GCC Maintainers:
This patch adds support for the various vec_bperm(), vec_mule() and
vec_mulo and vec_sldw() builtins.
The patch has been tested on powerpc64le-unknown-linux-gnu (Power 8 LE)
with no regressions.
Is the patch OK for gcc mainline?
Carl Love
--------------------------------------------------------------
gcc/ChangeLog:
2017-05-15 Carl Love <c...@us.ibm.com>
* config/rs6000/rs6000-c: Add support for built-in functions
vector unsigned long long vec_bperm (vector unsigned long long,
vector unsigned char)
vector signed long long vec_mule (vector signed int,
vector signed int)
vector unsigned long long vec_mule (vector unsigned int,
vector unsigned int)
vector signed long long vec_mulo (vector signed int,
vector signed int)
vector unsigned long long vec_mulo (vector unsigned int,
vector unsigned int)
vector signed char vec_sldw (vector signed char,
vector signed char,
const int)
vector unsigned char vec_sldw (vector unsigned char,
vector unsigned char,
const int)
vector signed short vec_sldw (vector signed short,
vector signed short,
const int)
vector unsigned short vec_sldw (vector unsigned short,
vector unsigned short,
const int)
vector signed int vec_sldw (vector signed int,
vector signed int,
const int)
vector unsigned int vec_sldw (vector unsigned int,
vector unsigned int,
const int)
vector signed long long vec_sldw (vector signed long long,
vector signed long long,
const int)
vector unsigned long long vec_sldw (vector unsigned long long,
vector unsigned long long,
const int)
* config/rs6000/rs6000-c: Add support for built-in functions
* config/rs6000/rs6000-builtin.def: Add definition for SLDW.
* config/rs6000/altivec.h: Add defintion for vec_sldw.
* doc/extend.texi: Update the built-in documentation for the
new built-in functions.
gcc/testsuite/ChangeLog:
2017-05-15 Carl Love <c...@us.ibm.com>
* gcc.target/powerpc/builtins-3.c: New vec_mule, vec_mulo test cases.
* gcc.target/powerpc/builtins-3-p8.c: Add tests for the new Power 8
built-ins to the test suite file. Note, support for mradds exists
but no test case exists.
* gcc.target/powerpc/builtins-3-p9.c: Add tests for the new Power 9
built-ins to the test suite file.
---
gcc/config/rs6000/altivec.h | 1 +
gcc/config/rs6000/rs6000-builtin.def | 1 +
gcc/config/rs6000/rs6000-c.c | 37 ++++++++++
gcc/doc/extend.texi | 32 ++++++++
gcc/testsuite/gcc.target/powerpc/builtins-3-p8.c | 37 +++-------
gcc/testsuite/gcc.target/powerpc/builtins-3-p9.c | 31 +++++++-
gcc/testsuite/gcc.target/powerpc/builtins-3.c | 93 +++++++++++++++++++++++-
7 files changed, 204 insertions(+), 28 deletions(-)
diff --git a/gcc/config/rs6000/altivec.h b/gcc/config/rs6000/altivec.h
index c334d9f..c92bcce 100644
--- a/gcc/config/rs6000/altivec.h
+++ b/gcc/config/rs6000/altivec.h
@@ -247,6 +247,7 @@
#define vec_sel __builtin_vec_sel
#define vec_sl __builtin_vec_sl
#define vec_sld __builtin_vec_sld
