Commit d2cd871f by Steve Ellcey Committed by Steve Ellcey

re PR target/46997 (new ia64 vector instructions are broken on HP-UX (big-endian))

	PR target/46997
	* ia64.c (ia64_expand_unpack): Fix code for TARGET_BIG_ENDIAN.
	(a64_expand_widen_sum): Ditto.
	* vect.md (mulv2si3): Disable for TARGET_BIG_ENDIAN.
	(vec_extract_evenodd_help): Ditto.
	(vec_extract_evenv4hi): Ditto.
	(vec_extract_oddv4hi): Ditto.
	(vec_extract_evenv2si): Ditto.
	(vec_extract_oddv2si): Ditto.
	(vec_extract_evenv2sf): Ditto.
	(vec_extract_oddv2sf): Ditto.
	(vec_pack_trunc_v4hi: Ditto.
	(vec_pack_trunc_v2si): Ditto.
	(vec_interleave_lowv8qi): Fix for TARGET_BIG_ENDIAN.
	(vec_interleave_highv8qi): Ditto.
	(mix1_r): Ditto.
	(vec_extract_oddv8qi): Ditto.
	(vec_interleave_lowv4hi): Ditto.
	(vec_interleave_highv4hi): Ditto.
	(vec_interleave_lowv2si): Ditto.
	(vec_interleave_highv2si): Ditto.

From-SVN: r168970
parent 41a1208a
2011-01-18 Steve Ellcey <sje@cup.hp.com>
PR target/46997
* ia64.c (ia64_expand_unpack): Fix code for TARGET_BIG_ENDIAN.
(a64_expand_widen_sum): Ditto.
* vect.md (mulv2si3): Disable for TARGET_BIG_ENDIAN.
(vec_extract_evenodd_help): Ditto.
(vec_extract_evenv4hi): Ditto.
(vec_extract_oddv4hi): Ditto.
(vec_extract_evenv2si): Ditto.
(vec_extract_oddv2si): Ditto.
(vec_extract_evenv2sf): Ditto.
(vec_extract_oddv2sf): Ditto.
(vec_pack_trunc_v4hi: Ditto.
(vec_pack_trunc_v2si): Ditto.
(vec_interleave_lowv8qi): Fix for TARGET_BIG_ENDIAN.
(vec_interleave_highv8qi): Ditto.
(mix1_r): Ditto.
(vec_extract_oddv8qi): Ditto.
(vec_interleave_lowv4hi): Ditto.
(vec_interleave_highv4hi): Ditto.
(vec_interleave_lowv2si): Ditto.
(vec_interleave_highv2si): Ditto.
2011-01-18 John David Anglin <dave.anglin@nrc-cnrc.gc.ca>
* doc/extend.texi: Mention __float128 support on hppa HP-UX.
......
......@@ -2007,7 +2007,10 @@ ia64_expand_unpack (rtx operands[3], bool unsignedp, bool highp)
gcc_assert (!neg);
}
emit_insn (gen (gen_lowpart (mode, operands[0]), operands[1], x));
if (TARGET_BIG_ENDIAN)
emit_insn (gen (gen_lowpart (mode, operands[0]), x, operands[1]));
else
emit_insn (gen (gen_lowpart (mode, operands[0]), operands[1], x));
}
/* Emit an integral vector widening sum operations. */
......@@ -2058,8 +2061,16 @@ ia64_expand_widen_sum (rtx operands[3], bool unsignedp)
h = gen_reg_rtx (wmode);
s = gen_reg_rtx (wmode);
emit_insn (unpack_l (gen_lowpart (mode, l), operands[1], x));
emit_insn (unpack_h (gen_lowpart (mode, h), operands[1], x));
if (TARGET_BIG_ENDIAN)
{
emit_insn (unpack_l (gen_lowpart (mode, l), x, operands[1]));
emit_insn (unpack_h (gen_lowpart (mode, h), x, operands[1]));
}
else
{
emit_insn (unpack_l (gen_lowpart (mode, l), operands[1], x));
emit_insn (unpack_h (gen_lowpart (mode, h), operands[1], x));
}
emit_insn (plus (s, l, operands[2]));
emit_insn (plus (operands[0], h, s));
}
......@@ -2082,7 +2093,10 @@ ia64_expand_widen_mul_v4hi (rtx operands[3], bool unsignedp, bool highp)
emit_insn (mulhigh (h, operands[1], operands[2], GEN_INT (16)));
interl = highp ? gen_vec_interleave_highv4hi : gen_vec_interleave_lowv4hi;
emit_insn (interl (gen_lowpart (V4HImode, operands[0]), l, h));
if (TARGET_BIG_ENDIAN)
emit_insn (interl (gen_lowpart (V4HImode, operands[0]), h, l));
else
emit_insn (interl (gen_lowpart (V4HImode, operands[0]), l, h));
}
/* Emit a signed or unsigned V8QI dot product operation. */
