This is the mail archive of the
gcc-patches@gcc.gnu.org
mailing list for the GCC project.
[PATCH, i386]: Back port Fix PR 52908 - xop-mul-1:f9 miscompiled on bulldozer (-mxop) to 4.7
- From: <venkataramanan dot kumar at amd dot com>
- To: <gcc-patches at gcc dot gnu dot org>
- Cc: <ubizjak at gmail dot com>, <venkataramanan dot kumar at amd dot com>
- Date: Thu, 7 Jun 2012 06:07:18 -0500
- Subject: [PATCH, i386]: Back port Fix PR 52908 - xop-mul-1:f9 miscompiled on bulldozer (-mxop) to 4.7
Hi Maintainers,
Please find the patch below that backports PR target/52908 to GCC 4.7.
The patch passed bootstrap and regression test.
Ok to commit?
regards,
Venkat.
Index: ChangeLog
===================================================================
--- ChangeLog (revision 187449)
+++ ChangeLog (working copy)
@@ -1,3 +1,17 @@
+2012-06-07 Venkataramanan Kumar <venkataramanan.kumar@amd.com>
+
+ Backport from 2012-05-09 mainline r187354
+
+ PR target/52908
+ * config/i386/sse.md (vec_widen_smult_hi_v4si): Expand using
+ xop_pmacsdqh insn pattern instead of xop_mulv2div2di3_high.
+ (vec_widen_smult_lo_v4si): Expand using xop_pmacsdql insn pattern
+ instead of xop_mulv2div2di3_low.
+ (xop_p<macs>dql): Fix vec_select selector.
+ (xop_p<macs>dqh): Ditto.
+ (xop_mulv2div2di3_low): Remove insn_and_split pattern.
+ (xop_mulv2div2di3_high): Ditto.
+
2012-05-13 Uros Bizjak <ubizjak@gmail.com>
Backport from mainline
Index: testsuite/gcc.target/i386/xop-imul32widen-vector.c
===================================================================
--- testsuite/gcc.target/i386/xop-imul32widen-vector.c (revision 187449)
+++ testsuite/gcc.target/i386/xop-imul32widen-vector.c (working copy)
@@ -32,5 +32,5 @@
exit (0);
}
-/* { dg-final { scan-assembler "vpmacsdql" } } */
+/* { dg-final { scan-assembler "vpmuldq" } } */
/* { dg-final { scan-assembler "vpmacsdqh" } } */
Index: testsuite/ChangeLog
===================================================================
--- testsuite/ChangeLog (revision 187449)
+++ testsuite/ChangeLog (working copy)
@@ -1,3 +1,11 @@
+2012-06-07 Venkataramanan Kumar <venkataramanan.kumar@amd.com>
+
+ Back port from 2012-05-09 mainline r187354
+
+ PR target/52908
+ * gcc.target/i386/xop-imul32widen-vector.c: Update scan-assembler
+ directive to Scan for vpmuldq, not vpmacsdql.
+
2012-05-12 Eric Botcazou <ebotcazou@adacore.com>
* gnat.dg/null_pointer_deref3.adb: New test.
Index: config/i386/sse.md
===================================================================
--- config/i386/sse.md (revision 187449)
+++ config/i386/sse.md (working copy)
@@ -5743,11 +5743,15 @@
if (TARGET_XOP)
{
+ rtx t3 = gen_reg_rtx (V2DImode);
+
emit_insn (gen_sse2_pshufd_1 (t1, op1, GEN_INT (0), GEN_INT (2),
GEN_INT (1), GEN_INT (3)));
emit_insn (gen_sse2_pshufd_1 (t2, op2, GEN_INT (0), GEN_INT (2),
GEN_INT (1), GEN_INT (3)));
- emit_insn (gen_xop_mulv2div2di3_high (operands[0], t1, t2));
+ emit_move_insn (t3, CONST0_RTX (V2DImode));
+
+ emit_insn (gen_xop_pmacsdqh (operands[0], t1, t2, t3));
DONE;
}
@@ -5772,11 +5776,15 @@
if (TARGET_XOP)
{
+ rtx t3 = gen_reg_rtx (V2DImode);
+
emit_insn (gen_sse2_pshufd_1 (t1, op1, GEN_INT (0), GEN_INT (2),
GEN_INT (1), GEN_INT (3)));
emit_insn (gen_sse2_pshufd_1 (t2, op2, GEN_INT (0), GEN_INT (2),
GEN_INT (1), GEN_INT (3)));
- emit_insn (gen_xop_mulv2div2di3_low (operands[0], t1, t2));
+ emit_move_insn (t3, CONST0_RTX (V2DImode));
+
+ emit_insn (gen_xop_pmacsdql (operands[0], t1, t2, t3));
DONE;
}
@@ -10443,12 +10451,12 @@
(sign_extend:V2DI
(vec_select:V2SI
(match_operand:V4SI 1 "nonimmediate_operand" "%x")
- (parallel [(const_int 1)
- (const_int 3)])))
- (vec_select:V2SI
+ (parallel [(const_int 0)
+ (const_int 2)])))
+ (vec_select:V2SI
(match_operand:V4SI 2 "nonimmediate_operand" "xm")
- (parallel [(const_int 1)
- (const_int 3)])))
+ (parallel [(const_int 0)
+ (const_int 2)])))
(match_operand:V2DI 3 "nonimmediate_operand" "x")))]
"TARGET_XOP"
"vpmacssdql\t{%3, %2, %1, %0|%0, %1, %2, %3}"
@@ -10462,13 +10470,13 @@
(sign_extend:V2DI
(vec_select:V2SI
