===================================================================
@@ -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 +4184,51 @@
"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])
===================================================================
@@ -0,0 +1,36 @@
+/* { 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. */
===================================================================
@@ -0,0 +1,36 @@
+/* { 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. */
===================================================================
@@ -0,0 +1,57 @@
+/* { 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;
+}
===================================================================
@@ -0,0 +1,57 @@
+/* { 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;
+}