......@@ -2115,14 +2129,28 @@ ia64_expand_dot_prod_v8qi (rtx operands[4], bool unsignedp)
h1 = gen_reg_rtx (V4HImode);
h2 = gen_reg_rtx (V4HImode);
emit_insn (gen_vec_interleave_lowv8qi
(gen_lowpart (V8QImode, l1), operands[1], x1));
emit_insn (gen_vec_interleave_lowv8qi
(gen_lowpart (V8QImode, l2), operands[2], x2));
emit_insn (gen_vec_interleave_highv8qi
(gen_lowpart (V8QImode, h1), operands[1], x1));
emit_insn (gen_vec_interleave_highv8qi
(gen_lowpart (V8QImode, h2), operands[2], x2));
if (TARGET_BIG_ENDIAN)
{
emit_insn (gen_vec_interleave_lowv8qi
(gen_lowpart (V8QImode, l1), x1, operands[1]));
emit_insn (gen_vec_interleave_lowv8qi
(gen_lowpart (V8QImode, l2), x2, operands[2]));
emit_insn (gen_vec_interleave_highv8qi
(gen_lowpart (V8QImode, h1), x1, operands[1]));
emit_insn (gen_vec_interleave_highv8qi
(gen_lowpart (V8QImode, h2), x2, operands[2]));
}
else
{
emit_insn (gen_vec_interleave_lowv8qi
(gen_lowpart (V8QImode, l1), operands[1], x1));
emit_insn (gen_vec_interleave_lowv8qi
(gen_lowpart (V8QImode, l2), operands[2], x2));
emit_insn (gen_vec_interleave_highv8qi
(gen_lowpart (V8QImode, h1), operands[1], x1));
emit_insn (gen_vec_interleave_highv8qi
(gen_lowpart (V8QImode, h2), operands[2], x2));
}
p1 = gen_reg_rtx (V2SImode);
p2 = gen_reg_rtx (V2SImode);
......
......@@ -370,7 +370,7 @@
[(set (match_operand:V2SI 0 "gr_register_operand" "")
(mult:V2SI (match_operand:V2SI 1 "gr_register_operand" "r")
(match_operand:V2SI 2 "gr_register_operand" "r")))]
""
"!TARGET_BIG_ENDIAN"
{
rtx t0, t1, t2, t3, t4, t5, t6, t7, x;
rtx op1h = gen_lowpart (V4HImode, operands[1]);
......@@ -709,7 +709,13 @@
(const_int 2) (const_int 10)
(const_int 3) (const_int 11)])))]
""
"unpack1.l %0 = %r2, %r1"
{
/* Recall that vector elements are numbered in memory order. */
if (TARGET_BIG_ENDIAN)
return "%,unpack1.l %0 = %r1, %r2";
else
return "%,unpack1.l %0 = %r2, %r1";
}
[(set_attr "itanium_class" "mmshf")])
(define_insn "vec_interleave_highv8qi"
......@@ -723,7 +729,13 @@
(const_int 6) (const_int 14)
(const_int 7) (const_int 15)])))]
""
"unpack1.h %0 = %r2, %r1"
{
/* Recall that vector elements are numbered in memory order. */
if (TARGET_BIG_ENDIAN)
return "%,unpack1.h %0 = %r1, %r2";
else
return "%,unpack1.h %0 = %r2, %r1";
}
[(set_attr "itanium_class" "mmshf")])
(define_insn "mix1_r"
......@@ -857,7 +869,10 @@
""
{
rtx temp = gen_reg_rtx (V8QImode);
emit_insn (gen_mix1_r (temp, operands[1], operands[2]));
if (TARGET_BIG_ENDIAN)
emit_insn (gen_mix1_l (temp, operands[2], operands[1]));
else
emit_insn (gen_mix1_r (temp, operands[1], operands[2]));
emit_insn (gen_mux1_alt (operands[0], temp));
DONE;
})
......@@ -869,7 +884,10 @@
""
{
rtx temp = gen_reg_rtx (V8QImode);
emit_insn (gen_mix1_l (temp, operands[1], operands[2]));
if (TARGET_BIG_ENDIAN)
emit_insn (gen_mix1_r (temp, operands[2], operands[1]));
else
emit_insn (gen_mix1_l (temp, operands[1], operands[2]));
emit_insn (gen_mux1_alt (operands[0], temp));
DONE;
})
......@@ -885,7 +903,13 @@
(const_int 1)
(const_int 5)])))]
""
"unpack2.l %0 = %r2, %r1"
{
/* Recall that vector elements are numbered in memory order. */
if (TARGET_BIG_ENDIAN)
return "%,unpack2.l %0 = %r1, %r2";
else
return "%,unpack2.l %0 = %r2, %r1";
}
[(set_attr "itanium_class" "mmshf")])
(define_insn "vec_interleave_highv4hi"
......@@ -899,7 +923,13 @@
(const_int 3)
(const_int 7)])))]
""
"unpack2.h %0 = %r2, %r1"
{
