Commit 8345965a by Alan Modra Committed by Alan Modra

rs6000.c (vspltis_constant): Correct for little-endian.

gcc/
	* config/rs6000/rs6000.c (vspltis_constant): Correct for little-endian.
	(gen_easy_altivec_constant): Likewise.
	* config/rs6000/predicates.md (easy_vector_constant_add_self,
	easy_vector_constant_msb): Likewise.
gcc/testsuite/
	* gcc.target/powerpc/altivec-consts.c: Correct for little-endian.
	Add scan-assembler-not "lvx".
	* gcc.target/powerpc/le-altivec-consts.c: New.

From-SVN: r200357
parent dab76671
2013-06-24 Alan Modra <amodra@gmail.com>
* config/rs6000/rs6000.c (vspltis_constant): Correct for little-endian.
(gen_easy_altivec_constant): Likewise.
* config/rs6000/predicates.md (easy_vector_constant_add_self,
easy_vector_constant_msb): Likewise.
2013-06-23 Jakub Jelinek <jakub@redhat.com> 2013-06-23 Jakub Jelinek <jakub@redhat.com>
PR target/57688 PR target/57688
......
...@@ -527,9 +527,11 @@ ...@@ -527,9 +527,11 @@
(match_test "easy_altivec_constant (op, mode)"))) (match_test "easy_altivec_constant (op, mode)")))
{ {
HOST_WIDE_INT val; HOST_WIDE_INT val;
int elt;
if (mode == V2DImode || mode == V2DFmode) if (mode == V2DImode || mode == V2DFmode)
return 0; return 0;
val = const_vector_elt_as_int (op, GET_MODE_NUNITS (mode) - 1); elt = BYTES_BIG_ENDIAN ? GET_MODE_NUNITS (mode) - 1 : 0;
val = const_vector_elt_as_int (op, elt);
val = ((val & 0xff) ^ 0x80) - 0x80; val = ((val & 0xff) ^ 0x80) - 0x80;
return EASY_VECTOR_15_ADD_SELF (val); return EASY_VECTOR_15_ADD_SELF (val);
}) })
...@@ -541,9 +543,11 @@ ...@@ -541,9 +543,11 @@
(match_test "easy_altivec_constant (op, mode)"))) (match_test "easy_altivec_constant (op, mode)")))
{ {
HOST_WIDE_INT val; HOST_WIDE_INT val;
int elt;
if (mode == V2DImode || mode == V2DFmode) if (mode == V2DImode || mode == V2DFmode)
return 0; return 0;
val = const_vector_elt_as_int (op, GET_MODE_NUNITS (mode) - 1); elt = BYTES_BIG_ENDIAN ? GET_MODE_NUNITS (mode) - 1 : 0;
val = const_vector_elt_as_int (op, elt);
return EASY_VECTOR_MSB (val, GET_MODE_INNER (mode)); return EASY_VECTOR_MSB (val, GET_MODE_INNER (mode));
}) })
......
...@@ -4657,7 +4657,7 @@ vspltis_constant (rtx op, unsigned step, unsigned copies) ...@@ -4657,7 +4657,7 @@ vspltis_constant (rtx op, unsigned step, unsigned copies)
bitsize = GET_MODE_BITSIZE (inner); bitsize = GET_MODE_BITSIZE (inner);
mask = GET_MODE_MASK (inner); mask = GET_MODE_MASK (inner);
val = const_vector_elt_as_int (op, nunits - 1); val = const_vector_elt_as_int (op, BYTES_BIG_ENDIAN ? nunits - 1 : 0);
splat_val = val; splat_val = val;
msb_val = val > 0 ? 0 : -1; msb_val = val > 0 ? 0 : -1;
...@@ -4697,7 +4697,7 @@ vspltis_constant (rtx op, unsigned step, unsigned copies) ...@@ -4697,7 +4697,7 @@ vspltis_constant (rtx op, unsigned step, unsigned copies)
for (i = 0; i < nunits - 1; ++i) for (i = 0; i < nunits - 1; ++i)
{ {
HOST_WIDE_INT desired_val; HOST_WIDE_INT desired_val;
if (((i + 1) & (step - 1)) == 0) if (((BYTES_BIG_ENDIAN ? i + 1 : i) & (step - 1)) == 0)
desired_val = val; desired_val = val;
else else
desired_val = msb_val; desired_val = msb_val;
...@@ -4782,13 +4782,13 @@ gen_easy_altivec_constant (rtx op) ...@@ -4782,13 +4782,13 @@ gen_easy_altivec_constant (rtx op)
{ {
enum machine_mode mode = GET_MODE (op); enum machine_mode mode = GET_MODE (op);
int nunits = GET_MODE_NUNITS (mode); int nunits = GET_MODE_NUNITS (mode);
