Skip to content

R
riscv-gcc-1
Commit 962b9668 by Bill Schmidt Committed by William Schmidt
Options

[gcc] 

2017-11-06  Bill Schmidt  <wschmidt@linux.vnet.ibm.com>

	* config/rs6000/altivec.md (*p9_vadu<mode>3) Rename to
	p9_vadu<mode>3.
	(usadv16qi): New define_expand.
	(usadv8hi): New define_expand.

[gcc/testsuite]

2017-11-06  Bill Schmidt  <wschmidt@linux.vnet.ibm.com>

	* gcc.target/powerpc/sad-vectorize-1.c: New file.
	* gcc.target/powerpc/sad-vectorize-2.c: New file.
	* gcc.target/powerpc/sad-vectorize-3.c: New file.
	* gcc.target/powerpc/sad-vectorize-4.c: New file.

From-SVN: r254453
parent 8e7d1486
Showing with 244 additions and 1 deletions
gcc/ChangeLog
2017-11-06 Bill Schmidt <wschmidt@linux.vnet.ibm.com>
* config/rs6000/altivec.md (*p9_vadu<mode>3) Rename to
p9_vadu<mode>3.
(usadv16qi): New define_expand.
(usadv8hi): New define_expand.
2017-11-06 Jan Hubicka <hubicka@ucw.cz>
PR bootstrap/82832
gcc/config/rs6000/altivec.md
......@@ -4020,7 +4020,7 @@
"TARGET_P9_VECTOR")
;; Vector absolute difference unsigned
(define_insn "*p9_vadu<mode>3"
(define_insn "p9_vadu<mode>3"
[(set (match_operand:VI 0 "register_operand" "=v")
(unspec:VI [(match_operand:VI 1 "register_operand" "v")
(match_operand:VI 2 "register_operand" "v")]
......@@ -4184,6 +4184,49 @@
"vbpermd %0,%1,%2"
[(set_attr "type" "vecsimple")])
;; Support for SAD (sum of absolute differences).
;; Due to saturating semantics, we can't combine the sum-across
;; with the vector accumulate in vsum4ubs. A vadduwm is needed.
(define_expand "usadv16qi"
[(use (match_operand:V4SI 0 "register_operand"))
(use (match_operand:V16QI 1 "register_operand"))
(use (match_operand:V16QI 2 "register_operand"))
(use (match_operand:V4SI 3 "register_operand"))]
"TARGET_P9_VECTOR"
{
rtx absd = gen_reg_rtx (V16QImode);
rtx zero = gen_reg_rtx (V4SImode);
rtx psum = gen_reg_rtx (V4SImode);
emit_insn (gen_p9_vaduv16qi3 (absd, operands[1], operands[2]));
emit_insn (gen_altivec_vspltisw (zero, const0_rtx));
emit_insn (gen_altivec_vsum4ubs (psum, absd, zero));
emit_insn (gen_addv4si3 (operands[0], psum, operands[3]));
DONE;
})
;; Since vsum4shs is saturating and further performs signed
;; arithmetic, we can't combine the sum-across with the vector
;; accumulate in vsum4shs. A vadduwm is needed.
(define_expand "usadv8hi"
[(use (match_operand:V4SI 0 "register_operand"))
(use (match_operand:V8HI 1 "register_operand"))
(use (match_operand:V8HI 2 "register_operand"))
(use (match_operand:V4SI 3 "register_operand"))]
"TARGET_P9_VECTOR"
{
rtx absd = gen_reg_rtx (V8HImode);
rtx zero = gen_reg_rtx (V4SImode);
rtx psum = gen_reg_rtx (V4SImode);
emit_insn (gen_p9_vaduv8hi3 (absd, operands[1], operands[2]));
emit_insn (gen_altivec_vspltisw (zero, const0_rtx));
emit_insn (gen_altivec_vsum4shs (psum, absd, zero));
emit_insn (gen_addv4si3 (operands[0], psum, operands[3]));
DONE;
})
;; Decimal Integer operations
(define_int_iterator UNSPEC_BCD_ADD_SUB [UNSPEC_BCDADD UNSPEC_BCDSUB])
......
gcc/testsuite/ChangeLog
2017-11-06 Bill Schmidt <wschmidt@linux.vnet.ibm.com>
* gcc.target/powerpc/sad-vectorize-1.c: New file.
* gcc.target/powerpc/sad-vectorize-2.c: New file.
* gcc.target/powerpc/sad-vectorize-3.c: New file.
* gcc.target/powerpc/sad-vectorize-4.c: New file.
2017-11-06 Martin Liska <mliska@suse.cz>
* c-c++-common/cilk-plus/AN/pr57541-2.c (foo1): Return a value
......
gcc/testsuite/gcc.target/powerpc/sad-vectorize-1.c 0 → 100644
/* { dg-do compile { target { powerpc*-*-* } } } */
/* { dg-skip-if "do not override -mcpu" { powerpc*-*-* } { "-mcpu=*" } { "-mcpu=power9" } } */
/* { dg-require-effective-target powerpc_p9vector_ok } */
/* { dg-skip-if "" { powerpc*-*-aix* } } */
/* { dg-options "-O3 -mcpu=power9" } */
/* Verify that we vectorize this SAD loop using vabsdub. */
extern int abs (int __x) __attribute__ ((__nothrow__, __leaf__)) __attribute__ ((__const__));
static int
foo (unsigned char *w, int i, unsigned char *x, int j)
