From: Stam Markianos-Wright <Stam.Markianos-Wright@arm.com>
To: "gcc-patches@gcc.gnu.org" <gcc-patches@gcc.gnu.org>,
Richard Earnshaw <Richard.Earnshaw@arm.com>,
Kyrylo Tkachov <Kyrylo.Tkachov@arm.com>,
Marcus Shawcroft <Marcus.Shawcroft@arm.com>,
Richard Sandiford <Richard.Sandiford@arm.com>
Subject: Re: [GCC][PATCH][AArch64]Add ACLE intrinsics for dot product (usdot - vector, <us/su>dot - by element) for AArch64 AdvSIMD ARMv8.6 Extension
Date: Thu, 09 Jan 2020 14:48:00 -0000 [thread overview]
Message-ID: <cc966061-1c1c-0e83-40e0-57c9b99d72d9@arm.com> (raw)
In-Reply-To: <mptr20mglkq.fsf@arm.com>
[-- Attachment #1: Type: text/plain, Size: 3995 bytes --]
On 12/30/19 10:21 AM, Richard Sandiford wrote:
> Stam Markianos-Wright <Stam.Markianos-Wright@arm.com> writes:
>> On 12/20/19 2:13 PM, Richard Sandiford wrote:
>>> Stam Markianos-Wright <Stam.Markianos-Wright@arm.com> writes:
>>>> +**...
>>>> +**ret
>>>> +*/
>>>> +int32x2_t ufoo (int32x2_t r, uint8x8_t x, int8x8_t y)
>>>> +{
>>>> + return vusdot_s32 (r, x, y);
>>>> +}
>>>> +
>>>
>>> If we're using check-function-bodies anyway, it might be slightly more
>>> robust to compile at -O and check for the exact RA. E.g.:
>>>
>>> /*
>>> **ufoo:
>>> **usdotv0\.2s, (v1\.8b, v2\.8b|v2\.8b, v1\.8b)
>>> **ret
>>> */
>>>
>>> Just a suggestion though -- either way is fine.
>>
>> done this too and as per our internal discussion also added one
>> xx_untied tests for usdot and one for usdot_lane
>>
>> That's one xx_untied test for each of the RTL pattern types added in
>> aarch64-simd.md. Lmk if this is ok!
>>
>> Also I found that the way we were using check-function-bodies wasn't
>> actually checking the assembler correctly, so I've changed that to:
>> +/* { dg-final { check-function-bodies "**" "" "" } } */
>> +/* { dg-skip-if "" { *-*-* } { "-fno-fat-lto-objects" } } */
>> which seems to perform more checks
>
> Ah, OK, hadn't realised that we were cycling through optimisation
> options already. In that case, it might be better to leave out the
> -O from the dg-options and instead use:
>
> /* { dg-skip-if "" { *-*-* } { { "-fno-fat-lto-objects" } { "-O0" } } } */
>
> (untested).
>
> It's unfortunate that we're skipping this for -O0 though. Ideally we'd
> still compile the code and just skip the dg-final. Does it work if you do:
>
> /* { dg-final { check-function-bodies "**" "" {-O[^0]} } } */
> /* { dg-skip-if "" { *-*-* } { { "-fno-fat-lto-objects" } } } */
>
> ? Make sure that we actually still run the check-function-bodies when
> optimisation is enabled. :-)
This works!
Now we are only doing the following for O0:
PASS: gcc.target/aarch64/advsimd-intrinsics/vdot-compile-3-2.c -O0 (test for
excess errors)
whereas for other optimisation levels do all the checks:
PASS: gcc.target/aarch64/advsimd-intrinsics/vdot-compile-3-2.c -O1 (test for
excess errors)
PASS: gcc.target/aarch64/advsimd-intrinsics/vdot-compile-3-2.c -O1
check-function-bodies ufoo
PASS: gcc.target/aarch64/advsimd-intrinsics/vdot-compile-3-2.c -O1
check-function-bodies ufooq
PASS: gcc.target/aarch64/advsimd-intrinsics/vdot-compile-3-2.c -O1
check-function-bodies ufoo_lane
PASS: gcc.target/aarch64/advsimd-intrinsics/vdot-compile-3-2.c -O1
check-function-bodies ufoo_laneq
PASS: gcc.target/aarch64/advsimd-intrinsics/vdot-compile-3-2.c -O1
check-function-bodies ufooq_lane
PASS: gcc.target/aarch64/advsimd-intrinsics/vdot-compile-3-2.c -O1
check-function-bodies ufooq_laneq
PASS: gcc.target/aarch64/advsimd-intrinsics/vdot-compile-3-2.c -O1
check-function-bodies sfoo_lane
PASS: gcc.target/aarch64/advsimd-intrinsics/vdot-compile-3-2.c -O1
check-function-bodies sfoo_laneq
PASS: gcc.target/aarch64/advsimd-intrinsics/vdot-compile-3-2.c -O1
check-function-bodies sfooq_lane
PASS: gcc.target/aarch64/advsimd-intrinsics/vdot-compile-3-2.c -O1
check-function-bodies sfooq_laneq
PASS: gcc.target/aarch64/advsimd-intrinsics/vdot-compile-3-2.c -O1
check-function-bodies ufoo_untied
PASS: gcc.target/aarch64/advsimd-intrinsics/vdot-compile-3-2.c -O1
check-function-bodies ufooq_laneq_untied
>
> Also, I'm an idiot. The reason I'd used (...|...) in the regexps was
> that "dot product is commutative". But of course that's not true for
> these mixed-sign ops, so the string must be:
>
> usdot v0\.2s, v1\.8b, v2\.8b
>
> The patch copied the (...|...) regexps above to the lane tests, but those
> wouldn't be commutative even if the operands had the same type.
Ahh, makes sense now. Done :)
Cheers,
Stam
>
> Thanks,
> Richard
>
[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #2: i8mm-us-su-dot-aarch64_REV3.patch --]
[-- Type: text/x-patch; name="i8mm-us-su-dot-aarch64_REV3.patch", Size: 21319 bytes --]
diff --git a/gcc/config/aarch64/aarch64-builtins.c b/gcc/config/aarch64/aarch64-builtins.c
index 1bd2640a1ced352de232fed1cf134b46c69b80f7..702b317d94d2fc6ebe59609727ad853f3f5cc652 100644
--- a/gcc/config/aarch64/aarch64-builtins.c
+++ b/gcc/config/aarch64/aarch64-builtins.c
@@ -107,6 +107,9 @@ enum aarch64_type_qualifiers
/* Lane indices selected in pairs. - must be in range, and flipped for
bigendian. */
qualifier_lane_pair_index = 0x800,
+ /* Lane indices selected in quadtuplets. - must be in range, and flipped for
+ bigendian. */
+ qualifier_lane_quadtup_index = 0x1000,
};
typedef struct
@@ -173,6 +176,10 @@ aarch64_types_ternopu_imm_qualifiers[SIMD_MAX_BUILTIN_ARGS]
= { qualifier_unsigned, qualifier_unsigned,
qualifier_unsigned, qualifier_immediate };
#define TYPES_TERNOPUI (aarch64_types_ternopu_imm_qualifiers)
+static enum aarch64_type_qualifiers
+aarch64_types_ternop_ssus_qualifiers[SIMD_MAX_BUILTIN_ARGS]
+ = { qualifier_none, qualifier_none, qualifier_unsigned, qualifier_none };
+#define TYPES_TERNOP_SSUS (aarch64_types_ternop_ssus_qualifiers)
static enum aarch64_type_qualifiers
@@ -191,6 +198,19 @@ aarch64_types_quadopu_lane_qualifiers[SIMD_MAX_BUILTIN_ARGS]
qualifier_unsigned, qualifier_lane_index };
#define TYPES_QUADOPU_LANE (aarch64_types_quadopu_lane_qualifiers)
+static enum aarch64_type_qualifiers
+aarch64_types_quadopssus_lane_quadtup_qualifiers[SIMD_MAX_BUILTIN_ARGS]
+ = { qualifier_none, qualifier_none, qualifier_unsigned,
+ qualifier_none, qualifier_lane_quadtup_index };
+#define TYPES_QUADOPSSUS_LANE_QUADTUP \
+ (aarch64_types_quadopssus_lane_quadtup_qualifiers)
+static enum aarch64_type_qualifiers
+aarch64_types_quadopsssu_lane_quadtup_qualifiers[SIMD_MAX_BUILTIN_ARGS]
+ = { qualifier_none, qualifier_none, qualifier_none,
+ qualifier_unsigned, qualifier_lane_quadtup_index };
+#define TYPES_QUADOPSSSU_LANE_QUADTUP \
+ (aarch64_types_quadopsssu_lane_quadtup_qualifiers)
+
static enum aarch64_type_qualifiers
aarch64_types_quadopu_imm_qualifiers[SIMD_MAX_BUILTIN_ARGS]
= { qualifier_unsigned, qualifier_unsigned, qualifier_unsigned,
@@ -1260,6 +1280,7 @@ typedef enum
SIMD_ARG_LANE_INDEX,
SIMD_ARG_STRUCT_LOAD_STORE_LANE_INDEX,
SIMD_ARG_LANE_PAIR_INDEX,
+ SIMD_ARG_LANE_QUADTUP_INDEX,
SIMD_ARG_STOP
} builtin_simd_arg;
@@ -1349,9 +1370,25 @@ aarch64_simd_expand_args (rtx target, int icode, int have_retval,
op[opc] = gen_int_mode (ENDIAN_LANE_N (nunits / 2, lane),
SImode);
}
- /* Fall through - if the lane index isn't a constant then
- the next case will error. */
- /* FALLTHRU */
+ /* If the lane index isn't a constant then error out. */
+ goto constant_arg;
+ case SIMD_ARG_LANE_QUADTUP_INDEX:
+ /* Must be a previous operand into which this is an index and
+ index is restricted to nunits / 4. */
+ gcc_assert (opc > 0);
+ if (CONST_INT_P (op[opc]))
+ {
+ machine_mode vmode = insn_data[icode].operand[opc - 1].mode;
+ unsigned int nunits
+ = GET_MODE_NUNITS (vmode).to_constant ();
+ aarch64_simd_lane_bounds (op[opc], 0, nunits / 4, exp);
+ /* Keep to GCC-vector-extension lane indices in the RTL. */
+ int lane = INTVAL (op[opc]);
+ op[opc] = gen_int_mode (ENDIAN_LANE_N (nunits / 4, lane),
+ SImode);
+ }
+ /* If the lane index isn't a constant then error out. */
+ goto constant_arg;
case SIMD_ARG_CONSTANT:
constant_arg:
if (!(*insn_data[icode].operand[opc].predicate)
@@ -1464,6 +1501,8 @@ aarch64_simd_expand_builtin (int fcode, tree exp, rtx target)
args[k] = SIMD_ARG_LANE_INDEX;
else if (d->qualifiers[qualifiers_k] & qualifier_lane_pair_index)
args[k] = SIMD_ARG_LANE_PAIR_INDEX;
+ else if (d->qualifiers[qualifiers_k] & qualifier_lane_quadtup_index)
+ args[k] = SIMD_ARG_LANE_QUADTUP_INDEX;
else if (d->qualifiers[qualifiers_k] & qualifier_struct_load_store_lane_index)
args[k] = SIMD_ARG_STRUCT_LOAD_STORE_LANE_INDEX;
else if (d->qualifiers[qualifiers_k] & qualifier_immediate)
diff --git a/gcc/config/aarch64/aarch64-simd-builtins.def b/gcc/config/aarch64/aarch64-simd-builtins.def
index 57fc5933b43bfc0da132342c681b8a2c14549c9c..4744dd1f6b2f20327db810277ff65c59ce5abdec 100644
--- a/gcc/config/aarch64/aarch64-simd-builtins.def
+++ b/gcc/config/aarch64/aarch64-simd-builtins.def
@@ -212,10 +212,15 @@
/* Implemented by aarch64_<sur><dotprod>{_lane}{q}<dot_mode>. */
BUILTIN_VB (TERNOP, sdot, 0)
BUILTIN_VB (TERNOPU, udot, 0)
+ BUILTIN_VB (TERNOP_SSUS, usdot, 0)
BUILTIN_VB (QUADOP_LANE, sdot_lane, 0)
BUILTIN_VB (QUADOPU_LANE, udot_lane, 0)
BUILTIN_VB (QUADOP_LANE, sdot_laneq, 0)
BUILTIN_VB (QUADOPU_LANE, udot_laneq, 0)
+ BUILTIN_VB (QUADOPSSUS_LANE_QUADTUP, usdot_lane, 0)
+ BUILTIN_VB (QUADOPSSUS_LANE_QUADTUP, usdot_laneq, 0)
+ BUILTIN_VB (QUADOPSSSU_LANE_QUADTUP, sudot_lane, 0)
+ BUILTIN_VB (QUADOPSSSU_LANE_QUADTUP, sudot_laneq, 0)
/* Implemented by aarch64_fcadd<rot><mode>. */
BUILTIN_VHSDF (BINOP, fcadd90, 0)
diff --git a/gcc/config/aarch64/aarch64-simd.md b/gcc/config/aarch64/aarch64-simd.md
index 4e28cf97516df19e1d502e56c776f6b34f15c116..2306fd8b42c2215fcd6229f6fbfadb9b7f2d19ae 100644
--- a/gcc/config/aarch64/aarch64-simd.md
+++ b/gcc/config/aarch64/aarch64-simd.md
@@ -506,6 +506,20 @@
[(set_attr "type" "neon_dot<q>")]
)
+;; These instructions map to the __builtins for the armv8.6a I8MM usdot
+;; (vector) Dot Product operation.
+(define_insn "aarch64_usdot<vsi2qi>"
+ [(set (match_operand:VS 0 "register_operand" "=w")
+ (plus:VS
+ (unspec:VS [(match_operand:<VSI2QI> 2 "register_operand" "w")
+ (match_operand:<VSI2QI> 3 "register_operand" "w")]
+ UNSPEC_USDOT)
+ (match_operand:VS 1 "register_operand" "0")))]
+ "TARGET_I8MM"
+ "usdot\\t%0.<Vtype>, %2.<Vdottype>, %3.<Vdottype>"
+ [(set_attr "type" "neon_dot<q>")]
+)
+
;; These expands map to the Dot Product optab the vectorizer checks for.
;; The auto-vectorizer expects a dot product builtin that also does an
;; accumulation into the provided register.
@@ -573,6 +587,26 @@
[(set_attr "type" "neon_dot<q>")]
)
+;; These instructions map to the __builtins for the armv8.6a I8MM usdot, sudot
+;; (by element) Dot Product operations.
+(define_insn "aarch64_<DOTPROD_I8MM:sur>dot_lane<VB:isquadop><VS:vsi2qi>"
+ [(set (match_operand:VS 0 "register_operand" "=w")
+ (plus:VS
+ (unspec:VS [(match_operand:<VS:VSI2QI> 2 "register_operand" "w")
+ (match_operand:VB 3 "register_operand" "w")
+ (match_operand:SI 4 "immediate_operand" "i")]
+ DOTPROD_I8MM)
+ (match_operand:VS 1 "register_operand" "0")))]
+ "TARGET_I8MM"
+ {
+ int nunits = GET_MODE_NUNITS (<VB:MODE>mode).to_constant ();
+ int lane = INTVAL (operands[4]);
+ operands[4] = gen_int_mode (ENDIAN_LANE_N (nunits / 4, lane), SImode);
+ return "<DOTPROD_I8MM:sur>dot\\t%0.<VS:Vtype>, %2.<VS:Vdottype>, %3.4b[%4]";
+ }
+ [(set_attr "type" "neon_dot<VS:q>")]
+)
+
(define_expand "copysign<mode>3"
[(match_operand:VHSDF 0 "register_operand")
(match_operand:VHSDF 1 "register_operand")
diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h
index c7425346b86b5f5310a7148c465497b53ac75bf5..5d6c65e99330a22cfe598532ecea85c1907431cb 100644
--- a/gcc/config/aarch64/arm_neon.h
+++ b/gcc/config/aarch64/arm_neon.h
@@ -34606,6 +34606,89 @@ vrnd64xq_f64 (float64x2_t __a)
#pragma GCC pop_options
+/* AdvSIMD 8-bit Integer Matrix Multiply (I8MM) intrinsics. */
+
+#pragma GCC push_options
+#pragma GCC target ("arch=armv8.2-a+i8mm")
+
+__extension__ extern __inline int32x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vusdot_s32 (int32x2_t __r, uint8x8_t __a, int8x8_t __b)
+{
+ return __builtin_aarch64_usdotv8qi_ssus (__r, __a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vusdotq_s32 (int32x4_t __r, uint8x16_t __a, int8x16_t __b)
+{
+ return __builtin_aarch64_usdotv16qi_ssus (__r, __a, __b);
+}
+
+__extension__ extern __inline int32x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vusdot_lane_s32 (int32x2_t __r, uint8x8_t __a, int8x8_t __b, const int __index)
+{
+ return __builtin_aarch64_usdot_lanev8qi_ssuss (__r, __a, __b, __index);
+}
+
+__extension__ extern __inline int32x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vusdot_laneq_s32 (int32x2_t __r, uint8x8_t __a, int8x16_t __b,
+ const int __index)
+{
+ return __builtin_aarch64_usdot_laneqv8qi_ssuss (__r, __a, __b, __index);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vusdotq_lane_s32 (int32x4_t __r, uint8x16_t __a, int8x8_t __b,
+ const int __index)
+{
+ return __builtin_aarch64_usdot_lanev16qi_ssuss (__r, __a, __b, __index);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vusdotq_laneq_s32 (int32x4_t __r, uint8x16_t __a, int8x16_t __b,
+ const int __index)
+{
+ return __builtin_aarch64_usdot_laneqv16qi_ssuss (__r, __a, __b, __index);
+}
+
+__extension__ extern __inline int32x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vsudot_lane_s32 (int32x2_t __r, int8x8_t __a, uint8x8_t __b, const int __index)
+{
+ return __builtin_aarch64_sudot_lanev8qi_sssus (__r, __a, __b, __index);
+}
+
+__extension__ extern __inline int32x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vsudot_laneq_s32 (int32x2_t __r, int8x8_t __a, uint8x16_t __b,
+ const int __index)
+{
+ return __builtin_aarch64_sudot_laneqv8qi_sssus (__r, __a, __b, __index);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vsudotq_lane_s32 (int32x4_t __r, int8x16_t __a, uint8x8_t __b,
+ const int __index)
+{
+ return __builtin_aarch64_sudot_lanev16qi_sssus (__r, __a, __b, __index);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vsudotq_laneq_s32 (int32x4_t __r, int8x16_t __a, uint8x16_t __b,
+ const int __index)
+{
+ return __builtin_aarch64_sudot_laneqv16qi_sssus (__r, __a, __b, __index);
+}
+
+#pragma GCC pop_options
+
#undef __aarch64_vget_lane_any
#undef __aarch64_vdup_lane_any
diff --git a/gcc/config/aarch64/iterators.md b/gcc/config/aarch64/iterators.md
index e5fa31f6748ee81d4323f11544fd8edb19d9af43..9dee626c65ef19f7d1582c05611028b65b2a32a8 100644
--- a/gcc/config/aarch64/iterators.md
+++ b/gcc/config/aarch64/iterators.md
@@ -650,6 +650,8 @@
UNSPEC_UMULHS ; Used in aarch64-sve2.md.
UNSPEC_UMULHRS ; Used in aarch64-sve2.md.
UNSPEC_ASRD ; Used in aarch64-sve.md.
+ UNSPEC_USDOT ; Used in aarch64-simd.md.
+ UNSPEC_SUDOT ; Used in aarch64-simd.md.
])
;; ------------------------------------------------------------------
@@ -1299,6 +1301,8 @@
(define_mode_attr f16quad [(V2SF "") (V4SF "q")])
+(define_mode_attr isquadop [(V8QI "") (V16QI "q")])
+
(define_code_attr f16mac [(plus "a") (minus "s")])
;; Map smax to smin and umax to umin.
@@ -1859,6 +1863,8 @@
(define_int_iterator DOTPROD [UNSPEC_SDOT UNSPEC_UDOT])
+(define_int_iterator DOTPROD_I8MM [UNSPEC_USDOT UNSPEC_SUDOT])
+
(define_int_iterator ADDSUBHN [UNSPEC_ADDHN UNSPEC_RADDHN
UNSPEC_SUBHN UNSPEC_RSUBHN])
@@ -2298,6 +2304,7 @@
(UNSPEC_URSHL "ur") (UNSPEC_SRSHL "sr")
(UNSPEC_UQRSHL "u") (UNSPEC_SQRSHL "s")
(UNSPEC_SDOT "s") (UNSPEC_UDOT "u")
+ (UNSPEC_USDOT "us") (UNSPEC_SUDOT "su")
])
(define_int_attr r [(UNSPEC_SQDMULH "") (UNSPEC_SQRDMULH "r")
diff --git a/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vdot-compile-3-1.c b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vdot-compile-3-1.c
new file mode 100755
index 0000000000000000000000000000000000000000..ac4f821e77143e93ecb23db71b7100b37df770f2
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vdot-compile-3-1.c
@@ -0,0 +1,136 @@
+/* { dg-do assemble { target { aarch64*-*-* } } } */
+/* { dg-require-effective-target arm_v8_2a_i8mm_ok } */
+/* { dg-add-options arm_v8_2a_i8mm } */
+/* { dg-additional-options "-save-temps" } */
+/* { dg-final { check-function-bodies "**" "" {-O[^0]} } } */
+/* { dg-skip-if "" { *-*-* } { "-fno-fat-lto-objects" } } */
+
+#include <arm_neon.h>
+
+/* Unsigned-Signed Dot Product instructions. */
+
+/*
+**ufoo:
+** usdot v0\.2s, v1\.8b, v2\.8b
+** ret
+*/
+int32x2_t ufoo (int32x2_t r, uint8x8_t x, int8x8_t y)
+{
+ return vusdot_s32 (r, x, y);
+}
+
+/*
+**ufooq:
+** usdot v0\.4s, v1\.16b, v2\.16b
+** ret
+*/
+int32x4_t ufooq (int32x4_t r, uint8x16_t x, int8x16_t y)
+{
+ return vusdotq_s32 (r, x, y);
+}
+
+/*
+**ufoo_lane:
+** usdot v0\.2s, v1\.8b, v2\.4b\[0\]
+** ret
+*/
+int32x2_t ufoo_lane (int32x2_t r, uint8x8_t x, int8x8_t y)
+{
+ return vusdot_lane_s32 (r, x, y, 0);
+}
+
+/*
+**ufoo_laneq:
+** usdot v0\.2s, v1\.8b, v2\.4b\[2\]
+** ret
+*/
+int32x2_t ufoo_laneq (int32x2_t r, uint8x8_t x, int8x16_t y)
+{
+ return vusdot_laneq_s32 (r, x, y, 2);
+}
+
+/*
+**ufooq_lane:
+** usdot v0\.4s, v1\.16b, v2\.4b\[1\]
+** ret
+*/
+int32x4_t ufooq_lane (int32x4_t r, uint8x16_t x, int8x8_t y)
+{
+ return vusdotq_lane_s32 (r, x, y, 1);
+}
+
+/*
+**ufooq_laneq:
+** usdot v0\.4s, v1\.16b, v2\.4b\[3\]
+** ret
+*/
+int32x4_t ufooq_laneq (int32x4_t r, uint8x16_t x, int8x16_t y)
+{
+ return vusdotq_laneq_s32 (r, x, y, 3);
+}
+
+
+/* Signed-Unsigned Dot Product instructions. */
+
+/*
+**sfoo_lane:
+** sudot v0\.2s, v1\.8b, v2\.4b\[0\]
+** ret
+*/
+int32x2_t sfoo_lane (int32x2_t r, int8x8_t x, uint8x8_t y)
+{
+ return vsudot_lane_s32 (r, x, y, 0);
+}
+
+/*
+**sfoo_laneq:
+** sudot v0\.2s, v1\.8b, v2\.4b\[2\]
+** ret
+*/
+int32x2_t sfoo_laneq (int32x2_t r, int8x8_t x, uint8x16_t y)
+{
+ return vsudot_laneq_s32 (r, x, y, 2);
+}
+
+/*
+**sfooq_lane:
+** sudot v0\.4s, v1\.16b, v2\.4b\[1\]
+** ret
+*/
+int32x4_t sfooq_lane (int32x4_t r, int8x16_t x, uint8x8_t y)
+{
+ return vsudotq_lane_s32 (r, x, y, 1);
+}
+
+/*
+**sfooq_laneq:
+** sudot v0\.4s, v1\.16b, v2\.4b\[3\]
+** ret
+*/
+int32x4_t sfooq_laneq (int32x4_t r, int8x16_t x, uint8x16_t y)
+{
+ return vsudotq_laneq_s32 (r, x, y, 3);
+}
+
+/*
+**ufoo_untied:
+** mov v0\.8b, v1\.8b
+** usdot v0\.2s, v2\.8b, v3\.8b
+** ret
+*/
+int32x2_t ufoo_untied (int32x2_t unused, int32x2_t r, uint8x8_t x, int8x8_t y)
+{
+ return vusdot_s32 (r, x, y);
+}
+
+/*
+**ufooq_laneq_untied:
+** mov v0\.16b, v1\.16b
+** usdot v0\.4s, v2\.16b, v3\.4b\[3\]
+** ret
+*/
+int32x4_t ufooq_laneq_untied (int32x2_t unused, int32x4_t r, uint8x16_t x, int8x16_t y)
+{
+ return vusdotq_laneq_s32 (r, x, y, 3);
+}
+
diff --git a/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vdot-compile-3-2.c b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vdot-compile-3-2.c
new file mode 100755
index 0000000000000000000000000000000000000000..96bca2356e4d5d93378d2c8de3778fe28751117e
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vdot-compile-3-2.c
@@ -0,0 +1,137 @@
+/* { dg-do assemble { target { aarch64*-*-* } } } */
+/* { dg-require-effective-target arm_v8_2a_i8mm_ok } */
+/* { dg-add-options arm_v8_2a_i8mm } */
+/* { dg-additional-options "-mbig-endian -save-temps" } */
+/* { dg-final { check-function-bodies "**" "" {-O[^0]} } } */
+/* { dg-skip-if "" { *-*-* } { "-fno-fat-lto-objects" } } */
+
+#include <arm_neon.h>
+
+/* Unsigned-Signed Dot Product instructions. */
+
+/*
+**ufoo:
+** usdot v0\.2s, v1\.8b, v2\.8b
+** ret
+*/
+int32x2_t ufoo (int32x2_t r, uint8x8_t x, int8x8_t y)
+{
+ return vusdot_s32 (r, x, y);
+}
+
+/*
+**ufooq:
+** usdot v0\.4s, v1\.16b, v2\.16b
+** ret
+*/
+int32x4_t ufooq (int32x4_t r, uint8x16_t x, int8x16_t y)
+{
+ return vusdotq_s32 (r, x, y);
+}
+
+/*
+**ufoo_lane:
+** usdot v0\.2s, v1\.8b, v2\.4b\[0\]
+** ret
+*/
+int32x2_t ufoo_lane (int32x2_t r, uint8x8_t x, int8x8_t y)
+{
+ return vusdot_lane_s32 (r, x, y, 0);
+}
+
+/*
+**ufoo_laneq:
+** usdot v0\.2s, v1\.8b, v2\.4b\[2\]
+** ret
+*/
+int32x2_t ufoo_laneq (int32x2_t r, uint8x8_t x, int8x16_t y)
+{
+ return vusdot_laneq_s32 (r, x, y, 2);
+}
+
+/*
+**ufooq_lane:
+** usdot v0\.4s, v1\.16b, v2\.4b\[1\]
+** ret
+*/
+int32x4_t ufooq_lane (int32x4_t r, uint8x16_t x, int8x8_t y)
+{
+ return vusdotq_lane_s32 (r, x, y, 1);
+}
+
+/*
+**ufooq_laneq:
+** usdot v0\.4s, v1\.16b, v2\.4b\[3\]
+** ret
+*/
+int32x4_t ufooq_laneq (int32x4_t r, uint8x16_t x, int8x16_t y)
+{
+ return vusdotq_laneq_s32 (r, x, y, 3);
+}
+
+
+/* Signed-Unsigned Dot Product instructions. */
+
+/*
+**sfoo_lane:
+** sudot v0\.2s, v1\.8b, v2\.4b\[0\]
+** ret
+*/
+int32x2_t sfoo_lane (int32x2_t r, int8x8_t x, uint8x8_t y)
+{
+ return vsudot_lane_s32 (r, x, y, 0);
+}
+
+/*
+**sfoo_laneq:
+** sudot v0\.2s, v1\.8b, v2\.4b\[2\]
+** ret
+*/
+int32x2_t sfoo_laneq (int32x2_t r, int8x8_t x, uint8x16_t y)
+{
+ return vsudot_laneq_s32 (r, x, y, 2);
+}
+
+/*
+**sfooq_lane:
+** sudot v0\.4s, v1\.16b, v2\.4b\[1\]
+** ret
+*/
+int32x4_t sfooq_lane (int32x4_t r, int8x16_t x, uint8x8_t y)
+{
+ return vsudotq_lane_s32 (r, x, y, 1);
+}
+
+/*
+**sfooq_laneq:
+** sudot v0\.4s, v1\.16b, v2\.4b\[3\]
+** ret
+*/
+int32x4_t sfooq_laneq (int32x4_t r, int8x16_t x, uint8x16_t y)
+{
+ return vsudotq_laneq_s32 (r, x, y, 3);
+}
+
+/*
+**ufoo_untied:
+** mov v0\.8b, v1\.8b
+** usdot v0\.2s, v2\.8b, v3\.8b
+** ret
+*/
+int32x2_t ufoo_untied (int32x2_t unused, int32x2_t r, uint8x8_t x, int8x8_t y)
+{
+ return vusdot_s32 (r, x, y);
+}
+
+/*
+**ufooq_laneq_untied:
+** mov v0\.16b, v1\.16b
+** usdot v0\.4s, v2\.16b, v3\.4b\[3\]
+** ret
+*/
+int32x4_t ufooq_laneq_untied (int32x2_t unused, int32x4_t r, uint8x16_t x, int8x16_t y)
+{
+ return vusdotq_laneq_s32 (r, x, y, 3);
+}
+
+
diff --git a/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vdot-compile-3-3.c b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vdot-compile-3-3.c
new file mode 100755
index 0000000000000000000000000000000000000000..18ecabef8dc6b99872d71c8e412b6f4b4809e901
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vdot-compile-3-3.c
@@ -0,0 +1,31 @@
+/* { dg-do assemble { target { aarch64*-*-* } } } */
+/* { dg-require-effective-target arm_v8_2a_i8mm_ok } */
+/* { dg-add-options arm_v8_2a_i8mm } */
+/* { dg-additional-options "--save-temps" } */
+/* { dg-skip-if "" { *-*-* } { "-fno-fat-lto-objects" } } */
+
+#include <arm_neon.h>
+
+int32x2_t ufoo_lane (int32x2_t r, uint8x8_t x, int8x8_t y)
+{
+ /* { dg-error "lane -1 out of range 0 - 1" "" { target *-*-* } 0 } */
+ return vusdot_lane_s32 (r, x, y, -1);
+}
+
+int32x2_t ufoo_laneq (int32x2_t r, uint8x8_t x, int8x16_t y)
+{
+ /* { dg-error "lane -1 out of range 0 - 3" "" { target *-*-* } 0 } */
+ return vusdot_laneq_s32 (r, x, y, -1);
+}
+
+int32x4_t ufooq_lane (int32x4_t r, uint8x16_t x, int8x8_t y)
+{
+ /* { dg-error "lane 2 out of range 0 - 1" "" { target *-*-* } 0 } */
+ return vusdotq_lane_s32 (r, x, y, 2);
+}
+
+int32x4_t ufooq_laneq (int32x4_t r, uint8x16_t x, int8x16_t y)
+{
+ /* { dg-error "lane 4 out of range 0 - 3" "" { target *-*-* } 0 } */
+ return vusdotq_laneq_s32 (r, x, y, 4);
+}
diff --git a/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vdot-compile-3-4.c b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vdot-compile-3-4.c
new file mode 100644
index 0000000000000000000000000000000000000000..66c87d48694bad9624b491aec4cd1a38b75fbb95
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vdot-compile-3-4.c
@@ -0,0 +1,31 @@
+/* { dg-do assemble { target { aarch64*-*-* } } } */
+/* { dg-require-effective-target arm_v8_2a_i8mm_ok } */
+/* { dg-add-options arm_v8_2a_i8mm } */
+/* { dg-additional-options "--save-temps" } */
+/* { dg-skip-if "" { *-*-* } { "-fno-fat-lto-objects" } } */
+
+#include <arm_neon.h>
+
+int32x2_t sfoo_lane (int32x2_t r, int8x8_t x, uint8x8_t y)
+{
+ /* { dg-error "lane -1 out of range 0 - 1" "" { target *-*-* } 0 } */
+ return vsudot_lane_s32 (r, x, y, -1);
+}
+
+int32x2_t sfoo_laneq (int32x2_t r, int8x8_t x, uint8x16_t y)
+{
+ /* { dg-error "lane -1 out of range 0 - 3" "" { target *-*-* } 0 } */
+ return vsudot_laneq_s32 (r, x, y, -1);
+}
+
+int32x4_t sfooq_lane (int32x4_t r, int8x16_t x, uint8x8_t y)
+{
+ /* { dg-error "lane 2 out of range 0 - 1" "" { target *-*-* } 0 } */
+ return vsudotq_lane_s32 (r, x, y, 2);
+}
+
+int32x4_t sfooq_laneq (int32x4_t r, int8x16_t x, uint8x16_t y)
+{
+ /* { dg-error "lane 4 out of range 0 - 3" "" { target *-*-* } 0 } */
+ return vsudotq_laneq_s32 (r, x, y, 4);
+}
next prev parent reply other threads:[~2020-01-09 14:46 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-12-13 10:18 Stam Markianos-Wright
2019-12-13 11:03 ` Richard Sandiford
2019-12-20 13:44 ` Stam Markianos-Wright
2019-12-20 14:24 ` Richard Sandiford
2019-12-30 9:22 ` Stam Markianos-Wright
2019-12-30 10:29 ` Richard Sandiford
2020-01-09 14:48 ` Stam Markianos-Wright [this message]
2020-01-09 15:53 ` Richard Sandiford
2020-01-16 16:14 ` Stam Markianos-Wright
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=cc966061-1c1c-0e83-40e0-57c9b99d72d9@arm.com \
--to=stam.markianos-wright@arm.com \
--cc=Kyrylo.Tkachov@arm.com \
--cc=Marcus.Shawcroft@arm.com \
--cc=Richard.Earnshaw@arm.com \
--cc=Richard.Sandiford@arm.com \
--cc=gcc-patches@gcc.gnu.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).