@@ -2575,6 +2575,8 @@ BU_P9_OVERLOAD_2 (CMPEQB, "byte_in_set")
/* Future architecture scalar built-ins. */
BU_FUTURE_MISC_2 (CFUGED, "cfuged", CONST, cfuged)
+BU_FUTURE_MISC_2 (CNTLZDM, "cntlzdm", CONST, cntlzdm)
+BU_FUTURE_MISC_2 (CNTTZDM, "cnttzdm", CONST, cnttzdm)
/* Future architecture vector built-ins. */
BU_FUTURE_V_2 (VCFUGED, "vcfuged", CONST, vcfuged)
@@ -149,6 +149,8 @@ (define_c_enum "unspec"
UNSPEC_PLTSEQ
UNSPEC_PLT16_HA
UNSPEC_CFUGED
+ UNSPEC_CNTLZDM
+ UNSPEC_CNTTZDM
])
;;
@@ -2463,6 +2465,24 @@ (define_insn "cfuged"
"cfuged %0,%1,%2"
[(set_attr "type" "integer")])
+(define_insn "cntlzdm"
+ [(set (match_operand:DI 0 "gpc_reg_operand" "=r")
+ (unspec:DI [(match_operand:DI 1 "gpc_reg_operand" "r")
+ (match_operand:DI 2 "gpc_reg_operand" "r")]
+ UNSPEC_CNTLZDM))]
+ "TARGET_FUTURE && TARGET_64BIT"
+ "cntlzdm %0,%1,%2"
+ [(set_attr "type" "integer")])
+
+(define_insn "cnttzdm"
+ [(set (match_operand:DI 0 "gpc_reg_operand" "=r")
+ (unspec:DI [(match_operand:DI 1 "gpc_reg_operand" "r")
+ (match_operand:DI 2 "gpc_reg_operand" "r")]
+ UNSPEC_CNTTZDM))]
+ "TARGET_FUTURE && TARGET_64BIT"
+ "cnttzdm %0,%1,%2"
+ [(set_attr "type" "integer")])
+
(define_insn "cmpb<mode>3"
[(set (match_operand:GPR 0 "gpc_reg_operand" "=r")
(unspec:GPR [(match_operand:GPR 1 "gpc_reg_operand" "r")
@@ -17556,6 +17556,22 @@ Perform a 64-bit centrifuge operation, as if implemented by the Future
@code{cfuged} instruction.
@findex __builtin_cfuged
+@smallexample
+@exdent unsigned long long int
+@exdent __builtin_cntlzdm (unsigned long long int, unsigned long long int)
+@end smallexample
+Perform a 64-bit count leading zeros operation under mask, as if
+implemented by the future @code{cntlzdm} instruction.
+@findex __builtin_cntlzdm
+
+@smallexample
+@exdent unsigned long long int
+@exdent __builtin_cnttzdm (unsigned long long int, unsigned long long int)
+@end smallexample
+Perform a 64-bit count trailing zeros operation under mask, as if
+implemented by the future @code{cnttzdm} instruction.
+@findex __builtin_cnttzdm
+
@node PowerPC AltiVec/VSX Built-in Functions
@subsection PowerPC AltiVec/VSX Built-in Functions
new file mode 100644
@@ -0,0 +1,57 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-options "-mdejagnu-cpu=future" } */
+
+extern void abort (void);
+
+unsigned long long int
+do_cntlzdm (unsigned long long int source, unsigned long long int mask)
+{
+ return __builtin_cntlzdm (source, mask);
+}
+
+int main (int argc, char *argv [])
+{
+ unsigned long long int sources [4], masks [4];
+ unsigned long long int intermediates [4][4] = {
+ /* sources[0] with each of masks [0 .. 3] */
+ { 0x0000a5f0ll, 0x00007e3cll, 0x000050ecll, 0x0000af73ll },
+ /* sources[1] with each of masks [0 .. 3] */
+ { 0x00007e3cll, 0x0000a5f0ll, 0x0000ec50ll, 0x000073afll },
+ /* sources[2] with each of masks [0 .. 3] */
+ { 0x00003ca5ll, 0x0000f07ell, 0x0000c50ell, 0x00003af7ll },
+ /* sources[3] with each of masks [0 .. 3] */
+ { 0x00005a0fll, 0x0000e7c3ll, 0x0000af73ll, 0x000050ecll },
+ };
+ unsigned long long int results [4][4] = {
+ { 0, 1, 1, 0 },
+ { 1, 0, 0, 1 },
+ { 2, 0, 0, 2 },
+ { 1, 0, 0, 1 },
+ };
+
+ sources[0] = 0xa5f07e3cll;
+ sources[1] = 0x7e3ca5f0ll;
+ sources[2] = 0x3ca5f07ell;
