From 0883673194a2b28ad888498d74dac9a4cccc513c Mon Sep 17 00:00:00 2001 From: Kyrylo Tkachov Date: Thu, 7 Nov 2019 10:43:19 +0000 Subject: [PATCH] [arm][3/X] Implement __smla* intrinsics (Q-setting) This patch implements some more Q-setting intrinsics form the SMLA* group. These can set the saturation bit on overflow in the accumulation step. Like earlier, these have non-Q-setting RTL forms as well for when the Q-bit read is not needed. * config/arm/arm.md (arm_smlabb_setq): New define_insn. (arm_smlabb): New define_expand. (*maddhisi4tb): Rename to... (maddhisi4tb): ... This. (*maddhisi4tt): Rename to... (maddhisi4tt): ... This. (arm_smlatb_setq): New define_insn. (arm_smlatb): New define_expand. (arm_smlatt_setq): New define_insn. (arm_smlatt): New define_expand. (arm__insn): New define_insn. (arm_): New define_expand. * config/arm/arm_acle.h (__smlabb, __smlatb, __smlabt, __smlatt, __smlawb, __smlawt): Define. * config/arm_acle_builtins.def: Define builtins for the above. * config/arm/iterators.md (SMLAWBT): New int_iterator. (slaw_op): New int_attribute. * config/arm/unspecs.md (UNSPEC_SMLAWB, UNSPEC_SMLAWT): Define. * gcc.target/arm/acle/dsp_arith.c: Update test. From-SVN: r277916 --- gcc/ChangeLog | 21 +++ gcc/config/arm/arm.md | 136 +++++++++++++++++- gcc/config/arm/arm_acle.h | 44 ++++++ gcc/config/arm/arm_acle_builtins.def | 5 + gcc/config/arm/iterators.md | 4 + gcc/config/arm/unspecs.md | 2 + gcc/testsuite/ChangeLog | 4 + gcc/testsuite/gcc.target/arm/acle/dsp_arith.c | 46 ++++++ 8 files changed, 260 insertions(+), 2 deletions(-) diff --git a/gcc/ChangeLog b/gcc/ChangeLog index 53de0821a78..436e38bcfb3 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -1,3 +1,24 @@ +2019-11-07 Kyrylo Tkachov + + * config/arm/arm.md (arm_smlabb_setq): New define_insn. + (arm_smlabb): New define_expand. + (*maddhisi4tb): Rename to... + (maddhisi4tb): ... This. + (*maddhisi4tt): Rename to... + (maddhisi4tt): ... This. + (arm_smlatb_setq): New define_insn. + (arm_smlatb): New define_expand. + (arm_smlatt_setq): New define_insn. + (arm_smlatt): New define_expand. + (arm__insn): New define_insn. + (arm_): New define_expand. + * config/arm/arm_acle.h (__smlabb, __smlatb, __smlabt, __smlatt, + __smlawb, __smlawt): Define. + * config/arm_acle_builtins.def: Define builtins for the above. + * config/arm/iterators.md (SMLAWBT): New int_iterator. + (slaw_op): New int_attribute. + * config/arm/unspecs.md (UNSPEC_SMLAWB, UNSPEC_SMLAWT): Define. + 2019-11-07 Kyrylo Tkachov * config/arm/arm.md (arm_): New define_expand. diff --git a/gcc/config/arm/arm.md b/gcc/config/arm/arm.md index 298b0bedcfd..c3a7aa9e40d 100644 --- a/gcc/config/arm/arm.md +++ b/gcc/config/arm/arm.md @@ -2565,8 +2565,40 @@ (set_attr "predicable" "yes")] ) +(define_insn "arm_smlabb_setq" + [(set (match_operand:SI 0 "s_register_operand" "=r") + (plus:SI (mult:SI (sign_extend:SI + (match_operand:HI 1 "s_register_operand" "r")) + (sign_extend:SI + (match_operand:HI 2 "s_register_operand" "r"))) + (match_operand:SI 3 "s_register_operand" "r"))) + (set (reg:CC APSRQ_REGNUM) + (unspec:CC [(reg:CC APSRQ_REGNUM)] UNSPEC_Q_SET))] + "TARGET_DSP_MULTIPLY" + "smlabb%?