (int x)
+{
+ if (__builtin_ia32_tzcnt_u16 (16) != 4
+ || __builtin_ia32_tzcnt_u16 (0) != 16
+ || __builtin_ia32_lzcnt_u16 (0x1ff) != 7
+ || __builtin_ia32_lzcnt_u16 (0) != 16
+ || __builtin_ia32_tzcnt_u32 (8) != 3
+ || __builtin_ia32_tzcnt_u32 (0) != 32
+ || __builtin_ia32_lzcnt_u32 (0x3fffffff) != 2
+ || __builtin_ia32_lzcnt_u32 (0) != 32
+#ifdef __x86_64__
+ || __builtin_ia32_tzcnt_u64 (4) != 2
+ || __builtin_ia32_tzcnt_u64 (0) != 64
+ || __builtin_ia32_lzcnt_u64 (0x1fffffff) != 35
+ || __builtin_ia32_lzcnt_u64 (0) != 64
+#endif
+ )
+ link_error ();
+ x += 2;
+ if (x == 0)
+ return 5;
+ return __builtin_ia32_tzcnt_u32 (x)
+ + __builtin_ia32_lzcnt_u32 (x)
+#ifdef __x86_64__
+ + __builtin_ia32_tzcnt_u64 (x)
+ + __builtin_ia32_lzcnt_u64 (x)
+#endif
+ ;
+}
+
+/* { dg-final { scan-tree-dump-not "link_error" "optimized" } } */
+/* { dg-final { scan-tree-dump-not "__builtin_ia32_\[lt]zcnt" "optimized" } }
*/
+/* { dg-final { scan-tree-dump-times "__builtin_ctz " 1 "optimized" } } */
+/* { dg-final { scan-tree-dump-times "__builtin_clz " 1 "optimized" } } */
+/* { dg-final { scan-tree-dump-times "__builtin_ctzll " 1 "optimized" { target
lp64 } } } */
