Skip to content

R
riscv-gcc-1
Commit ed6fa129 by Uros Bizjak
Options

re PR target/37101 (wrong code: tree vectorizer omits bogus movq/movlps construct) 

	PR target/37101
	* config/i386/sse.md (vec_concatv2di): Remove movlps alternative.
	(*vec_concatv2di_rex64_sse4_1): Ditto.
	(*vec_concatv2di_rex64_sse): Ditto.

testsuite/ChangeLog:

	PR target/37101
	* gcc.target/i386/pr37101.c: New test.

From-SVN: r139095
parent 2e1d2474
Showing with 101 additions and 28 deletions
gcc/ChangeLog
2008-08-14 Christophe Saout <christophe@saout.de>
Uros Bizjak <ubizjak@gmail.com>
PR target/37101
* config/i386/sse.md (vec_concatv2di): Remove movlps alternative.
(*vec_concatv2di_rex64_sse4_1): Ditto.
(*vec_concatv2di_rex64_sse): Ditto.
2008-08-14 Jakub Jelinek <jakub@redhat.com>
PR middle-end/37103
......@@ -139,7 +147,6 @@
2008-08-12 Nathan Froyd <froydnj@codesourcery.com>
PR libgomp/26165
* gcc.c (include_spec_function): Tweak call to find_a_file.
2008-08-12 Jakub Jelinek <jakub@redhat.com>
......@@ -155,7 +162,7 @@
2008-08-12 Anatoly Sokolov <aesok@post.ru>
* final.c (final_scan_insn): Use app_enable/app_disable functions.
* final.c (final_scan_insn): Use app_enable/app_disable functions.
2008-08-12 Ulrich Weigand <Ulrich.Weigand@de.ibm.com>
......@@ -685,8 +692,8 @@
2008-08-07 Bob Wilson <bob.wilson@acm.org>
* config/xtensa/xtensa.c (xtensa_copy_incoming_a7): Copy incoming value
in a6 after the set_frame_ptr insn.
* config/xtensa/xtensa.c (xtensa_copy_incoming_a7): Copy incoming
value in a6 after the set_frame_ptr insn.
2008-08-07 Richard Henderson <rth@redhat.com>
......@@ -774,7 +781,7 @@
* matrix-reorg.c (compute_offset): Avoid C++ keywords.
2008-08-06 Manuel Lopez-Ibanez <manu@gcc.gnu.org>
PR 26785
* diagnostic.c (permerror_at): New.
* toplev.h (permerror_at): Declare.
......
gcc/config/i386/sse.md
......@@ -4952,26 +4952,25 @@
(set_attr "mode" "TI,V4SF,V2SF")])
(define_insn "vec_concatv2di"
[(set (match_operand:V2DI 0 "register_operand" "=Y2 ,?Y2,Y2,x,x,x")
[(set (match_operand:V2DI 0 "register_operand" "=Y2 ,?Y2,Y2,x,x")
(vec_concat:V2DI
(match_operand:DI 1 "nonimmediate_operand" " mY2,*y ,0 ,0,0,m")
(match_operand:DI 2 "vector_move_operand" " C , C,Y2,x,m,0")))]
(match_operand:DI 1 "nonimmediate_operand" " mY2,*y ,0 ,0,0")
(match_operand:DI 2 "vector_move_operand" " C , C,Y2,x,m")))]
"!TARGET_64BIT && TARGET_SSE"
"@
movq\t{%1, %0|%0, %1}
movq2dq\t{%1, %0|%0, %1}
punpcklqdq\t{%2, %0|%0, %2}
movlhps\t{%2, %0|%0, %2}
movhps\t{%2, %0|%0, %2}
movlps\t{%1, %0|%0, %1}"
[(set_attr "type" "ssemov,ssemov,sselog,ssemov,ssemov,ssemov")
(set_attr "mode" "TI,TI,TI,V4SF,V2SF,V2SF")])
movhps\t{%2, %0|%0, %2}"
[(set_attr "type" "ssemov,ssemov,sselog,ssemov,ssemov")
(set_attr "mode" "TI,TI,TI,V4SF,V2SF")])
(define_insn "*vec_concatv2di_rex64_sse4_1"
[(set (match_operand:V2DI 0 "register_operand" "=x ,x ,Yi,!x,x,x,x,x")
[(set (match_operand:V2DI 0 "register_operand" "=x ,x ,Yi,!x,x,x,x")
(vec_concat:V2DI
(match_operand:DI 1 "nonimmediate_operand" " 0 ,mx,r ,*y,0,0,0,m")
(match_operand:DI 2 "vector_move_operand" " rm,C ,C ,C ,x,x,m,0")))]
(match_operand:DI 1 "nonimmediate_operand" " 0 ,mx,r ,*y,0,0,0")
(match_operand:DI 2 "vector_move_operand" " rm,C ,C ,C ,x,x,m")))]
"TARGET_64BIT && TARGET_SSE4_1"
"@
pinsrq\t{$0x1, %2, %0|%0, %2, 0x1}
......@@ -4980,17 +4979,16 @@
movq2dq\t{%1, %0|%0, %1}
punpcklqdq\t{%2, %0|%0, %2}
movlhps\t{%2, %0|%0, %2}
movhps\t{%2, %0|%0, %2}
movlps\t{%1, %0|%0, %1}"