+#define vec_sldw __builtin_vsx_xxsldwi
#define vec_sll __builtin_vec_sll
#define vec_slo __builtin_vec_slo
#define vec_splat __builtin_vec_splat
diff --git a/gcc/config/rs6000/rs6000-builtin.def
b/gcc/config/rs6000/rs6000-builtin.def
index 41186b1..ebe005a 100644
--- a/gcc/config/rs6000/rs6000-builtin.def
+++ b/gcc/config/rs6000/rs6000-builtin.def
@@ -1502,6 +1502,7 @@ BU_ALTIVEC_OVERLOAD_X (LVSR, "lvsr")
BU_ALTIVEC_OVERLOAD_X (MUL, "mul")
BU_ALTIVEC_OVERLOAD_X (PROMOTE, "promote")
BU_ALTIVEC_OVERLOAD_X (SLD, "sld")
+BU_ALTIVEC_OVERLOAD_X (SLDW, "sldw")
BU_ALTIVEC_OVERLOAD_X (SPLAT, "splat")
BU_ALTIVEC_OVERLOAD_X (SPLATS, "splats")
BU_ALTIVEC_OVERLOAD_X (ST, "st")
diff --git a/gcc/config/rs6000/rs6000-c.c b/gcc/config/rs6000/rs6000-c.c
index a0536d6..8039814 100644
--- a/gcc/config/rs6000/rs6000-c.c
+++ b/gcc/config/rs6000/rs6000-c.c
@@ -2182,6 +2182,11 @@ const struct altivec_builtin_types
altivec_overloaded_builtins[] = {
RS6000_BTI_unsigned_V4SI, RS6000_BTI_unsigned_V8HI,
RS6000_BTI_unsigned_V8HI, 0 },
{ ALTIVEC_BUILTIN_VEC_MULE, ALTIVEC_BUILTIN_VMULESH,
RS6000_BTI_V4SI, RS6000_BTI_V8HI, RS6000_BTI_V8HI, 0 },
+ { ALTIVEC_BUILTIN_VEC_MULE, ALTIVEC_BUILTIN_VMULESH,
+ RS6000_BTI_V4SI, RS6000_BTI_V4SI, RS6000_BTI_V4SI, 0 },
+ { ALTIVEC_BUILTIN_VEC_MULE, ALTIVEC_BUILTIN_VMULESH,
+ RS6000_BTI_unsigned_V4SI, RS6000_BTI_unsigned_V4SI,
+ RS6000_BTI_unsigned_V4SI, 0 },
{ ALTIVEC_BUILTIN_VEC_VMULEUB, ALTIVEC_BUILTIN_VMULEUB,
RS6000_BTI_unsigned_V8HI, RS6000_BTI_unsigned_V16QI,
RS6000_BTI_unsigned_V16QI, 0 },
{ ALTIVEC_BUILTIN_VEC_VMULESB, ALTIVEC_BUILTIN_VMULESB,
@@ -2197,6 +2202,11 @@ const struct altivec_builtin_types
altivec_overloaded_builtins[] = {
{ ALTIVEC_BUILTIN_VEC_MULO, ALTIVEC_BUILTIN_VMULOUH,
RS6000_BTI_unsigned_V4SI, RS6000_BTI_unsigned_V8HI,
RS6000_BTI_unsigned_V8HI, 0 },
{ ALTIVEC_BUILTIN_VEC_MULO, ALTIVEC_BUILTIN_VMULOSH,
+ RS6000_BTI_V4SI, RS6000_BTI_V4SI, RS6000_BTI_V4SI, 0 },
+ { ALTIVEC_BUILTIN_VEC_MULO, ALTIVEC_BUILTIN_VMULOSH,
+ RS6000_BTI_unsigned_V4SI, RS6000_BTI_unsigned_V4SI,
+ RS6000_BTI_unsigned_V4SI, 0 },
+ { ALTIVEC_BUILTIN_VEC_MULO, ALTIVEC_BUILTIN_VMULOSH,
RS6000_BTI_V4SI, RS6000_BTI_V8HI, RS6000_BTI_V8HI, 0 },
{ ALTIVEC_BUILTIN_VEC_VMULOSH, ALTIVEC_BUILTIN_VMULOSH,
RS6000_BTI_V4SI, RS6000_BTI_V8HI, RS6000_BTI_V8HI, 0 },
@@ -3457,6 +3467,30 @@ const struct altivec_builtin_types
altivec_overloaded_builtins[] = {
RS6000_BTI_bool_V16QI, RS6000_BTI_bool_V16QI, RS6000_BTI_bool_V16QI,
RS6000_BTI_NOT_OPAQUE },
{ ALTIVEC_BUILTIN_VEC_SLD, ALTIVEC_BUILTIN_VSLDOI_2DF,
RS6000_BTI_V2DF, RS6000_BTI_V2DF, RS6000_BTI_V2DF, RS6000_BTI_NOT_OPAQUE },
+ { ALTIVEC_BUILTIN_VEC_SLDW, VSX_BUILTIN_XXSLDWI_16QI,
+ RS6000_BTI_V16QI, RS6000_BTI_V16QI, RS6000_BTI_V16QI,
+ RS6000_BTI_NOT_OPAQUE },
+ { ALTIVEC_BUILTIN_VEC_SLDW, VSX_BUILTIN_XXSLDWI_16QI,
+ RS6000_BTI_unsigned_V16QI, RS6000_BTI_unsigned_V16QI,