{
int tot = 0;
for (int a = 0; a < 16; a++)
{
for (int b = 0; b < 16; b++)
tot += abs (w[b] - x[b]);
w += i;
x += j;
}
return tot;
}
void
bar (unsigned char *w, unsigned char *x, int i, int *result)
{
*result = foo (w, 16, x, i);
}
/* { dg-final { scan-assembler-times "vabsdub" 16 } } */
/* { dg-final { scan-assembler-times "vsum4ubs" 16 } } */
/* { dg-final { scan-assembler-times "vadduwm" 17 } } */
/* Note: One of the 16 adds is optimized out (add with zero),
leaving 15. The extra two adds are for the final reduction. */
gcc/testsuite/gcc.target/powerpc/sad-vectorize-2.c 0 → 100644
/* { dg-do compile { target { powerpc*-*-* } } } */
/* { dg-skip-if "do not override -mcpu" { powerpc*-*-* } { "-mcpu=*" } { "-mcpu=power9" } } */
/* { dg-require-effective-target powerpc_p9vector_ok } */
/* { dg-skip-if "" { powerpc*-*-aix* } } */
/* { dg-options "-O3 -mcpu=power9" } */
/* Verify that we vectorize this SAD loop using vabsduh. */
extern int abs (int __x) __attribute__ ((__nothrow__, __leaf__)) __attribute__ ((__const__));
static int
foo (unsigned short *w, int i, unsigned short *x, int j)
{
int tot = 0;
for (int a = 0; a < 16; a++)
{
for (int b = 0; b < 8; b++)
tot += abs (w[b] - x[b]);
w += i;
x += j;
}
return tot;
}
void
bar (unsigned short *w, unsigned short *x, int i, int *result)
{
*result = foo (w, 8, x, i);
}
/* { dg-final { scan-assembler-times "vabsduh" 16 } } */
/* { dg-final { scan-assembler-times "vsum4shs" 16 } } */
/* { dg-final { scan-assembler-times "vadduwm" 17 } } */
/* Note: One of the 16 adds is optimized out (add with zero),
leaving 15. The extra two adds are for the final reduction. */
gcc/testsuite/gcc.target/powerpc/sad-vectorize-3.c 0 → 100644
/* { dg-do run { target { powerpc*-*-linux* && { lp64 && p9vector_hw } } } } */
/* { dg-require-effective-target powerpc_p9vector_ok } */
/* { dg-options "-O3 -mcpu=power9" } */
/* { dg-skip-if "do not override -mcpu" { powerpc*-*-* } { "-mcpu=*" } { "-mcpu=power9" } } */
/* Verify that we get correct code when we vectorize this SAD loop using
vabsdub. */
extern void abort ();
extern int abs (int __x) __attribute__ ((__nothrow__, __leaf__)) __attribute__ ((__const__));
static int
foo (unsigned char *w, int i, unsigned char *x, int j)
{
int tot = 0;
for (int a = 0; a < 16; a++)
{
for (int b = 0; b < 16; b++)
tot += abs (w[b] - x[b]);
w += i;
x += j;
}
return tot;
}
void
bar (unsigned char *w, unsigned char *x, int i, int *result)
{
*result = foo (w, 16, x, i);
}
int
main ()
{
unsigned char m[256];
unsigned char n[256];
int sum, i;
for (i = 0; i < 256; ++i)
if (i % 2 == 0)
{
m[i] = (i % 8) * 2 + 1;
n[i] = -(i % 8);
}
else
{
m[i] = -((i % 8) * 2 + 2);
n[i] = -((i % 8) >> 1);
}
bar (m, n, 16, &sum);
if (sum != 32384)
abort ();
return 0;
}
gcc/testsuite/gcc.target/powerpc/sad-vectorize-4.c 0 → 100644
/* { dg-do run { target { powerpc*-*-linux* && { lp64 && p9vector_hw } } } } */
/* { dg-require-effective-target powerpc_p9vector_ok } */
/* { dg-options "-O3 -mcpu=power9" } */
/* { dg-skip-if "do not override -mcpu" { powerpc*-*-* } { "-mcpu=*" } { "-mcpu=power9" } } */
/* Verify that we get correct code when we vectorize this SAD loop using
vabsduh. */
extern void abort ();
extern int abs (int __x) __attribute__ ((__nothrow__, __leaf__)) __attribute__ ((__const__));
static int
foo (unsigned short *w, int i, unsigned short *x, int j)
{
int tot = 0;
for (int a = 0; a < 16; a++)
{
for (int b = 0; b < 8; b++)
tot += abs (w[b] - x[b]);
w += i;
x += j;
}
return tot;
}
void
bar (unsigned short *w, unsigned short *x, int i, int *result)
{
*result = foo (w, 8, x, i);
}
int
main ()
{
unsigned short m[128];
unsigned short n[128];
int sum, i;
for (i = 0; i < 128; ++i)
if (i % 2 == 0)
{
m[i] = (i % 8) * 2 + 1;
n[i] = i % 8;
}
else
{
m[i] = (i % 8) * 4 - 3;
n[i] = (i % 8) >> 1;
}
bar (m, n, 8, &sum);
if (sum != 992)
abort ();
return 0;
}
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