OpenE2K
/
gcc
2
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[AArch64] Pass number of units to aarch64_expand_vec_perm(_const) 

This patch passes the number of units to aarch64_expand_vec_perm
and aarch64_expand_vec_perm_const, which avoids a to_constant ()
once GET_MODE_NUNITS is variable.

2017-11-06  Richard Sandiford  <richard.sandiford@linaro.org>
	    Alan Hayward  <alan.hayward@arm.com>
	    David Sherwood  <david.sherwood@arm.com>

gcc/
	* config/aarch64/aarch64-protos.h (aarch64_expand_vec_perm)
	(aarch64_expand_vec_perm_const): Take the number of units too.
	* config/aarch64/aarch64.c (aarch64_expand_vec_perm)
	(aarch64_expand_vec_perm_const): Likewise.
	* config/aarch64/aarch64-simd.md (vec_perm_const<mode>)
	(vec_perm<mode>): Update accordingly.

Reviewed-by: James Greenhalgh <james.greenhalgh@arm.com>

Co-Authored-By: Alan Hayward <alan.hayward@arm.com>
Co-Authored-By: David Sherwood <david.sherwood@arm.com>

From-SVN: r254469
This commit is contained in:
Richard Sandiford 2017-11-06 20:02:49 +00:00 committed by Richard Sandiford
parent f5cbabc1cc
commit 8094001759
4 changed files with 26 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
gcc/ChangeLog
View File

@ -1,3 +1,14 @@
2017-11-06 Richard Sandiford <richard.sandiford@linaro.org>
Alan Hayward <alan.hayward@arm.com>
David Sherwood <david.sherwood@arm.com>
* config/aarch64/aarch64-protos.h (aarch64_expand_vec_perm)
(aarch64_expand_vec_perm_const): Take the number of units too.
* config/aarch64/aarch64.c (aarch64_expand_vec_perm)
(aarch64_expand_vec_perm_const): Likewise.
* config/aarch64/aarch64-simd.md (vec_perm_const<mode>)
(vec_perm<mode>): Update accordingly.
2017-11-06 Richard Sandiford <richard.sandiford@linaro.org>
Alan Hayward <alan.hayward@arm.com>
David Sherwood <david.sherwood@arm.com>

4
gcc/config/aarch64/aarch64-protos.h
View File

@ -471,11 +471,11 @@ tree aarch64_builtin_rsqrt (unsigned int);
tree aarch64_builtin_vectorized_function (unsigned int, tree, tree);
extern void aarch64_split_combinev16qi (rtx operands[3]);
extern void aarch64_expand_vec_perm (rtx target, rtx op0, rtx op1, rtx sel);
extern void aarch64_expand_vec_perm (rtx, rtx, rtx, rtx, unsigned int);
extern bool aarch64_madd_needs_nop (rtx_insn *);
extern void aarch64_final_prescan_insn (rtx_insn *);
extern bool
aarch64_expand_vec_perm_const (rtx target, rtx op0, rtx op1, rtx sel);
aarch64_expand_vec_perm_const (rtx, rtx, rtx, rtx, unsigned int);
void aarch64_atomic_assign_expand_fenv (tree *, tree *, tree *);
int aarch64_ccmp_mode_to_code (machine_mode mode);

4
gcc/config/aarch64/aarch64-simd.md
View File

@ -5239,7 +5239,7 @@
"TARGET_SIMD"
{
if (aarch64_expand_vec_perm_const (operands[0], operands[1],
operands[2], operands[3]))
operands[2], operands[3], <nunits>))
DONE;
else
FAIL;
@ -5253,7 +5253,7 @@
"TARGET_SIMD"
{
aarch64_expand_vec_perm (operands[0], operands[1],
operands[2], operands[3]);
operands[2], operands[3], <nunits>);
DONE;
})

18
gcc/config/aarch64/aarch64.c
View File

@ -13242,11 +13242,14 @@ aarch64_expand_vec_perm_1 (rtx target, rtx op0, rtx op1, rtx sel)
}
}
/* Expand a vec_perm with the operands given by TARGET, OP0, OP1 and SEL.
NELT is the number of elements in the vector. */
void
aarch64_expand_vec_perm (rtx target, rtx op0, rtx op1, rtx sel)
aarch64_expand_vec_perm (rtx target, rtx op0, rtx op1, rtx sel,
unsigned int nelt)
{
machine_mode vmode = GET_MODE (target);
unsigned int nelt = GET_MODE_NUNITS (vmode);
bool one_vector_p = rtx_equal_p (op0, op1);
rtx mask;
@ -13602,13 +13605,15 @@ aarch64_expand_vec_perm_const_1 (struct expand_vec_perm_d *d)
return false;
}
/* Expand a vec_perm_const pattern. */
/* Expand a vec_perm_const pattern with the operands given by TARGET,
OP0, OP1 and SEL. NELT is the number of elements in the vector. */
bool
aarch64_expand_vec_perm_const (rtx target, rtx op0, rtx op1, rtx sel)
aarch64_expand_vec_perm_const (rtx target, rtx op0, rtx op1, rtx sel,
unsigned int nelt)
{
struct expand_vec_perm_d d;
int i, nelt, which;
unsigned int i, which;
d.target = target;
d.op0 = op0;
@ -13618,12 +13623,11 @@ aarch64_expand_vec_perm_const (rtx target, rtx op0, rtx op1, rtx sel)
gcc_assert (VECTOR_MODE_P (d.vmode));
d.testing_p = false;
nelt = GET_MODE_NUNITS (d.vmode);
d.perm.reserve (nelt);
for (i = which = 0; i < nelt; ++i)
{
rtx e = XVECEXP (sel, 0, i);
int ei = INTVAL (e) & (2 * nelt - 1);
unsigned int ei = INTVAL (e) & (2 * nelt - 1);
which |= (ei < nelt ? 1 : 2);
d.perm.quick_push (ei);
}