diff mbox

[rs6000] Add builtin-support for new Power9 vslv and vsrv (vector shift left and right variable) instructions

Message ID 5748A79D.9050000@linux.vnet.ibm.com
State New
Headers show

Commit Message

Kelvin Nilsen May 27, 2016, 8:01 p.m. UTC
This patch adds built-in function support for the Power9 vslv and vsrv
instructions.

I have bootstrapped and tested this patch against the trunk on
powerpc64le-unkonwn-linux-gnu with no regressions.  Is this ok for the
trunk?

I have not yet tested against the gcc-6 branch as this patch depends on
infrastructure that has not yet been backported to gcc-6.  Once the
necessary infrastructure is available, is this ok for backporting to
gcc6 following bootstrap and regression testing?

Thanks,
Kelvin


gcc/ChangeLog:

2016-05-27  Kelvin Nilsen  <kelvin@gcc.gnu.org>

	* config/rs6000/altivec.h (vec_slv): New macro.
	(vec_srv): New macro.
	* config/rs6000/altivec.md (UNSPEC_VSLV): New value.
	(UNSPEC_VSRV): New value.
	(vslv): New insn.
	(vsrv): New insn.
	* config/rs6000/rs6000-builtin.def (vslv): New builtin definition.
	(vsrv): New builtin definition.
	* config/rs6000/rs6000-c.c (P9V_BUILTIN_VSLV): Macro expansion to
	define argument types for new builtin.
	(P9V_BUILTIN_VSRV): Macro expansion to define argument types for
	new builtin.
	* doc/extend.texi: Document the new vec_vslv and vec_srv built-in
	functions. 

gcc/testsuite/ChangeLog:

2016-05-27  Kelvin Nilsen  <kelvin@gcc.gnu.org>

	* gcc.target/powerpc/vslv-0.c: New test.
	* gcc.target/powerpc/vslv-1.c: New test.
	* gcc.target/powerpc/vsrv-0.c: New test.
	* gcc.target/powerpc/vsrv-1.c: New test.

Comments

Segher Boessenkool May 30, 2016, 4:05 p.m. UTC | #1
On Fri, May 27, 2016 at 02:01:33PM -0600, Kelvin Nilsen wrote:
> 
> This patch adds built-in function support for the Power9 vslv and vsrv
> instructions.


> +Tne @code{vec_slv} and @code{vec_srv} functions operate in parallel on

Typo ("Tne").

> +all of the bytes of their @code{src} and @code{shift_distance}
> +arguments in parallel.  The behavior of the @code{vec_slv} is as if

You also say "in parallel" twice here.

> --- gcc/testsuite/gcc.target/powerpc/vslv-0.c	(revision 0)
> +++ gcc/testsuite/gcc.target/powerpc/vslv-0.c	(working copy)
> @@ -0,0 +1,14 @@
> +/* { dg-do compile { target { powerpc*-*-* } } } */
> +/* { dg-options "-mcpu=power9" } */

I think you need to prevent the user from overriding -mcpu= for these
tests?  There are many examples of this in gcc.target/powerpc/ .

Okay for trunk with those things taken care of; okay for 6 later, too.

Thanks,


Segher
diff mbox

Patch

Index: gcc/config/rs6000/altivec.h
===================================================================
--- gcc/config/rs6000/altivec.h	(revision 236796)
+++ gcc/config/rs6000/altivec.h	(working copy)
@@ -400,6 +400,9 @@ 
 #ifdef _ARCH_PPC64
 #define vec_vprtybq __builtin_vec_vprtybq
 #endif
+
+#define vec_slv __builtin_vec_vslv
+#define vec_srv __builtin_vec_vsrv
 #endif
 
 /* Predicates.
Index: gcc/config/rs6000/altivec.md
===================================================================
--- gcc/config/rs6000/altivec.md	(revision 236796)
+++ gcc/config/rs6000/altivec.md	(working copy)
@@ -114,6 +114,8 @@ 
    UNSPEC_STVLXL
    UNSPEC_STVRX
    UNSPEC_STVRXL
+   UNSPEC_VSLV
+   UNSPEC_VSRV
    UNSPEC_VMULWHUB
    UNSPEC_VMULWLUB
    UNSPEC_VMULWHSB
@@ -1631,6 +1633,24 @@ 
   "vslo %0,%1,%2"
   [(set_attr "type" "vecperm")])
 