+ RS6000_BTI_unsigned_V16QI, RS6000_BTI_NOT_OPAQUE },
+ { ALTIVEC_BUILTIN_VEC_SLDW, VSX_BUILTIN_XXSLDWI_8HI,
+ RS6000_BTI_V8HI, RS6000_BTI_V8HI, RS6000_BTI_V8HI,
+ RS6000_BTI_NOT_OPAQUE },
+ { ALTIVEC_BUILTIN_VEC_SLDW, VSX_BUILTIN_XXSLDWI_8HI,
+ RS6000_BTI_unsigned_V8HI, RS6000_BTI_unsigned_V8HI,
+ RS6000_BTI_unsigned_V8HI, RS6000_BTI_NOT_OPAQUE },
+ { ALTIVEC_BUILTIN_VEC_SLDW, VSX_BUILTIN_XXSLDWI_4SI,
+ RS6000_BTI_V4SI, RS6000_BTI_V4SI, RS6000_BTI_V4SI,
+ RS6000_BTI_NOT_OPAQUE },
+ { ALTIVEC_BUILTIN_VEC_SLDW, VSX_BUILTIN_XXSLDWI_4SI,
+ RS6000_BTI_unsigned_V4SI, RS6000_BTI_unsigned_V4SI,
+ RS6000_BTI_unsigned_V4SI, RS6000_BTI_NOT_OPAQUE },
+ { ALTIVEC_BUILTIN_VEC_SLDW, VSX_BUILTIN_XXSLDWI_2DI,
+ RS6000_BTI_V2DI, RS6000_BTI_V2DI, RS6000_BTI_V2DI,
+ RS6000_BTI_NOT_OPAQUE },
+ { ALTIVEC_BUILTIN_VEC_SLDW, VSX_BUILTIN_XXSLDWI_2DI,
+ RS6000_BTI_unsigned_V2DI, RS6000_BTI_unsigned_V2DI,
+ RS6000_BTI_unsigned_V2DI, RS6000_BTI_NOT_OPAQUE },
{ ALTIVEC_BUILTIN_VEC_ST, ALTIVEC_BUILTIN_STVX_V2DF,
RS6000_BTI_void, RS6000_BTI_V2DF, RS6000_BTI_INTSI, ~RS6000_BTI_V2DF },
{ ALTIVEC_BUILTIN_VEC_ST, ALTIVEC_BUILTIN_STVX_V2DI,
@@ -4451,6 +4485,9 @@ const struct altivec_builtin_types
altivec_overloaded_builtins[] = {
RS6000_BTI_unsigned_V16QI, 0 },
{ P8V_BUILTIN_VEC_VBPERMQ, P8V_BUILTIN_VBPERMQ,
+ RS6000_BTI_unsigned_V2DI, RS6000_BTI_unsigned_V2DI,
+ RS6000_BTI_unsigned_V16QI, 0 },
+ { P8V_BUILTIN_VEC_VBPERMQ, P8V_BUILTIN_VBPERMQ,
RS6000_BTI_V2DI, RS6000_BTI_V16QI, RS6000_BTI_V16QI, 0 },
{ P8V_BUILTIN_VEC_VBPERMQ, P8V_BUILTIN_VBPERMQ,
RS6000_BTI_unsigned_V2DI, RS6000_BTI_unsigned_V16QI,
diff --git a/gcc/doc/extend.texi b/gcc/doc/extend.texi
index c737634..3511d25 100644
--- a/gcc/doc/extend.texi
+++ b/gcc/doc/extend.texi
@@ -16321,6 +16321,10 @@ vector signed short vec_mule (vector signed char,
vector unsigned int vec_mule (vector unsigned short,
vector unsigned short);
vector signed int vec_mule (vector signed short, vector signed short);
+vector unsigned int vec_mule (vector unsigned int,
+ vector unsigned int);
+vector signed int vec_mule (vector signed int,
+ vector signed int);
vector signed int vec_vmulesh (vector signed short,
vector signed short);
@@ -16340,6 +16344,7 @@ vector signed short vec_mulo (vector signed char,
vector signed char);
vector unsigned int vec_mulo (vector unsigned short,
vector unsigned short);
vector signed int vec_mulo (vector signed short, vector signed short);
+vector unsigned int vec_mulo (vector unsigned short, vector unsigned short);
vector signed int vec_vmulosh (vector signed short,
vector signed short);
@@ -16641,6 +16646,31 @@ vector bool char vec_sld (vector bool char,
vector bool char,
const int);
+vector signed char vec_sldw (vector signed char,
+ vector signed char,
+ const int);
+vector unsigned char vec_sldw (vector unsigned char,
+ vector unsigned char,
+ const int);
+vector signed short vec_sldw (vector signed short,