\\t%0, %1, %2, %3" + [(set_attr "type" "smlaxy") + (set_attr "predicable" "yes")] +) + +(define_expand "arm_smlabb" + [(match_operand:SI 0 "s_register_operand") + (match_operand:SI 1 "s_register_operand") + (match_operand:SI 2 "s_register_operand") + (match_operand:SI 3 "s_register_operand")] + "TARGET_DSP_MULTIPLY" + { + rtx mult1 = gen_lowpart (HImode, operands[1]); + rtx mult2 = gen_lowpart (HImode, operands[2]); + if (ARM_Q_BIT_READ) + emit_insn (gen_arm_smlabb_setq (operands[0], mult1, mult2, operands[3])); + else + emit_insn (gen_maddhisi4 (operands[0], mult1, mult2, operands[3])); + DONE; + } +) + ;; Note: there is no maddhisi4ibt because this one is canonical form -(define_insn "*maddhisi4tb" +(define_insn "maddhisi4tb" [(set (match_operand:SI 0 "s_register_operand" "=r") (plus:SI (mult:SI (ashiftrt:SI (match_operand:SI 1 "s_register_operand" "r") @@ -2580,7 +2612,41 @@ (set_attr "predicable" "yes")] ) -(define_insn "*maddhisi4tt" +(define_insn "arm_smlatb_setq" + [(set (match_operand:SI 0 "s_register_operand" "=r") + (plus:SI (mult:SI (ashiftrt:SI + (match_operand:SI 1 "s_register_operand" "r") + (const_int 16)) + (sign_extend:SI + (match_operand:HI 2 "s_register_operand" "r"))) + (match_operand:SI 3 "s_register_operand" "r"))) + (set (reg:CC APSRQ_REGNUM) + (unspec:CC [(reg:CC APSRQ_REGNUM)] UNSPEC_Q_SET))] + "TARGET_DSP_MULTIPLY" + "smlatb%?\\t%0, %1, %2, %3" + [(set_attr "type" "smlaxy") + (set_attr "predicable" "yes")] +) + +(define_expand "arm_smlatb" + [(match_operand:SI 0 "s_register_operand") + (match_operand:SI 1 "s_register_operand") + (match_operand:SI 2 "s_register_operand") + (match_operand:SI 3 "s_register_operand")] + "TARGET_DSP_MULTIPLY" + { + rtx mult2 = gen_lowpart (HImode, operands[2]); + if (ARM_Q_BIT_READ) + emit_insn (gen_arm_smlatb_setq (operands[0], operands[1], + mult2, operands[3])); + else + emit_insn (gen_maddhisi4tb (operands[0], operands[1], + mult2, operands[3])); + DONE; + } +) + +(define_insn "maddhisi4tt" [(set (match_operand:SI 0 "s_register_operand" "=r") (plus:SI (mult:SI (ashiftrt:SI (match_operand:SI 1 "s_register_operand" "r") @@ -2595,6 +2661,40 @@ (set_attr "predicable" "yes")] ) +(define_insn "arm_smlatt_setq" + [(set (match_operand:SI 0 "s_register_operand" "=r") + (plus:SI (mult:SI (ashiftrt:SI + (match_operand:SI 1 "s_register_operand" "r") + (const_int 16)) + (ashiftrt:SI + (match_operand:SI 2 "s_register_operand" "r") + (const_int 16))) + (match_operand:SI 3 "s_register_operand" "r"))) + (set (reg:CC APSRQ_REGNUM) + (unspec:CC [(reg:CC APSRQ_REGNUM)] UNSPEC_Q_SET))] + "TARGET_DSP_MULTIPLY" + "smlatt%?