/* Recall that vector elements are numbered in memory order. */
if (TARGET_BIG_ENDIAN)
return "%,unpack2.h %0 = %r1, %r2";
else
return "%,unpack2.h %0 = %r2, %r1";
}
[(set_attr "itanium_class" "mmshf")])
(define_insn "mix2_r"
......@@ -958,13 +988,13 @@
(const_int 2)
(const_int 1)
(const_int 3)])))]
"")
"!TARGET_BIG_ENDIAN")
(define_expand "vec_extract_evenv4hi"
[(match_operand:V4HI 0 "gr_register_operand")
(match_operand:V4HI 1 "gr_reg_or_0_operand")
(match_operand:V4HI 2 "gr_reg_or_0_operand")]
""
"!TARGET_BIG_ENDIAN"
{
rtx temp = gen_reg_rtx (V4HImode);
emit_insn (gen_mix2_r (temp, operands[1], operands[2]));
......@@ -976,7 +1006,7 @@
[(match_operand:V4HI 0 "gr_register_operand")
(match_operand:V4HI 1 "gr_reg_or_0_operand")
(match_operand:V4HI 2 "gr_reg_or_0_operand")]
""
"!TARGET_BIG_ENDIAN"
{
rtx temp = gen_reg_rtx (V4HImode);
emit_insn (gen_mix2_l (temp, operands[1], operands[2]));
......@@ -1002,7 +1032,13 @@
(parallel [(const_int 0)
(const_int 2)])))]
""
"unpack4.l %0 = %r2, %r1"
{
/* Recall that vector elements are numbered in memory order. */
if (TARGET_BIG_ENDIAN)
return "%,unpack4.h %0 = %r1, %r2";
else
return "%,unpack4.l %0 = %r2, %r1";
}
[(set_attr "itanium_class" "mmshf")])
;; Note that mix4.l performs the exact same operation.
......@@ -1015,14 +1051,20 @@
(parallel [(const_int 1)
(const_int 3)])))]
""
"unpack4.h %0 = %r2, %r1"
{
/* Recall that vector elements are numbered in memory order. */
if (TARGET_BIG_ENDIAN)
return "%,unpack4.l %0 = %r1, %r2";
else
return "%,unpack4.h %0 = %r2, %r1";
}
[(set_attr "itanium_class" "mmshf")])
(define_expand "vec_extract_evenv2si"
[(match_operand:V2SI 0 "gr_register_operand" "")
(match_operand:V2SI 1 "gr_register_operand" "")
(match_operand:V2SI 2 "gr_register_operand" "")]
""
"!TARGET_BIG_ENDIAN"
{
emit_insn (gen_vec_interleave_lowv2si (operands[0], operands[1],
operands[2]));
......@@ -1033,7 +1075,7 @@
[(match_operand:V2SI 0 "gr_register_operand" "")
(match_operand:V2SI 1 "gr_register_operand" "")
(match_operand:V2SI 2 "gr_register_operand" "")]
""
"!TARGET_BIG_ENDIAN"
{
emit_insn (gen_vec_interleave_highv2si (operands[0], operands[1],
operands[2]));
......@@ -1397,7 +1439,7 @@
[(match_operand:V2SF 0 "gr_register_operand" "")
(match_operand:V2SF 1 "gr_register_operand" "")
(match_operand:V2SF 2 "gr_register_operand" "")]
""
"!TARGET_BIG_ENDIAN"
{
emit_insn (gen_vec_interleave_lowv2sf (operands[0], operands[1],
operands[2]));
......@@ -1408,7 +1450,7 @@
[(match_operand:V2SF 0 "gr_register_operand" "")
(match_operand:V2SF 1 "gr_register_operand" "")
(match_operand:V2SF 2 "gr_register_operand" "")]
""
"!TARGET_BIG_ENDIAN"
{
emit_insn (gen_vec_interleave_highv2sf (operands[0], operands[1],
operands[2]));
......@@ -1540,7 +1582,7 @@
[(match_operand:V8QI 0 "gr_register_operand" "")
(match_operand:V4HI 1 "gr_register_operand" "")
(match_operand:V4HI 2 "gr_register_operand" "")]
""
"!TARGET_BIG_ENDIAN"
{
rtx op1 = gen_lowpart(V8QImode, operands[1]);
rtx op2 = gen_lowpart(V8QImode, operands[2]);
......@@ -1552,7 +1594,7 @@
[(match_operand:V4HI 0 "gr_register_operand" "")
(match_operand:V2SI 1 "gr_register_operand" "")
(match_operand:V2SI 2 "gr_register_operand" "")]
""
"!TARGET_BIG_ENDIAN"
{
rtx op1 = gen_lowpart(V4HImode, operands[1]);
rtx op2 = gen_lowpart(V4HImode, operands[2]);
......
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