+ sources[3] = 0x5a0fe7c3ll;
+
+ masks[0] = 0xffff0000ll;
+ masks[1] = 0x0000ffffll;
+ masks[2] = 0x0f0f0f0fll;
+ masks[3] = 0xf0f0f0f0ll;
+
+ unsigned long long int result;
+
+ for (int i = 0; i < 4; i++)
+ {
+ for (int j = 0; j < 4; j++)
+ {
+ if (do_cntlzdm (sources[i], masks[j]) != results [i][j])
+ abort ();
+ }
+ }
+
+ return 0;
+}
+
+/* { dg-final { scan-assembler {\mcntlzdm\M} } } */
new file mode 100644
@@ -0,0 +1,56 @@
+/* { dg-do run } */
+/* { dg-require-effective-target powerpc_future_hw } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-options "-mdejagnu-cpu=future" } */
+
+extern void abort (void);
+
+unsigned long long int
+do_cntlzdm (unsigned long long int source, unsigned long long int mask)
+{
+ return __builtin_cntlzdm (source, mask);
+}
+
+int main (int argc, char *argv [])
+{
+ unsigned long long int sources [4], masks [4];
+ unsigned long long int intermediates [4][4] = {
+ /* sources[0] with each of masks [0 .. 3] */
+ { 0x0000a5f0ll, 0x00007e3cll, 0x000050ecll, 0x0000af73ll },
+ /* sources[1] with each of masks [0 .. 3] */
+ { 0x00007e3cll, 0x0000a5f0ll, 0x0000ec50ll, 0x000073afll },
+ /* sources[2] with each of masks [0 .. 3] */
+ { 0x00003ca5ll, 0x0000f07ell, 0x0000c50ell, 0x00003af7ll },
+ /* sources[3] with each of masks [0 .. 3] */
+ { 0x00005a0fll, 0x0000e7c3ll, 0x0000af73ll, 0x000050ecll },
+ };
+ unsigned long long int results [4][4] = {
+ { 0, 1, 1, 0 },
+ { 1, 0, 0, 1 },
+ { 2, 0, 0, 2 },
+ { 1, 0, 0, 1 },
+ };
+
+ sources[0] = 0xa5f07e3cll;
+ sources[1] = 0x7e3ca5f0ll;
+ sources[2] = 0x3ca5f07ell;
+ sources[3] = 0x5a0fe7c3ll;
+
+ masks[0] = 0xffff0000ll;
+ masks[1] = 0x0000ffffll;
+ masks[2] = 0x0f0f0f0fll;
+ masks[3] = 0xf0f0f0f0ll;
+
+ unsigned long long int result;
+
+ for (int i = 0; i < 4; i++)
+ {
+ for (int j = 0; j < 4; j++)
+ {
+ if (do_cntlzdm (sources[i], masks[j]) != results [i][j])
+ abort ();
+ }
+ }
+
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,53 @@
+/* { dg-do compile } */
+/* { dg-options "-mdejagnu-cpu=future" } */
+
+extern void abort (void);
+
+unsigned long long int
+do_cnttzdm (unsigned long long int source, unsigned long long int mask) {
+ return __builtin_cnttzdm (source, mask);
+}
+
+int main (int argc, char *argv [])
+{
+ unsigned long long int sources [4], masks [4];
+ unsigned long long int intermediates [4][4] = {
+ /* sources[0] with each of masks [0 .. 3] */
+ { 0x0000a5f0ll, 0x00007e3cll, 0x000050ecll, 0x0000af73ll },
+ /* sources[1] with each of masks [0 .. 3] */
+ { 0x00007e3cll, 0x0000a5f0ll, 0x0000ec50ll, 0x000073afll },
+ /* sources[2] with each of masks [0 .. 3] */
+ { 0x00003ca5ll, 0x0000f07ell, 0x0000c50ell, 0x00003af7ll },
+ /* sources[3] with each of masks [0 .. 3] */
+ { 0x00005a0fll, 0x0000e7c3ll, 0x0000af73ll, 0x000050ecll },
+ };
+ unsigned long long int results [4][4] = {
+ { 4, 2, 2, 0 },
+ { 2, 4, 4, 0 },
+ { 0, 1, 1, 0 },
+ { 0, 0, 0, 2 },
+ };
+
+ sources[0] = 0xa5f07e3cll;
+ sources[1] = 0x7e3ca5f0ll;
+ sources[2] = 0x3ca5f07ell;
+ sources[3] = 0x5a0fe7c3ll;
+
+ masks[0] = 0xffff0000ll;
+ masks[1] = 0x0000ffffll;
+ masks[2] = 0x0f0f0f0fll;
+ masks[3] = 0xf0f0f0f0ll;
+
+ for (int i = 0; i < 4; i++)
+ {
+ for (int j = 0; j < 4; j++)
+ {
+ if (do_cnttzdm (sources[i], masks[j]) != results [i][j])