rtx last = CONST_VECTOR_ELT (op, nunits - 1); rtx val = CONST_VECTOR_ELT (op, BYTES_BIG_ENDIAN ? nunits - 1 : 0);
unsigned step = nunits / 4; unsigned step = nunits / 4;
unsigned copies = 1; unsigned copies = 1;
/* Start with a vspltisw. */ /* Start with a vspltisw. */
if (vspltis_constant (op, step, copies)) if (vspltis_constant (op, step, copies))
return gen_rtx_VEC_DUPLICATE (V4SImode, gen_lowpart (SImode, last)); return gen_rtx_VEC_DUPLICATE (V4SImode, gen_lowpart (SImode, val));
/* Then try with a vspltish. */ /* Then try with a vspltish. */
if (step == 1) if (step == 1)
...@@ -4797,7 +4797,7 @@ gen_easy_altivec_constant (rtx op) ...@@ -4797,7 +4797,7 @@ gen_easy_altivec_constant (rtx op)
step >>= 1; step >>= 1;
if (vspltis_constant (op, step, copies)) if (vspltis_constant (op, step, copies))
return gen_rtx_VEC_DUPLICATE (V8HImode, gen_lowpart (HImode, last)); return gen_rtx_VEC_DUPLICATE (V8HImode, gen_lowpart (HImode, val));
/* And finally a vspltisb. */ /* And finally a vspltisb. */
if (step == 1) if (step == 1)
...@@ -4806,7 +4806,7 @@ gen_easy_altivec_constant (rtx op) ...@@ -4806,7 +4806,7 @@ gen_easy_altivec_constant (rtx op)
step >>= 1; step >>= 1;
if (vspltis_constant (op, step, copies)) if (vspltis_constant (op, step, copies))
return gen_rtx_VEC_DUPLICATE (V16QImode, gen_lowpart (QImode, last)); return gen_rtx_VEC_DUPLICATE (V16QImode, gen_lowpart (QImode, val));
gcc_unreachable (); gcc_unreachable ();
} }
......
2013-06-24 Alan Modra <amodra@gmail.com>
* gcc.target/powerpc/altivec-consts.c: Correct for little-endian.
Add scan-assembler-not "lvx".
* gcc.target/powerpc/le-altivec-consts.c: New.
2013-06-23 Paolo Carlini <paolo.carlini@oracle.com> 2013-06-23 Paolo Carlini <paolo.carlini@oracle.com>
* g++.dg/cpp0x/sfinae47.C: New. * g++.dg/cpp0x/sfinae47.C: New.
......
...@@ -11,31 +11,24 @@ typedef __attribute__ ((vector_size (16))) unsigned char v16qi; ...@@ -11,31 +11,24 @@ typedef __attribute__ ((vector_size (16))) unsigned char v16qi;
typedef __attribute__ ((vector_size (16))) unsigned short v8hi; typedef __attribute__ ((vector_size (16))) unsigned short v8hi;
typedef __attribute__ ((vector_size (16))) unsigned int v4si; typedef __attribute__ ((vector_size (16))) unsigned int v4si;
char w[16] __attribute__((aligned(16))); typedef __attribute__((aligned(16))) char c16[16];
typedef __attribute__((aligned(16))) short s8[8];
typedef __attribute__((aligned(16))) int i4[4];
#define V16QI(V1,V2,V3,V4,V5,V6,V7,V8,V9,V10,V11,V12,V13,V14,V15,V16) \
v16qi v = {V1,V2,V3,V4,V5,V6,V7,V8,V9,V10,V11,V12,V13,V14,V15,V16}; \
static c16 w = {V1,V2,V3,V4,V5,V6,V7,V8,V9,V10,V11,V12,V13,V14,V15,V16}; \
check_v16qi (v, w);
/* Emulate the vspltis? instructions on a 16-byte array of chars. */ #define V8HI(V1,V2,V3,V4,V5,V6,V7,V8) \
v8hi v = {V1,V2,V3,V4,V5,V6,V7,V8}; \
void vspltisb (char *v, int val) static s8 w = {V1,V2,V3,V4,V5,V6,V7,V8}; \
{ check_v8hi (v, w);
int i;
for (i = 0; i < 16; i++)
v[i] = val;
}
void vspltish (char *v, int val)
{
int i;
for (i = 0; i < 16; i += 2)
v[i] = val >> 7, v[i + 1] = val;
}
void vspltisw (char *v, int val) #define V4SI(V1,V2,V3,V4) \
{ v4si v = {V1,V2,V3,V4}; \
int i; static i4 w = {V1,V2,V3,V4}; \
for (i = 0; i < 16; i += 4) check_v4si (v, w);
v[i] = v[i + 1] = v[i + 2] = val >> 7, v[i + 3] = val;
}
/* Use three different check functions for each mode-instruction pair. /* Use three different check functions for each mode-instruction pair.