[(set_attr "type" "sselog,ssemov,ssemov,ssemov,sselog,ssemov,ssemov,ssemov")
(set_attr "prefix_extra" "1,*,*,*,*,*,*,*")
(set_attr "mode" "TI,TI,TI,TI,TI,V4SF,V2SF,V2SF")])
movhps\t{%2, %0|%0, %2}"
[(set_attr "type" "sselog,ssemov,ssemov,ssemov,sselog,ssemov,ssemov")
(set_attr "prefix_extra" "1,*,*,*,*,*,*")
(set_attr "mode" "TI,TI,TI,TI,TI,V4SF,V2SF")])
(define_insn "*vec_concatv2di_rex64_sse"
[(set (match_operand:V2DI 0 "register_operand" "=Y2 ,Yi,!Y2,Y2,x,x,x")
[(set (match_operand:V2DI 0 "register_operand" "=Y2 ,Yi,!Y2,Y2,x,x")
(vec_concat:V2DI
(match_operand:DI 1 "nonimmediate_operand" " mY2,r ,*y ,0 ,0,0,m")
(match_operand:DI 2 "vector_move_operand" " C ,C ,C ,Y2,x,m,0")))]
(match_operand:DI 1 "nonimmediate_operand" " mY2,r ,*y ,0 ,0,0")
(match_operand:DI 2 "vector_move_operand" " C ,C ,C ,Y2,x,m")))]
"TARGET_64BIT && TARGET_SSE"
"@
movq\t{%1, %0|%0, %1}
......@@ -4998,10 +4996,9 @@
movq2dq\t{%1, %0|%0, %1}
punpcklqdq\t{%2, %0|%0, %2}
movlhps\t{%2, %0|%0, %2}
movhps\t{%2, %0|%0, %2}
movlps\t{%1, %0|%0, %1}"
[(set_attr "type" "ssemov,ssemov,ssemov,sselog,ssemov,ssemov,ssemov")
(set_attr "mode" "TI,TI,TI,TI,V4SF,V2SF,V2SF")])
movhps\t{%2, %0|%0, %2}"
[(set_attr "type" "ssemov,ssemov,ssemov,sselog,ssemov,ssemov")
(set_attr "mode" "TI,TI,TI,TI,V4SF,V2SF")])
(define_expand "vec_unpacku_hi_v16qi"
[(match_operand:V8HI 0 "register_operand" "")
......
gcc/testsuite/ChangeLog
2008-08-14 Uros Bizjak <ubizjak@gmail.com>
PR target/37101
* gcc.target/i386/pr37101.c: New test.
2008-08-14 Jakub Jelinek <jakub@redhat.com>
PR middle-end/37103
......@@ -126,7 +131,7 @@
loop.
Should be vectorizable on targets that support vector unpack.
* gcc.dg/vect/vect-widen-mult-u8.c,
gcc.dg/vect/wrapv-vect-reduc-dot-s8b.c,.
gcc.dg/vect/wrapv-vect-reduc-dot-s8b.c,
gcc.dg/vect/wrapv-vect-reduc-dot-s8b.c: Likewise.
* gcc.dg/vect/vect-35.c: Should be vectorizable on targets that
support vector pack. Avoid vectorization of the init loop.
......
gcc/testsuite/gcc.target/i386/pr37101.c 0 → 100644
/* { dg-do compile } */
/* { dg-options "-O2 -msse2 -ftree-vectorize -march=nocona" } */
typedef __SIZE_TYPE__ size_t;
extern void *malloc (size_t);
extern void free (void *);
typedef struct _Resource
{
struct _Resource *next;
unsigned int id;
} ResourceRec, *ResourcePtr;
typedef struct _ClientResource
{
ResourcePtr *resources;
int elements;
int buckets;
int hashsize;
} ClientResourceRec;
static ClientResourceRec clientTable[256];
void
RebuildTable (int client)
{
int j;
ResourcePtr res, next;
ResourcePtr **tails, *resources;
ResourcePtr **tptr, *rptr;
j = 2 * clientTable[client].buckets;
tails =
(ResourcePtr **) malloc ((unsigned long) (j * sizeof (ResourcePtr *)));
resources =
(ResourcePtr *) malloc ((unsigned long) (j * sizeof (ResourcePtr)));
for (rptr = resources, tptr = tails; --j >= 0; rptr++, tptr++)
{
*rptr = ((ResourcePtr) ((void *) 0));
*tptr = rptr;
}
clientTable[client].hashsize++;
for (j = clientTable[client].buckets,
rptr = clientTable[client].resources; --j >= 0; rptr++)
{
for (res = *rptr; res; res = next)
{
next = res->next;
res->next = ((ResourcePtr) ((void *) 0));
tptr = &tails[Hash (client, res->id)];
**tptr = res;
*tptr = &res->next;
}
}
free ((void *) tails);
clientTable[client].buckets *= 2;
free ((void *) clientTable[client].resources);
clientTable[client].resources = resources;
}
/* { dg-final { scan-assembler-not "movlps" } } */
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