Commit da80a646 by Jakub Jelinek Committed by Jakub Jelinek

i386.c (ix86_expand_builtin): If gather mask argument is known to have all high bits set...

	* config/i386/i386.c (ix86_expand_builtin): If gather mask
	argument is known to have all high bits set, pass pc_rtx as
	second argument to the expander instead of op0.
	* config/i386/sse.md (*avx2_gathersi<mode>_2,
	*avx2_gatherdi<mode>_2): New patterns.
	* config/i386/avx2intrin.h (_mm256_i32gather_pd,
	_mm256_i64gather_pd, _mm256_i32gather_ps): Set mask using
	_mm256_cmp_pd with zero vector arguments and _CMP_EQ_OQ instead of
	_mm256_set1_pd.

From-SVN: r181090
parent aec7ae7d
2011-11-07 Jakub Jelinek <jakub@redhat.com>
* config/i386/i386.c (ix86_expand_builtin): If gather mask
argument is known to have all high bits set, pass pc_rtx as
second argument to the expander instead of op0.
* config/i386/sse.md (*avx2_gathersi<mode>_2,
*avx2_gatherdi<mode>_2): New patterns.
* config/i386/avx2intrin.h (_mm256_i32gather_pd,
_mm256_i64gather_pd, _mm256_i32gather_ps): Set mask using
_mm256_cmp_pd with zero vector arguments and _CMP_EQ_OQ instead of
_mm256_set1_pd.
PR tree-optimization/50789
* tree-vect-stmts.c (process_use): Add force argument, avoid
exist_non_indexing_operands_for_use_p check if true.
......@@ -1252,7 +1252,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_i32gather_pd (double const *base, __m128i index, const int scale)
{
__v4df src = _mm256_setzero_pd ();
__v4df mask = _mm256_set1_pd((double)(long long int) -1);
__v4df mask = _mm256_cmp_pd (src, src, _CMP_EQ_OQ);
return (__m256d) __builtin_ia32_gathersiv4df (src,
base,
......@@ -1304,7 +1304,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_i64gather_pd (double const *base, __m256i index, const int scale)
{
__v4df src = _mm256_setzero_pd ();
__v4df mask = _mm256_set1_pd((double)(long long int) -1);
__v4df mask = _mm256_cmp_pd (src, src, _CMP_EQ_OQ);
return (__m256d) __builtin_ia32_gatherdiv4df (src,
base,
......@@ -1356,7 +1356,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_i32gather_ps (float const *base, __m256i index, const int scale)
{
__v8sf src = _mm256_setzero_ps ();
__v8sf mask = _mm256_set1_ps((float)(int) -1);
__v8sf mask = _mm256_cmp_ps (src, src, _CMP_EQ_OQ);
return (__m256) __builtin_ia32_gathersiv8sf (src,
base,
......
......@@ -29087,6 +29087,71 @@ rdrand_step:
error ("last argument must be scale 1, 2, 4, 8");
return const0_rtx;
}
/* Optimize. If mask is known to have all high bits set,
replace op0 with pc_rtx to signal that the instruction
overwrites the whole destination and doesn't use its
previous contents. */
if (optimize)
{
if (TREE_CODE (arg3) == VECTOR_CST)
{
tree elt;
unsigned int negative = 0;
for (elt = TREE_VECTOR_CST_ELTS (arg3);
elt; elt = TREE_CHAIN (elt))
{
tree cst = TREE_VALUE (elt);
if (TREE_CODE (cst) == INTEGER_CST
&& tree_int_cst_sign_bit (cst))
negative++;
else if (TREE_CODE (cst) == REAL_CST
&& REAL_VALUE_NEGATIVE (TREE_REAL_CST (cst)))
negative++;
}
if (negative == TYPE_VECTOR_SUBPARTS (TREE_TYPE (arg3)))