...@@ -48,13 +41,13 @@ void __attribute__ ((noinline)) check_v16qi (v16qi v1, char *v2) ...@@ -48,13 +41,13 @@ void __attribute__ ((noinline)) check_v16qi (v16qi v1, char *v2)
abort (); abort ();
} }
void __attribute__ ((noinline)) check_v8hi (v8hi v1, char *v2) void __attribute__ ((noinline)) check_v8hi (v8hi v1, short *v2)
{ {
if (memcmp (&v1, v2, 16)) if (memcmp (&v1, v2, 16))
abort (); abort ();
} }
void __attribute__ ((noinline)) check_v4si (v4si v1, char *v2) void __attribute__ ((noinline)) check_v4si (v4si v1, int *v2)
{ {
if (memcmp (&v1, v2, 16)) if (memcmp (&v1, v2, 16))
abort (); abort ();
...@@ -65,72 +58,52 @@ void __attribute__ ((noinline)) check_v4si (v4si v1, char *v2) ...@@ -65,72 +58,52 @@ void __attribute__ ((noinline)) check_v4si (v4si v1, char *v2)
void v16qi_vspltisb () void v16qi_vspltisb ()
{ {
v16qi v = { 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15 }; V16QI (15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15);
vspltisb (w, 15);
check_v16qi (v, w);
} }
void v16qi_vspltisb_neg () void v16qi_vspltisb_neg ()
{ {
v16qi v = { -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5 }; V16QI (-5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5);
vspltisb (w, -5);
check_v16qi (v, w);
} }
void v16qi_vspltisb_addself () void v16qi_vspltisb_addself ()
{ {
v16qi v = { 30, 30, 30, 30, 30, 30, 30, 30, 30, 30, 30, 30, 30, 30, 30, 30 }; V16QI (30, 30, 30, 30, 30, 30, 30, 30, 30, 30, 30, 30, 30, 30, 30, 30);
vspltisb (w, 30);
check_v16qi (v, w);
} }
void v16qi_vspltisb_neg_addself () void v16qi_vspltisb_neg_addself ()
{ {
v16qi v = { -24, -24, -24, -24, -24, -24, -24, -24, -24, -24, -24, -24, -24, -24, -24, -24 }; V16QI (-24, -24, -24, -24, -24, -24, -24, -24, -24, -24, -24, -24, -24, -24, -24, -24);
vspltisb (w, -24);
check_v16qi (v, w);
} }
void v16qi_vspltish () void v16qi_vspltish ()
{ {
v16qi v = { 0, 15, 0, 15, 0, 15, 0, 15, 0, 15, 0, 15, 0, 15, 0, 15 }; V16QI (0, 15, 0, 15, 0, 15, 0, 15, 0, 15, 0, 15, 0, 15, 0, 15);
vspltish (w, 15);
check_v16qi (v, w);
} }
void v16qi_vspltish_addself () void v16qi_vspltish_addself ()
{ {
v16qi v = { 0, 30, 0, 30, 0, 30, 0, 30, 0, 30, 0, 30, 0, 30, 0, 30 }; V16QI (0, 30, 0, 30, 0, 30, 0, 30, 0, 30, 0, 30, 0, 30, 0, 30);
vspltish (w, 30);
check_v16qi (v, w);
} }
void v16qi_vspltish_neg () void v16qi_vspltish_neg ()
{ {
v16qi v = { -1, -5, -1, -5, -1, -5, -1, -5, -1, -5, -1, -5, -1, -5, -1, -5 }; V16QI (-1, -5, -1, -5, -1, -5, -1, -5, -1, -5, -1, -5, -1, -5, -1, -5);
vspltish (w, -5);
check_v16qi (v, w);
} }
