From a6eacbf1055520e968d1a25f6d30d6ff4b66272d Mon Sep 17 00:00:00 2001 From: Christophe Lyon Date: Mon, 17 May 2021 12:29:42 +0000 Subject: [PATCH] arm: Auto-vectorization for MVE: vcmp Since MVE has a different set of vector comparison operators from Neon, we have to update the expansion to take into account the new ones, for instance 'NE' for which MVE does not require to use 'EQ' with the inverted condition. Conversely, Neon supports comparisons with #0, MVE does not. For: typedef long int vs32 __attribute__((vector_size(16))); vs32 cmp_eq_vs32_reg (vs32 a, vs32 b) { return a == b; } we now generate: cmp_eq_vs32_reg: vldr.64 d4, .L123 @ 8 [c=8 l=4] *mve_movv4si/8 vldr.64 d5, .L123+8 vldr.64 d6, .L123+16 @ 9 [c=8 l=4] *mve_movv4si/8 vldr.64 d7, .L123+24 vcmp.i32 eq, q0, q1 @ 7 [c=16 l=4] mve_vcmpeqq_v4si vpsel q0, q3, q2 @ 15 [c=8 l=4] mve_vpselq_sv4si bx lr @ 26 [c=8 l=4] *thumb2_return .L124: .align 3 .L123: .word 0 .word 0 .word 0 .word 0 .word 1 .word 1 .word 1 .word 1 For some reason emit_move_insn (zero, CONST0_RTX (cmp_mode)) produces a pair of vldr instead of vmov.i32, qX, #0 2021-05-17 Christophe Lyon gcc/ * config/arm/arm-protos.h (arm_expand_vector_compare): Update prototype. * config/arm/arm.c (arm_expand_vector_compare): Add support for MVE. (arm_expand_vcond): Likewise. * config/arm/iterators.md (supf): Remove VCMPNEQ_S, VCMPEQQ_S, VCMPEQQ_N_S, VCMPNEQ_N_S. (VCMPNEQ, VCMPEQQ, VCMPEQQ_N, VCMPNEQ_N): Remove. * config/arm/mve.md (@mve_vcmpq_): Add '@' prefix. (@mve_vcmpq_f): Likewise. (@mve_vcmpq_n_f): Likewise. (@mve_vpselq_): Likewise. (@mve_vpselq_f"): Likewise. * config/arm/neon.md (vec_cmp): Likewise. (vcond): Likewise. (vcond): Likewise. (vcondu): Likewise. (vcond_mask_): Likewise. * config/arm/unspecs.md (VCMPNEQ_U, VCMPNEQ_S, VCMPEQQ_S) (VCMPEQQ_N_S, VCMPNEQ_N_S, VCMPEQQ_U, CMPEQQ_N_U, VCMPNEQ_N_U) (VCMPGEQ_N_S, VCMPGEQ_S, VCMPGTQ_N_S, VCMPGTQ_S, VCMPLEQ_N_S) (VCMPLEQ_S, VCMPLTQ_N_S, VCMPLTQ_S, VCMPCSQ_N_U, VCMPCSQ_U) (VCMPHIQ_N_U, VCMPHIQ_U): Remove. * config/arm/vec-common.md (vec_cmp): Likewise. (vcond): Likewise. (vcond): Likewise. (vcondu): Likewise. (vcond_mask_): Likewise. Added unsafe math condition. gcc/testsuite * gcc.target/arm/simd/mve-compare-1.c: New test with GCC vectors. * gcc.target/arm/simd/mve-compare-2.c: New test with GCC vectors. * gcc.target/arm/simd/mve-compare-scalar-1.c: New test with GCC vectors. * gcc.target/arm/simd/mve-vcmp-f32.c: New test for auto-vectorization. * gcc.target/arm/simd/mve-vcmp.c: New test for auto-vectorization. --- gcc/config/arm/arm-protos.h | 2 +- gcc/config/arm/arm.c | 211 ++++++++++++++++----- gcc/config/arm/iterators.md | 9 +- gcc/config/arm/mve.md | 10 +- gcc/config/arm/neon.md | 87 --------- gcc/config/arm/unspecs.md | 20 -- gcc/config/arm/vec-common.md | 108 +++++++++++ gcc/testsuite/gcc.target/arm/simd/mve-compare-1.c | 80 ++++++++ gcc/testsuite/gcc.target/arm/simd/mve-compare-2.c | 38 ++++ .../gcc.target/arm/simd/mve-compare-scalar-1.c | 69 +++++++ gcc/testsuite/gcc.target/arm/simd/mve-vcmp-f32.c | 30 +++ gcc/testsuite/gcc.target/arm/simd/mve-vcmp.c | 50 +++++ 12 files changed, 548 insertions(+), 166 deletions(-) create mode 100644 