+ vector signed short,
+ const int);
+vector unsigned short vec_sldw (vector unsigned short,
+ vector unsigned short,
+ const int);
+vector signed int vec_sldw (vector signed int,
+ vector signed int,
+ const int);
+vector unsigned int vec_sldw (vector unsigned int,
+ vector unsigned int,
+ const int);
+vector signed long long vec_sldw (vector signed long long,
+ vector signed long long,
+ const int);
+vector unsigned long long vec_sldw (vector unsigned long long,
+ vector unsigned long long,
+ const int);
+
vector signed int vec_sll (vector signed int,
vector unsigned int);
vector signed int vec_sll (vector signed int,
@@ -17909,6 +17939,8 @@ vector long long vec_vbpermq (vector signed char,
vector signed char);
vector long long vec_vbpermq (vector unsigned char, vector unsigned char);
vector unsigned char vec_bperm (vector unsigned char, vector unsigned char);
+vector unsigned char vec_bperm (vector unsigned long long,
+ vector unsigned char);
vector unsigned long long vec_bperm (vector unsigned __int128,
vector unsigned char);
diff --git a/gcc/testsuite/gcc.target/powerpc/builtins-3-p8.c
b/gcc/testsuite/gcc.target/powerpc/builtins-3-p8.c
index b0f6929..3baa1d8 100644
--- a/gcc/testsuite/gcc.target/powerpc/builtins-3-p8.c
+++ b/gcc/testsuite/gcc.target/powerpc/builtins-3-p8.c
@@ -16,12 +16,6 @@ test_pack_float (vector double x, vector double y)
return vec_pack (x, y);
}
-vector long long
-test_nabs_long_long (vector long long x)
-{
- return vec_nabs (x);
-}
-
vector signed int
test_vsi_packs_vsll_vsll (vector signed long long x,
vector signed long long y)
@@ -36,12 +30,6 @@ test_vui_packs_vull_vull (vector unsigned long long x,
return vec_packs (x, y);
}
-vector long long
-test_neg_long_long (vector long long x)
-{
- return vec_neg (x);
-}
-
vector unsigned char
test_unsigned_char_popcnt_signed_char (vector signed char x)
{
@@ -90,35 +78,34 @@ test_unsigned_long_long_popcnt_unsigned_long (vector
unsigned long long x)
return vec_popcnt (x);
}
+vector signed short
+test_vss_mradds_vss_vss (vector signed short x, vector signed short y,
+ vector signed short z)
+{
+ return vec_mradds (x, y, z);
+}
+
/* Expected test results:
test_eq_long_long 1 vcmpequd inst
test_pack_float 1 vpkudum inst
- test_nabs_long_long 1 vspltisw, 1 vsubudm, 1 vminsd
test_vsi_packs_vsll_vsll 1 vpksdss
test_vui_packs_vull_vull 1 vpkudus
- test_neg_long_long 1 vspltisw, 1 vsubudm
- test_eq_long_long 1 vcmpequd inst
- test_pack_float 1 vpkudum inst
- test_nabs_long_long 1 vspltisw, 1 vsubudm, 1 vminsd
- test_neg_long_long 1 vspltisw, 1 vsubudm
test_unsigned_char_popcnt_signed_char 1 vpopcntb
test_unsigned_char_popcnt_unsigned_char 1 vpopcntb
test_unsigned_short_popcnt_signed_short 1 vpopcnth
test_unsigned_short_popcnt_unsigned_short 1 vpopcnth
- test_unsigned_signed_popcnt_signed_int 1 vpopcntw
- test_unsigned_signed_popcnt_unsigned_int 1 vpopcntw