+(define_insn "vslv"
+  [(set (match_operand:V16QI 0 "register_operand" "=v")
+	(unspec:V16QI [(match_operand:V16QI 1 "register_operand" "v")
+		       (match_operand:V16QI 2 "register_operand" "v")]
+         UNSPEC_VSLV))]
+  "TARGET_P9_VECTOR"
+  "vslv %0,%1,%2"
+  [(set_attr "type" "vecsimple")])
+
+(define_insn "vsrv"
+  [(set (match_operand:V16QI 0 "register_operand" "=v")
+	(unspec:V16QI [(match_operand:V16QI 1 "register_operand" "v")
+		       (match_operand:V16QI 2 "register_operand" "v")]
+         UNSPEC_VSRV))]
+  "TARGET_P9_VECTOR"
+  "vsrv %0,%1,%2"
+  [(set_attr "type" "vecsimple")])
+
 (define_insn "*altivec_vsl<VI_char>"
   [(set (match_operand:VI2 0 "register_operand" "=v")
         (ashift:VI2 (match_operand:VI2 1 "register_operand" "v")
Index: gcc/config/rs6000/rs6000-builtin.def
===================================================================
--- gcc/config/rs6000/rs6000-builtin.def	(revision 236796)
+++ gcc/config/rs6000/rs6000-builtin.def	(working copy)
@@ -1749,6 +1749,14 @@  BU_P8V_OVERLOAD_3 (VADDEUQM,	"vaddeuqm")
 BU_P8V_OVERLOAD_3 (VSUBECUQ,	"vsubecuq")
 BU_P8V_OVERLOAD_3 (VSUBEUQM,	"vsubeuqm")
 
+/* ISA 3.0 vector overloaded 2-argument functions. */
+BU_P9V_AV_2 (VSLV,		"vslv",			CONST, vslv)
+BU_P9V_AV_2 (VSRV,		"vsrv",			CONST, vsrv)
+
+/* ISA 3.0 vector overloaded 2-argument functions. */
+BU_P9V_OVERLOAD_2 (VSLV,	"vslv")
+BU_P9V_OVERLOAD_2 (VSRV,	"vsrv")
+
 
 /* 2 argument extended divide functions added in ISA 2.06.  */
 BU_P7_MISC_2 (DIVWE,		"divwe",	CONST,	dive_si)
Index: gcc/config/rs6000/rs6000-c.c
===================================================================
--- gcc/config/rs6000/rs6000-c.c	(revision 236796)
+++ gcc/config/rs6000/rs6000-c.c	(working copy)
@@ -4488,6 +4488,13 @@  const struct altivec_builtin_types altivec_overloa
   { P8V_BUILTIN_VEC_VGBBD, P8V_BUILTIN_VGBBD,
     RS6000_BTI_unsigned_V16QI, 0, 0, 0 },
 
+  { P9V_BUILTIN_VEC_VSLV, P9V_BUILTIN_VSLV,
+    RS6000_BTI_unsigned_V16QI, RS6000_BTI_unsigned_V16QI,
+    RS6000_BTI_unsigned_V16QI, 0 },
+  { P9V_BUILTIN_VEC_VSRV, P9V_BUILTIN_VSRV,
+    RS6000_BTI_unsigned_V16QI, RS6000_BTI_unsigned_V16QI,
+    RS6000_BTI_unsigned_V16QI, 0 },
+
   /* Crypto builtins.  */
   { CRYPTO_BUILTIN_VPERMXOR, CRYPTO_BUILTIN_VPERMXOR_V16QI,
     RS6000_BTI_unsigned_V16QI, RS6000_BTI_unsigned_V16QI,
Index: gcc/doc/extend.texi
===================================================================
--- gcc/doc/extend.texi	(revision 236796)
+++ gcc/doc/extend.texi	(working copy)
@@ -14686,8 +14686,8 @@  The @code{__builtin_divde}, @code{__builtin_divdeo
 64-bit environment support ISA 2.06 or later.
 
 The following built-in functions are available for the PowerPC family
-of processors, starting with ISA 3.0 or later (@option{-mcpu=power9}
-or @option{-mmodulo}):
+of processors, starting with ISA 3.0 or later (@option{-mcpu=power9})
+or with @option{-mmodulo}:
 @smallexample
 long long __builtin_darn (void);
 long long __builtin_darn_raw (void);
@@ -17341,6 +17341,40 @@  vector __int128_t vec_vprtybq (vector __int128_t);
 vector __uint128_t vec_vprtybd (vector __uint128_t);
 @end smallexample
 
+The following built-in vector functions are available for the PowerPC family
+of processors, starting with ISA 3.0 or later (@option{-mcpu=power9})
+or with @option{-mpower9-vector}:
+@smallexample
+__vector unsigned char
+vec_slv (__vector unsigned char src, __vector unsigned char shift_distance);
+__vector unsigned char
+vec_srv (__vector unsigned char src, __vector unsigned char shift_distance);
+@end smallexample
+
+Tne @code{vec_slv} and @code{vec_srv} functions operate in parallel on
+all of the bytes of their @code{src} and @code{shift_distance}
+arguments in parallel.  The behavior of the @code{vec_slv} is as if
+there existed a temporary array of 17 unsigned characters
+@code{slv_array} within which elements 0 through 15 are the same as
+the entries in the @code{src} array and element 16 equals 0.  The
+result returned from the @code{vec_slv} function is a
+@code{__vector} of 16 unsigned characters within which element
+@code{i} is computed using the C expression
+@code{0xff & (*((unsigned short *)(slv_array + i)) << (0x07 &
+shift_distance[i]))},
+with this resulting value coerced to the @code{unsigned char} type.
+The behavior of the @code{vec_srv} is as if
+there existed a temporary array of 17 unsigned characters
+@code{srv_array} within which element 0 equals zero and
+elements 1 through 16 equal the elements 0 through 15 of
+the @code{src} array.  The
+result returned from the @code{vec_srv} function is a
+@code{__vector} of 16 unsigned characters within which element
+@code{i} is computed using the C expression
+@code{0xff & (*((unsigned short *)(srv_array + i)) >>
+(0x07 & shift_distance[i]))},
+with this resulting value coerced to the @code{unsigned char} type.
+
 If the cryptographic instructions are enabled (@option{-mcrypto} or
 @option{-mcpu=power8}), the following builtins are enabled.
 
Index: gcc/testsuite/gcc.target/powerpc/vslv-0.c
===================================================================
--- gcc/testsuite/gcc.target/powerpc/vslv-0.c	(revision 0)
+++ gcc/testsuite/gcc.target/powerpc/vslv-0.c	(working copy)
@@ -0,0 +1,14 @@ 
+/* { dg-do compile { target { powerpc*-*-* } } } */
+/* { dg-options "-mcpu=power9" } */
+
+#include <altivec.h>
+
+__vector unsigned char
+doCharShiftLeft (__vector unsigned char *p, __vector unsigned char *q)
+{
+  __vector unsigned char result, input, shift_distance;
+  result = __builtin_vec_vslv (input, shift_distance);
+  return result;
+}
+
+/* { dg-final { scan-assembler "vslv" } } */
Index: gcc/testsuite/gcc.target/powerpc/vslv-1.c
===================================================================
--- gcc/testsuite/gcc.target/powerpc/vslv-1.c	(revision 0)
+++ gcc/testsuite/gcc.target/powerpc/vslv-1.c	(working copy)
@@ -0,0 +1,14 @@ 
+/* { dg-do compile { target { powerpc*-*-* } } } */
+/* { dg-options "-mcpu=power9" } */
+
+#include <altivec.h>
+
+__vector unsigned char
+doCharShiftLeft (__vector unsigned char *p, __vector unsigned char *q)
+{
+  __vector unsigned char result, input, shift_distance;
+  result = vec_slv (input, shift_distance);
+  return result;
+}
+
+/* { dg-final { scan-assembler "vslv" } } */
Index: gcc/testsuite/gcc.target/powerpc/vsrv-0.c
===================================================================
--- gcc/testsuite/gcc.target/powerpc/vsrv-0.c	(revision 0)
+++ gcc/testsuite/gcc.target/powerpc/vsrv-0.c	(working copy)
@@ -0,0 +1,14 @@ 
+/* { dg-do compile { target { powerpc*-*-* } } } */
+/* { dg-options "-mcpu=power9" } */
+
+#include <altivec.h>
+
+__vector unsigned char
+doCharShiftLeft (__vector unsigned char *p, __vector unsigned char *q)
+{
+  __vector unsigned char result, input, shift_distance;
+  result = __builtin_vec_vsrv (input, shift_distance);
+  return result;
+}
+
+/* { dg-final { scan-assembler "vsrv" } } */
Index: gcc/testsuite/gcc.target/powerpc/vsrv-1.c
===================================================================
--- gcc/testsuite/gcc.target/powerpc/vsrv-1.c	(revision 0)
+++ gcc/testsuite/gcc.target/powerpc/vsrv-1.c	(working copy)
@@ -0,0 +1,14 @@ 
+/* { dg-do compile { target { powerpc*-*-* } } } */
+/* { dg-options "-mcpu=power9" } */
+
+#include <altivec.h>
+
+__vector unsigned char
+doCharShiftLeft (__vector unsigned char *p, __vector unsigned char *q)
+{
+  __vector unsigned char result, input, shift_distance;
+  result = vec_srv (input, shift_distance);
+  return result;
+}
+
+/* { dg-final { scan-assembler "vsrv" } } */