void v16qi_vspltisw () void v16qi_vspltisw ()
{ {
v16qi v = { 0, 0, 0, 15, 0, 0, 0, 15, 0, 0, 0, 15, 0, 0, 0, 15 }; V16QI (0, 0, 0, 15, 0, 0, 0, 15, 0, 0, 0, 15, 0, 0, 0, 15);
vspltisw (w, 15);
check_v16qi (v, w);
} }
void v16qi_vspltisw_addself () void v16qi_vspltisw_addself ()
{ {
v16qi v = { 0, 0, 0, 30, 0, 0, 0, 30, 0, 0, 0, 30, 0, 0, 0, 30 }; V16QI (0, 0, 0, 30, 0, 0, 0, 30, 0, 0, 0, 30, 0, 0, 0, 30);
vspltisw (w, 30);
check_v16qi (v, w);
} }
void v16qi_vspltisw_neg () void v16qi_vspltisw_neg ()
{ {
v16qi v = { -1, -1, -1, -5, -1, -1, -1, -5, -1, -1, -1, -5, -1, -1, -1, -5 }; V16QI (-1, -1, -1, -5, -1, -1, -1, -5, -1, -1, -1, -5, -1, -1, -1, -5);
vspltisw (w, -5);
check_v16qi (v, w);
} }
...@@ -138,144 +111,104 @@ void v16qi_vspltisw_neg () ...@@ -138,144 +111,104 @@ void v16qi_vspltisw_neg ()
void v8hi_vspltisb () void v8hi_vspltisb ()
{ {
v8hi v = { 0x0F0F, 0x0F0F, 0x0F0F, 0x0F0F, 0x0F0F, 0x0F0F, 0x0F0F, 0x0F0F }; V8HI (0x0F0F, 0x0F0F, 0x0F0F, 0x0F0F, 0x0F0F, 0x0F0F, 0x0F0F, 0x0F0F);
vspltisb (w, 15);
check_v8hi (v, w);
} }
void v8hi_vspltisb_addself () void v8hi_vspltisb_addself ()
{ {
v8hi v = { 0x1E1E, 0x1E1E, 0x1E1E, 0x1E1E, 0x1E1E, 0x1E1E, 0x1E1E, 0x1E1E }; V8HI (0x1E1E, 0x1E1E, 0x1E1E, 0x1E1E, 0x1E1E, 0x1E1E, 0x1E1E, 0x1E1E);
vspltisb (w, 30);
check_v8hi (v, w);
} }
void v8hi_vspltisb_neg () void v8hi_vspltisb_neg ()
{ {
v8hi v = { 0xFBFB, 0xFBFB, 0xFBFB, 0xFBFB, 0xFBFB, 0xFBFB, 0xFBFB, 0xFBFB }; V8HI (0xFBFB, 0xFBFB, 0xFBFB, 0xFBFB, 0xFBFB, 0xFBFB, 0xFBFB, 0xFBFB);
vspltisb (w, -5);
check_v8hi (v, w);
} }
void v8hi_vspltish () void v8hi_vspltish ()
{ {
v8hi v = { 15, 15, 15, 15, 15, 15, 15, 15 }; V8HI (15, 15, 15, 15, 15, 15, 15, 15);
vspltish (w, 15);
check_v8hi (v, w);
} }
void v8hi_vspltish_neg () void v8hi_vspltish_neg ()
{ {
v8hi v = { -5, -5, -5, -5, -5, -5, -5, -5 }; V8HI (-5, -5, -5, -5, -5, -5, -5, -5);
vspltish (w, -5);
check_v8hi (v, w);
} }
void v8hi_vspltish_addself () void v8hi_vspltish_addself ()
{ {
v8hi v = { 30, 30, 30, 30, 30, 30, 30, 30 }; V8HI (30, 30, 30, 30, 30, 30, 30, 30);
vspltish (w, 30);
check_v8hi (v, w);
} }
void v8hi_vspltish_neg_addself () void v8hi_vspltish_neg_addself ()
{ {
v8hi v = { -24, -24, -24, -24, -24, -24, -24, -24 }; V8HI (-24, -24, -24, -24, -24, -24, -24, -24);
vspltish (w, -24);
check_v8hi (v, w);
} }
void v8hi_vspltisw () void v8hi_vspltisw ()
{ {
v8hi v = { 0, 15, 0, 15, 0, 15, 0, 15 }; V8HI (0, 15, 0, 15, 0, 15, 0, 15);
vspltisw (w, 15);
check_v8hi (v, w);
} }
void v8hi_vspltisw_addself () void v8hi_vspltisw_addself ()