- test_unsigned_signed_popcnt_signed_long 1 vpopcntd
- test_unsigned_signed_popcnt_unsigned_long 1 vpopcntd */
+ test_unsigned_int_popcnt_signed_int 2 vpopcntw
+ test_unsigned_int_popcnt_unsigned_int 1 vpopcntd
+ test_unsigned_long_long_popcnt_unsigned_long 1 vpopcntd
+ test_vss_mradds_vss_vsss 1 vmhraddshs */
/* { dg-final { scan-assembler-times "vcmpequd" 1 } } */
/* { dg-final { scan-assembler-times "vpkudum" 1 } } */
-/* { dg-final { scan-assembler-times "vspltisw" 2 } } */
-/* { dg-final { scan-assembler-times "vsubudm" 2 } } */
-/* { dg-final { scan-assembler-times "vminsd" 1 } } */
/* { dg-final { scan-assembler-times "vpksdss" 1 } } */
/* { dg-final { scan-assembler-times "vpkudus" 1 } } */
/* { dg-final { scan-assembler-times "vpopcntb" 2 } } */
/* { dg-final { scan-assembler-times "vpopcnth" 2 } } */
/* { dg-final { scan-assembler-times "vpopcntw" 2 } } */
/* { dg-final { scan-assembler-times "vpopcntd" 2 } } */
+/* { dg-final { scan-assembler-times "vmhraddshs" 1 } } */
diff --git a/gcc/testsuite/gcc.target/powerpc/builtins-3-p9.c
b/gcc/testsuite/gcc.target/powerpc/builtins-3-p9.c
index e3db2da..46a31ae 100644
--- a/gcc/testsuite/gcc.target/powerpc/builtins-3-p9.c
+++ b/gcc/testsuite/gcc.target/powerpc/builtins-3-p9.c
@@ -28,15 +28,44 @@ test_ne_long (vector bool long long x, vector bool long
long y)
return vec_cmpne (x, y);
}
+vector long long
+test_nabs_long_long (vector long long x)
+{
+ return vec_nabs (x);
+}
+
+vector long long
+test_neg_long_long (vector long long x)
+{
+ return vec_neg (x);
+}
+
+vector unsigned long long
+test_vull_bperm_vull_vuc (vector unsigned long long x,
+ vector unsigned char y)
+{
+ return vec_bperm (x, y);
+}
+
/* Expected test results:
test_ne_char 1 vcmpneb
test_ne_short 1 vcmpneh
test_ne_int 1 vcmpnew
- test_ne_long 1 vcmpequd, 1 xxlnor inst */
+ test_ne_long 1 vcmpequd, 1 xxlnor inst
+ test_nabs_long_long 1 xxspltib, 1 vsubudm, 1 vminsd
+ test_neg_long_long 1 vnegd
+ test_vull_bperm_vull_vuc 1 vbpermd
+
/* { dg-final { scan-assembler-times "vcmpneb" 1 } } */
/* { dg-final { scan-assembler-times "vcmpneh" 1 } } */
/* { dg-final { scan-assembler-times "vcmpnew" 1 } } */
/* { dg-final { scan-assembler-times "vcmpequd" 1 } } */
/* { dg-final { scan-assembler-times "xxlnor" 1 } } */
+/* { dg-final { scan-assembler-times "xxspltib" 1 } } */
+/* { dg-final { scan-assembler-times "vsubudm" 1 } } */
+/* { dg-final { scan-assembler-times "vminsd" 1 } } */
+/* { dg-final { scan-assembler-times "vnegd" 1 } } */
+/* { dg-final { scan-assembler-times "vbpermd" 1 } } */
+
diff --git a/gcc/testsuite/gcc.target/powerpc/builtins-3.c
b/gcc/testsuite/gcc.target/powerpc/builtins-3.c
index 1549329..5cbac81 100644
--- a/gcc/testsuite/gcc.target/powerpc/builtins-3.c
+++ b/gcc/testsuite/gcc.target/powerpc/builtins-3.c
@@ -112,6 +112,81 @@ test_vull_slo_vull_vuc (vector unsigned long long x,
vector unsigned char y)
