Hi all,
On 16/12/2019 13:45, Dennis Zhang wrote:
Hi all,
This patch is part of a series adding support for Armv8.6-A features.
It depends on the Arm Armv8.6-A CLI patch,
https://gcc.gnu.org/ml/gcc-patches/2019-11/msg02195.html.
It also depends on the Armv8.6-A effective target checking patch,
https://gcc.gnu.org/ml/gcc-patches/2019-12/msg00857.html.
It also depends on the ARMv8.6-A I8MM dot product patch for using the
same builtin qualifier
https://gcc.gnu.org/ml/gcc-patches/2019-12/msg00945.html.
This patch adds intrinsics for matrix multiply-accumulate operations
including vmmlaq_s32, vmmlaq_u32, and vusmmlaq_s32.
ACLE documents are at https://developer.arm.com/docs/101028/latest
ISA documents are at https://developer.arm.com/docs/ddi0596/latest
Regtested for arm-none-linux-gnueabi-armv8.2-a.
Is it OK for trunk please?
Thanks,
Dennis
gcc/ChangeLog:
2019-12-10 Dennis Zhang
* config/arm/arm_neon.h (vmmlaq_s32, vmmlaq_u32, vusmmlaq_s32): New.
* config/arm/arm_neon_builtins.def (smmla, ummla, usmmla): New.
* config/arm/iterators.md (MATMUL): New.
(sup): Add UNSPEC_MATMUL_S, UNSPEC_MATMUL_U, and UNSPEC_MATMUL_US.
(mmla_sfx): New.
* config/arm/neon.md (neon_mmlav16qi): New.
* config/arm/unspecs.md (UNSPEC_MATMUL_S): New.
(UNSPEC_MATMUL_U, UNSPEC_MATMUL_US): New.
gcc/testsuite/ChangeLog:
2019-12-10 Dennis Zhang
* gcc.target/arm/simd/vmmla_1.c: New test.
This patch has been updated according to the feedback on related AArch64
version at https://gcc.gnu.org/ml/gcc-patches/2020-01/msg01591.html
Regtested. OK to commit please?
Many thanks
Dennis
gcc/ChangeLog:
2020-02-11 Dennis Zhang
* config/arm/arm-builtins.c (USTERNOP_QUALIFIERS): New macro.
* config/arm/arm_neon.h (vmmlaq_s32, vmmlaq_u32, vusmmlaq_s32): New.
* config/arm/arm_neon_builtins.def (smmla, ummla, usmmla): New.
* config/arm/iterators.md (MATMUL): New iterator.
(sup): Add UNSPEC_MATMUL_S, UNSPEC_MATMUL_U, and UNSPEC_MATMUL_US.
(mmla_sfx): New attribute.
* config/arm/neon.md (neon_mmlav16qi): New.
* config/arm/unspecs.md (UNSPEC_MATMUL_S, UNSPEC_MATMUL_U): New.
(UNSPEC_MATMUL_US): New.
gcc/testsuite/ChangeLog:
2020-02-11 Dennis Zhang
* gcc.target/arm/simd/vmmla_1.c: New test.
diff --git a/gcc/config/arm/arm-builtins.c b/gcc/config/arm/arm-builtins.c
index 7f279cca668..60c65c1772f 100644
--- a/gcc/config/arm/arm-builtins.c
+++ b/gcc/config/arm/arm-builtins.c
@@ -122,6 +122,11 @@ arm_unsigned_uternop_qualifiers[SIMD_MAX_BUILTIN_ARGS]
qualifier_unsigned };
#define UTERNOP_QUALIFIERS (arm_unsigned_uternop_qualifiers)
+static enum arm_type_qualifiers
+arm_usternop_qualifiers[SIMD_MAX_BUILTIN_ARGS]
+ = { qualifier_none, qualifier_none, qualifier_unsigned, qualifier_none };
+#define USTERNOP_QUALIFIERS (arm_usternop_qualifiers)
+
/* T (T, immediate). */
static enum arm_type_qualifiers
arm_binop_imm_qualifiers[SIMD_MAX_BUILTIN_ARGS]
diff --git a/gcc/config/arm/arm_neon.h b/gcc/config/arm/arm_neon.h
index 3c78f435009..7461c90e3fe 100644
--- a/gcc/config/arm/arm_neon.h
+++ b/gcc/config/arm/arm_neon.h
@@ -18745,6 +18745,34 @@ vcmlaq_rot270_laneq_f32 (float32x4_t __r, float32x4_t __a, float32x4_t __b,
#pragma GCC pop_options
#endif
+/* AdvSIMD 8-bit Integer Matrix Multiply (I8MM) intrinsics. */
+
+#pragma GCC push_options
+#pragma GCC target ("arch=armv8.2-a+i8mm")
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vmmlaq_s32 (int32x4_t __r, int8x16_t __a, int8x16_t __b)
+{
+ return __builtin_neon_smmlav16qi (__r, __a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vmmlaq_u32 (uint32x4_t __r, uint8x16_t __a, uint8x16_t __b)
+{
+ return __builtin_neon_ummlav16qi_ (__r, __a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vusmmlaq_s32 (int32x4_t __r, uint8x16_t __a, int8x16_t __b)
+{
+ return __builtin_neon_usmmlav16qi_ssus (__r, __a, __b);
+}
+
+#pragma GCC pop_options
+
#ifdef __cplusplus
}
#endif
diff --git a/gcc/config/arm/arm_neon_builtins.def b/gcc/config/arm/arm_neon_builtins.def
index e9ff4e501cb..d304cdb33cc 100644
--- a/gcc/config/arm/arm_neon_builtins.def
+++ b/gcc/config/arm/arm_neon_builtins.def
@@ -373,3 +373,7 @@ VAR2 (MAC_LANE_PAIR, vcmlaq_lane0, v4sf, v8hf)
VAR2 (MAC_LANE_PAIR, vcmlaq_lane90, v4sf, v8hf)
VAR2 (MAC_LANE_PAIR, vcmlaq_lane180, v4sf, v8hf)
VAR2 (MAC_LANE_PAIR, vcmlaq_lane270, v4sf, v8hf)
+
+VAR1 (TERNOP, smmla, v16qi)
+VAR1 (UTERNOP, ummla, v16qi)
+VAR1 (USTERNOP, usmmla, v16qi)
diff --git a/gcc/config/arm/iterators.md b/gcc/config/arm/iterators.md
index 33e29509f00..141ad96d6db 100644
--- a/gcc/config/arm/iterators.md
+++ b/gcc/config/arm/iterators.md
@@ -485,6 +485,8 @@
(define_int_iterator VCADD [UNSPEC_VCADD90 UNSPEC_VCADD27