(match_operand:V4SI 1 "nonimmediate_operand" "%x")
- (parallel [(const_int 0)
- (const_int 2)])))
+ (parallel [(const_int 1)
+ (const_int 3)])))
(sign_extend:V2DI
(vec_select:V2SI
(match_operand:V4SI 2 "nonimmediate_operand" "xm")
- (parallel [(const_int 0)
- (const_int 2)]))))
+ (parallel [(const_int 1)
+ (const_int 3)]))))
(match_operand:V2DI 3 "nonimmediate_operand" "x")))]
"TARGET_XOP"
"vpmacssdqh\t{%3, %2, %1, %0|%0, %1, %2, %3}"
@@ -10482,61 +10490,19 @@
(sign_extend:V2DI
(vec_select:V2SI
(match_operand:V4SI 1 "nonimmediate_operand" "%x")
- (parallel [(const_int 1)
- (const_int 3)])))
+ (parallel [(const_int 0)
+ (const_int 2)])))
(sign_extend:V2DI
(vec_select:V2SI
(match_operand:V4SI 2 "nonimmediate_operand" "xm")
- (parallel [(const_int 1)
- (const_int 3)]))))
+ (parallel [(const_int 0)
+ (const_int 2)]))))
(match_operand:V2DI 3 "nonimmediate_operand" "x")))]
"TARGET_XOP"
"vpmacsdql\t{%3, %2, %1, %0|%0, %1, %2, %3}"
[(set_attr "type" "ssemuladd")
(set_attr "mode" "TI")])
-;; We don't have a straight 32-bit parallel multiply and extend on XOP, so
-;; fake it with a multiply/add. In general, we expect the define_split to
-;; occur before register allocation, so we have to handle the corner case where
-;; the target is the same as operands 1/2
-(define_insn_and_split "xop_mulv2div2di3_low"
- [(set (match_operand:V2DI 0 "register_operand" "=&x")
- (mult:V2DI
- (sign_extend:V2DI
- (vec_select:V2SI
- (match_operand:V4SI 1 "register_operand" "%x")
- (parallel [(const_int 1)
- (const_int 3)])))
- (sign_extend:V2DI
- (vec_select:V2SI
- (match_operand:V4SI 2 "nonimmediate_operand" "xm")
- (parallel [(const_int 1)
- (const_int 3)])))))]
- "TARGET_XOP"
- "#"
- "&& reload_completed"
- [(set (match_dup 0)
- (match_dup 3))
- (set (match_dup 0)
- (plus:V2DI
- (mult:V2DI
- (sign_extend:V2DI
- (vec_select:V2SI
- (match_dup 1)
- (parallel [(const_int 1)
- (const_int 3)])))
- (sign_extend:V2DI
- (vec_select:V2SI
- (match_dup 2)
- (parallel [(const_int 1)
- (const_int 3)]))))
- (match_dup 0)))]
-{
- operands[3] = CONST0_RTX (V2DImode);
-}
- [(set_attr "type" "ssemul")
- (set_attr "mode" "TI")])
-
(define_insn "xop_pmacsdqh"
[(set (match_operand:V2DI 0 "register_operand" "=x")
(plus:V2DI
@@ -10544,61 +10510,19 @@
(sign_extend:V2DI
(vec_select:V2SI
(match_operand:V4SI 1 "nonimmediate_operand" "%x")
- (parallel [(const_int 0)
- (const_int 2)])))
+ (parallel [(const_int 1)
+ (const_int 3)])))
(sign_extend:V2DI
(vec_select:V2SI
(match_operand:V4SI 2 "nonimmediate_operand" "xm")
- (parallel [(const_int 0)
- (const_int 2)]))))
+ (parallel [(const_int 1)
+ (const_int 3)]))))
(match_operand:V2DI 3 "nonimmediate_operand" "x")))]
"TARGET_XOP"
"vpmacsdqh\t{%3, %2, %1, %0|%0, %1, %2, %3}"
[(set_attr "type" "ssemuladd")
(set_attr "mode" "TI")])
-;; We don't have a straight 32-bit parallel multiply and extend on XOP, so
-;; fake it with a multiply/add. In general, we expect the define_split to
-;; occur before register allocation, so we have to handle the corner case where
-;; the target is the same as either operands[1] or operands[2]
-(define_insn_and_split "xop_mulv2div2di3_high"
- [(set (match_operand:V2DI 0 "register_operand" "=&x")
- (mult:V2DI
- (sign_extend:V2DI
- (vec_select:V2SI
- (match_operand:V4SI 1 "register_operand" "%x")
- (parallel [(const_int 0)
- (const_int 2)])))
- (sign_extend:V2DI
- (vec_select:V2SI
- (match_operand:V4SI 2 "nonimmediate_operand" "xm")
- (parallel [(const_int 0)
- (const_int 2)])))))]
- "TARGET_XOP"
- "#"
- "&& reload_completed"
- [(set (match_dup 0)
- (match_dup 3))
- (set (match_dup 0)
- (plus:V2DI
- (mult:V2DI
- (sign_extend:V2DI
- (vec_select:V2SI
- (match_dup 1)
- (parallel [(const_int 0)
- (const_int 2)])))
- (sign_extend:V2DI
- (vec_select:V2SI
- (match_dup 2)
- (parallel [(const_int 0)
- (const_int 2)]))))
- (match_dup 0)))]
-{
- operands[3] = CONST0_RTX (V2DImode);
-}
- [(set_attr "type" "ssemul")
- (set_attr "mode" "TI")])
-
;; XOP parallel integer multiply/add instructions for the intrinisics
(define_insn "xop_pmacsswd"
[(set (match_operand:V4SI 0 "register_operand" "=x")