return vec_slo (x, y);
}
+vector signed int
+test_vsi_mule_vsi_vsi (vector signed int x, vector signed int y)
+{
+ return vec_mule (x, y);
+}
+
+vector unsigned int
+test_vui_mule_vui_vui (vector unsigned int x, vector unsigned int y)
+{
+ return vec_mule (x, y);
+}
+
+vector signed int
+test_vsi_mulo_vsi_vsi (vector signed int x, vector signed int y)
+{
+ return vec_mulo (x, y);
+}
+
+vector unsigned int
+test_vui_mulo_vui_vui (vector unsigned int x, vector unsigned int y)
+{
+ return vec_mulo (x, y);
+}
+
+vector signed char
+test_vsc_sldw_vsc_vsc (vector signed char x, vector signed char y)
+{
+ return vec_sldw (x, y, 1);
+}
+
+vector unsigned char
+test_vuc_sldw_vuc_vuc (vector unsigned char x, vector unsigned char y)
+{
+ return vec_sldw (x, y, 3);
+}
+
+vector signed short int
+test_vssi_sldw_vssi_vssi (vector signed short int x,
+ vector signed short int y)
+{
+ return vec_sldw (x, y, 1);
+}
+
+vector unsigned short int
+test_vusi_sldw_vusi_vusi (vector unsigned short int x,
+ vector unsigned short int y)
+{
+ return vec_sldw (x, y, 3);
+}
+
+vector signed int
+test_vsi_sldw_vsi_vsi (vector signed int x, vector signed int y)
+{
+ return vec_sldw (x, y, 1);
+}
+
+vector unsigned int
+test_vui_sldw_vui_vui (vector unsigned int x, vector unsigned int y)
+{
+ return vec_sldw (x, y, 3);
+}
+
+vector signed long long
+test_vsl_sldw_vsl_vsl (vector signed long long x, vector signed long long y)
+{
+ return vec_sldw (x, y, 1);
+}
+
+vector unsigned long long
+test_vul_sldw_vul_vul (vector unsigned long long x,
+ vector unsigned long long y)
+{
+ return vec_sldw (x, y, 3);
+}
+
/* Expected test results:
test_eq_char 1 vcmpequb inst
@@ -131,7 +206,19 @@ test_vull_slo_vull_vuc (vector unsigned long long x,
vector unsigned char y)
test_vsll_slo_vsll_vsc 1 vslo
test_vsll_slo_vsll_vuc 1 vslo
test_vull_slo_vsll_vsc 1 vslo
- test_vull_slo_vsll_vuc 1 vslo */
+ test_vull_slo_vsll_vuc 1 vslo
+ test_vsi_mulo_vsi_vsi 1 vmulosh
+ test_vui_mulo_vui_vui 1 vmulosh
+ test_vsi_mule_vsi_vsi 1 vmulesh
+ test_vui_mule_vui_vui 1 vmulesh
+ test_vsc_mulo_vsc_vsc 1 xxsldwi
+ test_vuc_mulo_vuc_vuc 1 xxsldwi
+ test_vssi_mulo_vssi_vssi 1 xxsldwi
+ test_vusi_mulo_vusi_vusi 1 xxsldwi
+ test_vsi_mulo_vsi_vsi 1 xxsldwi
+ test_vui_mulo_vui_vui 1 xxsldwi
+ test_vsl_mulo_vsl_vsl 1 xxsldwi
+ test_vul_mulo_vul_vul 1 xxsldwi */
/* { dg-final { scan-assembler-times "vcmpequb" 1 } } */
/* { dg-final { scan-assembler-times "vcmpequh" 1 } } */
@@ -149,4 +236,6 @@ test_vull_slo_vull_vuc (vector unsigned long long x, vector
unsigned char y)
/* { dg-final { scan-assembler-times "xvnegsp" 1 } } */
/* { dg-final { scan-assembler-times "xvnegdp" 1 } } */
/* { dg-final { scan-assembler-times "vslo" 4 } } */
-
+/* { dg-final { scan-assembler-times "vmulosh" 2 } } */
+/* { dg-final { scan-assembler-times "vmulesh" 2 } } */
+/* { dg-final { scan-assembler-times "xxsldwi" 8 } } */
--
1.9.1