\\t%0, %1, %2, %3" + [(set_attr "type" "smlaxy") + (set_attr "predicable" "yes")] +) + +(define_expand "arm_smlatt" + [(match_operand:SI 0 "s_register_operand") + (match_operand:SI 1 "s_register_operand") + (match_operand:SI 2 "s_register_operand") + (match_operand:SI 3 "s_register_operand")] + "TARGET_DSP_MULTIPLY" + { + if (ARM_Q_BIT_READ) + emit_insn (gen_arm_smlatt_setq (operands[0], operands[1], + operands[2], operands[3])); + else + emit_insn (gen_maddhisi4tt (operands[0], operands[1], + operands[2], operands[3])); + DONE; + } +) + (define_insn "maddhidi4" [(set (match_operand:DI 0 "s_register_operand" "=r") (plus:DI @@ -2641,6 +2741,38 @@ [(set_attr "type" "smlalxy") (set_attr "predicable" "yes")]) +(define_insn "arm__insn" + [(set (match_operand:SI 0 "s_register_operand" "=r") + (unspec:SI + [(match_operand:SI 1 "s_register_operand" "r") + (match_operand:SI 2 "s_register_operand" "r") + (match_operand:SI 3 "s_register_operand" "r")] + SMLAWBT))] + "TARGET_DSP_MULTIPLY && " + "%?\\t%0, %1, %2, %3" + [(set_attr "type" "smlaxy") + (set_attr "predicable" "yes")] +) + +(define_expand "arm_" + [(set (match_operand:SI 0 "s_register_operand") + (unspec:SI + [(match_operand:SI 1 "s_register_operand") + (match_operand:SI 2 "s_register_operand") + (match_operand:SI 3 "s_register_operand")] + SMLAWBT))] + "TARGET_DSP_MULTIPLY" + { + if (ARM_Q_BIT_READ) + emit_insn (gen_arm__setq_insn (operands[0], operands[1], + operands[2], operands[3])); + else + emit_insn (gen_arm__insn (operands[0], operands[1], + operands[2], operands[3])); + DONE; + } +) + (define_expand "mulsf3" [(set (match_operand:SF 0 "s_register_operand") (mult:SF (match_operand:SF 1 "s_register_operand") diff --git a/gcc/config/arm/arm_acle.h b/gcc/config/arm/arm_acle.h index 397653d3e8b..fb144cf789c 100644 --- a/gcc/config/arm/arm_acle.h +++ b/gcc/config/arm/arm_acle.h @@ -499,6 +499,50 @@ __qdbl (int32_t __x) { return __qadd (__x, __x); } + +__extension__ extern __inline int32_t +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) +__smlabb (int32_t __a, int32_t __b, int32_t __c) +{ + return __builtin_arm_smlabb (__a, __b, __c); +} + +__extension__ extern __inline int32_t +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) +__smlatb (int32_t __a, int32_t __b, int32_t __c) +{ + return __builtin_arm_smlatb (__a, __b, __c); +} + +/* smlatb is equivalent to smlabt with the two multiplication operands + swapped around. */ +__extension__ extern __inline int32_t +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) +__smlabt (int32_t __a, int32_t __b, int32_t __c) +{ + return __smlatb (__b, __a, __c); +} + +__extension__ extern __inline int32_t +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) +__smlatt (int32_t __a, int32_t __b, int32_t __c) +{ + return __builtin_arm_smlatt (__a, __b, __c); +} + +__extension__ extern __inline int32_t +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) +__smlawb (int32_t __a, int32_t __b, int32_t __c) +{ + return __builtin_arm_smlawb (__a, __b, __c); +} + +__extension__ extern __inline int32_t +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) +__smlawt (int32_t __a, int32_t __b, int32_t __c) +{ + return __builtin_arm_smlawt (__a, __b, __c); +} #endif #pragma GCC push_options diff --git a/gcc/config/arm/arm_acle_builtins.def b/gcc/config/arm/arm_acle_builtins.def index def1a569311..85dd87e9d8e 100644 --- a/gcc/config/arm/arm_acle_builtins.def +++ b/gcc/config/arm/arm_acle_builtins.def @@ -86,3 +86,8 @@ VAR1 (SAT_OCCURRED, saturation_occurred, si) VAR1 (SET_SAT, set_saturation, void) VAR1 (BINOP, qadd, si) VAR1 (BINOP, qsub, si) +VAR1 (TERNOP, smlabb, si) +VAR1 (TERNOP, smlatb, si) +VAR1 (TERNOP, smlatt, si) +VAR1 (TERNOP, smlawb, si) +VAR1 (TERNOP, smlawt, si) diff --git a/gcc/config/arm/iterators.md b/gcc/config/arm/iterators.md index ebb8218f265..006ffd7fc6c 100644 --- a/gcc/config/arm/iterators.md +++ b/gcc/config/arm/iterators.md @@ -446,6 +446,8 @@ (define_int_iterator SIMD32_DIMODE [UNSPEC_SMLALD UNSPEC_SMLALDX UNSPEC_SMLSLD UNSPEC_SMLSLDX]) +(define_int_iterator SMLAWBT [UNSPEC_SMLAWB UNSPEC_SMLAWT]) + (define_int_iterator VQRDMLH_AS [UNSPEC_VQRDMLAH UNSPEC_VQRDMLSH]) (define_int_iterator VFM_LANE_AS [UNSPEC_VFMA_LANE UNSPEC_VFMS_LANE]) @@ -1127,3 +1129,5 @@ (define_int_attr opsuffix [(UNSPEC_DOT_S "s8") (UNSPEC_DOT_U "u8")]) + +(define_int_attr smlaw_op [(UNSPEC_SMLAWB "smlawb") (UNSPEC_SMLAWT "smlawt")]) diff --git a/gcc/config/arm/unspecs.md b/gcc/config/arm/unspecs.md index a4287949e52..06988abb67e 100644 --- a/gcc/config/arm/unspecs.md +++ b/gcc/config/arm/unspecs.md @@ -130,6 +130,8 @@ UNSPEC_SMLALDX ; Represent the SMLALDX operation. UNSPEC_SMLSLD ; Represent the SMLSLD operation. UNSPEC_SMLSLDX ; Represent the SMLSLDX operation. + UNSPEC_SMLAWB ; Represent the SMLAWB operation. + UNSPEC_SMLAWT ; Represent the SMLAWT operation. ]) diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog index 05183b08b7d..6008206aa5e 100644 --- a/gcc/testsuite/ChangeLog +++ b/gcc/testsuite/ChangeLog @@ -1,3 +1,7 @@ +2019-11-07 Kyrylo Tkachov + + * gcc.target/arm/acle/dsp_arith.c: Update test. + 2019-11-07 Kyrylo Tkachov * gcc.target/arm/acle/dsp_arith.c: New test. diff --git a/gcc/testsuite/gcc.target/arm/acle/dsp_arith.c b/gcc/testsuite/gcc.target/arm/acle/dsp_arith.c index f0bf80993be..9ebd55a1287 100644 --- a/gcc/testsuite/gcc.target/arm/acle/dsp_arith.c +++ b/gcc/testsuite/gcc.target/arm/acle/dsp_arith.c @@ -25,3 +25,49 @@ test_qsub (int32_t a, int32_t b) } /* { dg-final { scan-assembler-times "qsub\t...?, ...?, ...?" 1 } } */ + +int32_t +test_smlabb (int32_t a, int32_t b, int32_t c) +{ + return __smlabb (a, b, c); +} + +/* { dg-final { scan-assembler-times "smlabb\t...?, ...?, ...?, ...?" 1 } } */ + +int32_t +test_smlabt (int32_t a, int32_t b, int32_t c) +{ + return __smlabt (a, b, c); +} + +int32_t +test_smlatb (int32_t a, int32_t b, int32_t c) +{ + return __smlatb (a, b, c); +} + +/* { dg-final { scan-assembler-times "smlatb\t...?, ...?, ...?, ...?" 2 } } */ + +int32_t +test_smlatt (int32_t a, int32_t b, int32_t c) +{ + return __smlatt (a, b, c); +} + +/* { dg-final { scan-assembler-times "smlatt\t...?, ...?, ...?, ...?" 1 } } */ + +int32_t +test_smlawb (int32_t a, int32_t b, int32_t c) +{ + return __smlawb (a, b, c); +} + +/* { dg-final { scan-assembler-times "smlawb\t...?, ...?, ...?, ...?" 1 } } */ + +int32_t +test_smlawt (int32_t a, int32_t b, int32_t c) +{ + return __smlawt (a, b, c); +} + +/* { dg-final { scan-assembler-times "smlawt\t...?, ...?, ...?, ...?" 1 } } */ -- 2.30.2