op0 = pc_rtx;
}
else if (TREE_CODE (arg3) == SSA_NAME)
{
/* Recognize also when mask is like:
__v2df src = _mm_setzero_pd ();
__v2df mask = _mm_cmpeq_pd (src, src);
or
__v8sf src = _mm256_setzero_ps ();
__v8sf mask = _mm256_cmp_ps (src, src, _CMP_EQ_OQ);
as that is a cheaper way to load all ones into
a register than having to load a constant from
memory. */
gimple def_stmt = SSA_NAME_DEF_STMT (arg3);
if (is_gimple_call (def_stmt))
{
tree fndecl = gimple_call_fndecl (def_stmt);
if (fndecl
&& DECL_BUILT_IN_CLASS (fndecl) == BUILT_IN_MD)
switch ((unsigned int) DECL_FUNCTION_CODE (fndecl))
{
case IX86_BUILTIN_CMPPD:
case IX86_BUILTIN_CMPPS:
case IX86_BUILTIN_CMPPD256:
case IX86_BUILTIN_CMPPS256:
if (!integer_zerop (gimple_call_arg (def_stmt, 2)))
break;
/* FALLTHRU */
case IX86_BUILTIN_CMPEQPD:
case IX86_BUILTIN_CMPEQPS:
if (initializer_zerop (gimple_call_arg (def_stmt, 0))
&& initializer_zerop (gimple_call_arg (def_stmt,
1)))
op0 = pc_rtx;
break;
default:
break;
}
}
}
}
pat = GEN_FCN (icode) (subtarget, op0, op1, op2, op3, op4);
if (! pat)
return const0_rtx;
......@@ -12567,6 +12567,26 @@
(set_attr "prefix" "vex")
(set_attr "mode" "<sseinsnmode>")])
(define_insn "*avx2_gathersi<mode>_2"
[(set (match_operand:VEC_GATHER_MODE 0 "register_operand" "=&x")
(unspec:VEC_GATHER_MODE
[(pc)
(match_operator:<ssescalarmode> 6 "vsib_mem_operator"
[(unspec:P
[(match_operand:P 2 "vsib_address_operand" "p")
(match_operand:<VEC_GATHER_IDXSI> 3 "register_operand" "x")
(match_operand:SI 5 "const1248_operand" "n")]
UNSPEC_VSIBADDR)])
(mem:BLK (scratch))
(match_operand:VEC_GATHER_MODE 4 "register_operand" "1")]
UNSPEC_GATHER))
(clobber (match_scratch:VEC_GATHER_MODE 1 "=&x"))]
"TARGET_AVX2"
"v<sseintprefix>gatherd<ssemodesuffix>\t{%1, %6, %0|%0, %6, %1}"
[(set_attr "type" "ssemov")
(set_attr "prefix" "vex")
(set_attr "mode" "<sseinsnmode>")])
(define_expand "avx2_gatherdi<mode>"
[(parallel [(set (match_operand:VEC_GATHER_MODE 0 "register_operand" "")
(unspec:VEC_GATHER_MODE
......@@ -12608,3 +12628,27 @@
[(set_attr "type" "ssemov")
(set_attr "prefix" "vex")
(set_attr "mode" "<sseinsnmode>")])
(define_insn "*avx2_gatherdi<mode>_2"
[(set (match_operand:VEC_GATHER_MODE 0 "register_operand" "=&x")
(unspec:VEC_GATHER_MODE
[(pc)
(match_operator:<ssescalarmode> 6 "vsib_mem_operator"
[(unspec:P
[(match_operand:P 2 "vsib_address_operand" "p")
(match_operand:<VEC_GATHER_IDXDI> 3 "register_operand" "x")
(match_operand:SI 5 "const1248_operand" "n")]
UNSPEC_VSIBADDR)])
(mem:BLK (scratch))
(match_operand:<VEC_GATHER_SRCDI> 4 "register_operand" "1")]
UNSPEC_GATHER))
(clobber (match_scratch:VEC_GATHER_MODE 1 "=&x"))]
"TARGET_AVX2"
{
if (<MODE>mode != <VEC_GATHER_SRCDI>mode)
return "v<sseintprefix>gatherq<ssemodesuffix>\t{%4, %6, %x0|%x0, %6, %4}";
return "v<sseintprefix>gatherq<ssemodesuffix>\t{%4, %6, %0|%0, %6, %4}";
}
[(set_attr "type" "ssemov")
(set_attr "prefix" "vex")
(set_attr "mode" "<sseinsnmode>")])
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment