diff options
author | Dennis Zhang <dennis.zhang@arm.com> | 2020-02-21 15:36:13 +0000 |
---|---|---|
committer | Dennis Zhang <dennis.zhang@arm.com> | 2020-02-21 15:36:13 +0000 |
commit | 436016f45694c7236e2e9f9db2adb0b4d9bf6b94 (patch) | |
tree | 02de5ac2ba0cf5b55459d05ccf280431add435a5 /gcc/config/arm/neon.md | |
parent | b59506cd8b9f92293fc154c1470691534e29ddcf (diff) | |
download | gcc-436016f45694c7236e2e9f9db2adb0b4d9bf6b94.zip gcc-436016f45694c7236e2e9f9db2adb0b4d9bf6b94.tar.gz gcc-436016f45694c7236e2e9f9db2adb0b4d9bf6b94.tar.bz2 |
arm: ACLE I8MM multiply-accumulate
This patch adds intrinsics for matrix multiply-accumulate instructions
including vmmlaq_s32, vmmlaq_u32, and vusmmlaq_s32.
gcc/ChangeLog:
2020-02-21 Dennis Zhang <dennis.zhang@arm.com>
* 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_<sup>mmlav16qi): New.
* config/arm/unspecs.md (UNSPEC_MATMUL_S, UNSPEC_MATMUL_U): New.
(UNSPEC_MATMUL_US): New.
gcc/testsuite/ChangeLog:
2020-02-21 Dennis Zhang <dennis.zhang@arm.com>
* gcc.target/arm/simd/vmmla_1.c: New test.
Diffstat (limited to 'gcc/config/arm/neon.md')
-rw-r--r-- | gcc/config/arm/neon.md | 11 |
1 files changed, 11 insertions, 0 deletions
diff --git a/gcc/config/arm/neon.md b/gcc/config/arm/neon.md index 5d085dc..039cd90 100644 --- a/gcc/config/arm/neon.md +++ b/gcc/config/arm/neon.md @@ -6585,3 +6585,14 @@ if (BYTES_BIG_ENDIAN) "vabd.<V_if_elem> %<V_reg>0, %<V_reg>1, %<V_reg>2" [(set_attr "type" "neon_fp_abd_s<q>")] ) + +(define_insn "neon_<sup>mmlav16qi" + [(set (match_operand:V4SI 0 "register_operand" "=w") + (plus:V4SI + (unspec:V4SI [(match_operand:V16QI 2 "register_operand" "w") + (match_operand:V16QI 3 "register_operand" "w")] MATMUL) + (match_operand:V4SI 1 "register_operand" "0")))] + "TARGET_I8MM" + "v<sup>mmla.<mmla_sfx>\t%q0, %q2, %q3" + [(set_attr "type" "neon_mla_s_q")] +) |