{ {
v8hi v = { 0, 30, 0, 30, 0, 30, 0, 30 }; V8HI (0, 30, 0, 30, 0, 30, 0, 30);
vspltisw (w, 30);
check_v8hi (v, w);
} }
void v8hi_vspltisw_neg () void v8hi_vspltisw_neg ()
{ {
v8hi v = { -1, -5, -1, -5, -1, -5, -1, -5 }; V8HI (-1, -5, -1, -5, -1, -5, -1, -5);
vspltisw (w, -5);
check_v8hi (v, w);
} }
/* V4SI tests. */ /* V4SI tests. */
void v4si_vspltisb () void v4si_vspltisb ()
{ {
v4si v = { 0x0F0F0F0F, 0x0F0F0F0F, 0x0F0F0F0F, 0x0F0F0F0F }; V4SI (0x0F0F0F0F, 0x0F0F0F0F, 0x0F0F0F0F, 0x0F0F0F0F);
vspltisb (w, 15);
check_v4si (v, w);
} }
void v4si_vspltisb_addself () void v4si_vspltisb_addself ()
{ {
v4si v = { 0x1E1E1E1E, 0x1E1E1E1E, 0x1E1E1E1E, 0x1E1E1E1E }; V4SI (0x1E1E1E1E, 0x1E1E1E1E, 0x1E1E1E1E, 0x1E1E1E1E);
vspltisb (w, 30);
check_v4si (v, w);
} }
void v4si_vspltisb_neg () void v4si_vspltisb_neg ()
{ {
v4si v = { 0xFBFBFBFB, 0xFBFBFBFB, 0xFBFBFBFB, 0xFBFBFBFB }; V4SI (0xFBFBFBFB, 0xFBFBFBFB, 0xFBFBFBFB, 0xFBFBFBFB);
vspltisb (w, -5);
check_v4si (v, w);
} }
void v4si_vspltish () void v4si_vspltish ()
{ {
v4si v = { 0x000F000F, 0x000F000F, 0x000F000F, 0x000F000F }; V4SI (0x000F000F, 0x000F000F, 0x000F000F, 0x000F000F);
vspltish (w, 15);
check_v4si (v, w);
} }
void v4si_vspltish_addself () void v4si_vspltish_addself ()
{ {
v4si v = { 0x001E001E, 0x001E001E, 0x001E001E, 0x001E001E }; V4SI (0x001E001E, 0x001E001E, 0x001E001E, 0x001E001E);
vspltish (w, 30);
check_v4si (v, w);
} }
void v4si_vspltish_neg () void v4si_vspltish_neg ()
{ {
v4si v = { 0xFFFBFFFB, 0xFFFBFFFB, 0xFFFBFFFB, 0xFFFBFFFB }; V4SI (0xFFFBFFFB, 0xFFFBFFFB, 0xFFFBFFFB, 0xFFFBFFFB);
vspltish (w, -5);
check_v4si (v, w);
} }
void v4si_vspltisw () void v4si_vspltisw ()
{ {
v4si v = { 15, 15, 15, 15 }; V4SI (15, 15, 15, 15);
vspltisw (w, 15);
check_v4si (v, w);
} }
void v4si_vspltisw_neg () void v4si_vspltisw_neg ()
{ {
v4si v = { -5, -5, -5, -5 }; V4SI (-5, -5, -5, -5);
vspltisw (w, -5);
check_v4si (v, w);
} }
void v4si_vspltisw_addself () void v4si_vspltisw_addself ()
{ {
v4si v = { 30, 30, 30, 30 }; V4SI (30, 30, 30, 30);
vspltisw (w, 30);
check_v4si (v, w);
} }
void v4si_vspltisw_neg_addself () void v4si_vspltisw_neg_addself ()
{ {
v4si v = { -24, -24, -24, -24 }; V4SI (-24, -24, -24, -24);
vspltisw (w, -24);
check_v4si (v, w);
} }
...@@ -316,3 +249,5 @@ int main () ...@@ -316,3 +249,5 @@ int main ()
v4si_vspltisw_neg_addself (); v4si_vspltisw_neg_addself ();
return 0; return 0;
} }
/* { dg-final { scan-assembler-not "lvx" { target { ! powerpc*le-*-* } } } } */
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