+ abort ();
+ }
+ }
+
+ return 0;
+}
+
+/* { dg-final { scan-assembler {\mcnttzdm\M} } } */
new file mode 100644
@@ -0,0 +1,53 @@
+/* { dg-do run } */
+/* { dg-require-effective-target powerpc_future_hw } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-options "-mdejagnu-cpu=future" } */
+
+extern void abort (void);
+
+unsigned long long int
+do_cnttzdm (unsigned long long int source, unsigned long long int mask) {
+ return __builtin_cnttzdm (source, mask);
+}
+
+int main (int argc, char *argv [])
+{
+ unsigned long long int sources [4], masks [4];
+ unsigned long long int intermediates [4][4] = {
+ /* sources[0] with each of masks [0 .. 3] */
+ { 0x0000a5f0ll, 0x00007e3cll, 0x000050ecll, 0x0000af73ll },
+ /* sources[1] with each of masks [0 .. 3] */
+ { 0x00007e3cll, 0x0000a5f0ll, 0x0000ec50ll, 0x000073afll },
+ /* sources[2] with each of masks [0 .. 3] */
+ { 0x00003ca5ll, 0x0000f07ell, 0x0000c50ell, 0x00003af7ll },
+ /* sources[3] with each of masks [0 .. 3] */
+ { 0x00005a0fll, 0x0000e7c3ll, 0x0000af73ll, 0x000050ecll },
+ };
+ unsigned long long int results [4][4] = {
+ { 4, 2, 2, 0 },
+ { 2, 4, 4, 0 },
+ { 0, 1, 1, 0 },
+ { 0, 0, 0, 2 },
+ };
+
+ sources[0] = 0xa5f07e3cll;
+ sources[1] = 0x7e3ca5f0ll;
+ sources[2] = 0x3ca5f07ell;
+ sources[3] = 0x5a0fe7c3ll;
+
+ masks[0] = 0xffff0000ll;
+ masks[1] = 0x0000ffffll;
+ masks[2] = 0x0f0f0f0fll;
+ masks[3] = 0xf0f0f0f0ll;
+
+ for (int i = 0; i < 4; i++)
+ {
+ for (int j = 0; j < 4; j++)
+ {
+ if (do_cnttzdm (sources[i], masks[j]) != results [i][j])
+ abort ();
+ }
+ }
+
+ return 0;
+}
From: Kelvin Nilsen <kelvin@gcc.gnu.org> Add support for new scalar instructions for counting leading or trailing zeros under control of a bitmask. Bootstrapped and tested on powerpc64le-unknown-linux-gnu with no regressions. Is this okay for master? Thanks, Bill [gcc] 2020-05-08 Kelvin Nilsen <kelvin@gcc.gnu.org> * config/rs6000/rs6000-builtin.def (__builtin_cntlzdm): New built-in function definition. (__builtin_cnttzdm): Likewise., * config/rs6000/rs6000.md (UNSPEC_CNTLZDM): New constant. (UNSPEC_CNTTZDM): Likewise. (cntlzdm): New insn. (cnttzdm): Likewise. * doc/extend.texi (Basic PowerPC Built-in Functions available for a Future Architecture): Add descriptions of __builtin_cntlzdm and __builtin_cnttzdm functions. [gcc/testsuite] 2020-05-08 Kelvin Nilsen <kelvin@gcc.gnu.org> * gcc.target/powerpc/cntlzdm-0.c: New test. * gcc.target/powerpc/cntlzdm-1.c: New test. * gcc.target/powerpc/cnttzdm-0.c: New test. * gcc.target/powerpc/cnttzdm-1.c: New test. --- gcc/config/rs6000/rs6000-builtin.def | 2 + gcc/config/rs6000/rs6000.md | 20 +++++++ gcc/doc/extend.texi | 16 ++++++ gcc/testsuite/gcc.target/powerpc/cntlzdm-0.c | 57 ++++++++++++++++++++ gcc/testsuite/gcc.target/powerpc/cntlzdm-1.c | 56 +++++++++++++++++++ gcc/testsuite/gcc.target/powerpc/cnttzdm-0.c | 53 ++++++++++++++++++ gcc/testsuite/gcc.target/powerpc/cnttzdm-1.c | 53 ++++++++++++++++++ 7 files changed, 257 insertions(+) create mode 100644 gcc/testsuite/gcc.target/powerpc/cntlzdm-0.c create mode 100644 gcc/testsuite/gcc.target/powerpc/cntlzdm-1.c create mode 100644 gcc/testsuite/gcc.target/powerpc/cnttzdm-0.c create mode 100644 gcc/testsuite/gcc.target/powerpc/cnttzdm-1.c