gcc/testsuite/gcc.target/arm/simd/mve-compare-1.c create mode 100644 gcc/testsuite/gcc.target/arm/simd/mve-compare-2.c create mode 100644 gcc/testsuite/gcc.target/arm/simd/mve-compare-scalar-1.c create mode 100644 gcc/testsuite/gcc.target/arm/simd/mve-vcmp-f32.c create mode 100644 gcc/testsuite/gcc.target/arm/simd/mve-vcmp.c diff --git a/gcc/config/arm/arm-protos.h b/gcc/config/arm/arm-protos.h index 2521541..ffccaa7 100644 --- a/gcc/config/arm/arm-protos.h +++ b/gcc/config/arm/arm-protos.h @@ -373,7 +373,7 @@ extern void arm_emit_coreregs_64bit_shift (enum rtx_code, rtx, rtx, rtx, rtx, extern bool arm_fusion_enabled_p (tune_params::fuse_ops); extern bool arm_valid_symbolic_address_p (rtx); extern bool arm_validize_comparison (rtx *, rtx *, rtx *); -extern bool arm_expand_vector_compare (rtx, rtx_code, rtx, rtx, bool); +extern bool arm_expand_vector_compare (rtx, rtx_code, rtx, rtx, bool, bool); #endif /* RTX_CODE */ extern bool arm_gen_setmem (rtx *); diff --git a/gcc/config/arm/arm.c b/gcc/config/arm/arm.c index d0c0c50..eee3671 100644 --- a/gcc/config/arm/arm.c +++ b/gcc/config/arm/arm.c @@ -30959,66 +30959,113 @@ arm_split_atomic_op (enum rtx_code code, rtx old_out, rtx new_out, rtx mem, and return true if TARGET contains the inverse. If !CAN_INVERT, always store the result in TARGET, never its inverse. + If VCOND_MVE, do not emit the vpsel instruction here, let arm_expand_vcond do + it with the right destination type to avoid emiting two vpsel, one here and + one in arm_expand_vcond. + Note that the handling of floating-point comparisons is not IEEE compliant. */ bool arm_expand_vector_compare (rtx target, rtx_code code, rtx op0, rtx op1, - bool can_invert) + bool can_invert, bool vcond_mve) { machine_mode cmp_result_mode = GET_MODE (target); machine_mode cmp_mode = GET_MODE (op0); bool inverted; - switch (code) - { - /* For these we need to compute the inverse of the requested - comparison. */ - case UNORDERED: - case UNLT: - case UNLE: - case UNGT: - case UNGE: - case UNEQ: - case NE: - code = reverse_condition_maybe_unordered (code); - if (!can_invert) - { - /* Recursively emit the inverted comparison into a temporary - and then store its inverse in TARGET. This avoids reusing - TARGET (which for integer NE could be one of the inputs). */ - rtx tmp = gen_reg_rtx (cmp_result_mode); - if (arm_expand_vector_compare (tmp, code, op0, op1, true)) - gcc_unreachable (); - emit_insn (gen_rtx_SET (target, gen_rtx_NOT (cmp_result_mode, tmp))); - return false; - } - inverted = true; - break; - default: + /* MVE supports more comparisons than Neon. */ + if (TARGET_HAVE_MVE) inverted = false; - break; - } + else + switch (code) + { + /* For these we need to compute the inverse of the requested + comparison. */ + case UNORDERED: + case UNLT: + case UNLE: + case UNGT: + case UNGE: + case UNEQ: + case NE: + code = reverse_condition_maybe_unordered (code); + if (!can_invert) + { + /* Recursively emit the inverted comparison into a temporary + and then store its inverse in TARGET. This avoids reusing + TARGET (which for integer NE could be one of the inputs). */ + rtx tmp = gen_reg_rtx (cmp_result_mode); + if (arm_expand_vector_compare (tmp, code, op0, op1, true, vcond_mve)) + gcc_unreachable (); + emit_insn (gen_rtx_SET (target, gen_rtx_NOT (cmp_result_mode, tmp))); + return false; + } + inverted = true; + break; + + default: + inverted = false; + break; + } switch (code) { - /* These are natively supported for zero comparisons, but otherwise - require the operands to be swapped. */ + /* These are natively supported by Neon for zero comparisons, but otherwise + require the operands to be swapped. For MVE, we can only compare + registers. */ case LE: case LT: - if (op1 != CONST0_RTX (cmp_mode)) - { - code = swap_condition (code); - std::swap (op0, op1); - } + if (!TARGET_HAVE_MVE) + if (op1 != CONST0_RTX (cmp_mode)) + { + code = swap_condition (code); + std::swap (op0, op1); + } /* Fall through. */ - /* These are natively supported for both register and zero operands. */ + /* These are natively supported by Neon for both register and zero + operands. MVE supports registers only. */ case EQ: case GE: case GT: - emit_insn (gen_neon_vc (code, cmp_mode, target, op0, op1)); + case NE: + if (TARGET_HAVE_MVE) + { + rtx vpr_p0; + if (vcond_mve) + vpr_p0 = target; + else + vpr_p0 = gen_reg_rtx (HImode); + + switch (GET_MODE_CLASS (cmp_mode)) + { + case MODE_VECTOR_INT: + emit_insn (gen_mve_vcmpq (code, cmp_mode, vpr_p0, op0, force_reg (cmp_mode, op1))); + break; + case MODE_VECTOR_FLOAT: + if (TARGET_HAVE_MVE_FLOAT) + emit_insn (gen_mve_vcmpq_f (code, cmp_mode, vpr_p0, op0, force_reg (cmp_mode, op1))); + else + gcc_unreachable (); + break; + default: + gcc_unreachable (); + } + + /* If we are not expanding a vcond, build the result here. */ + if (!vcond_mve) + { + rtx zero = gen_reg_rtx (cmp_result_mode); + rtx one = gen_reg_rtx (cmp_result_mode); + emit_move_insn (zero, CONST0_RTX (cmp_result_mode)); + emit_move_insn (one, CONST1_RTX (cmp_result_mode)); + emit_insn (gen_mve_vpselq (VPSELQ_S, cmp_result_mode, target, one, zero, vpr_p0)); + } + } + else + emit_insn (gen_neon_vc (code, cmp_mode, target, op0, op1)); return inverted; /* These are natively supported for register operands only. @@ -31026,16 +31073,54 @@ arm_expand_vector_compare (rtx target, rtx_code code, rtx op0, rtx op1, or canonicalized by target-independent code. */ case GEU: case GTU: - emit_insn (gen_neon_vc (code, cmp_mode, target, - op0, force_reg (cmp_mode, op1))); + if (TARGET_HAVE_MVE) + { + rtx vpr_p0; + if (vcond_mve) + vpr_p0 = target; + else + vpr_p0 = gen_reg_rtx (HImode); + + emit_insn (gen_mve_vcmpq (code, cmp_mode, vpr_p0, op0, force_reg (cmp_mode, op1))); + if (!vcond_mve) + { + rtx zero = gen_reg_rtx (cmp_result_mode); + rtx one = gen_reg_rtx (cmp_result_mode); + emit_move_insn (zero, CONST0_RTX (cmp_result_mode)); + emit_move_insn (one, CONST1_RTX (cmp_result_mode)); + emit_insn (gen_mve_vpselq (VPSELQ_S, cmp_result_mode, target, one, zero, vpr_p0)); + } + } + else + emit_insn (gen_neon_vc (code, cmp_mode, target, + op0, force_reg (cmp_mode, op1))); return inverted; /* These require the operands to be swapped and likewise do not support comparisons with zero. */ case LEU: case LTU: - emit_insn (gen_neon_vc (swap_condition (code), cmp_mode, - target, force_reg (cmp_mode, op1), op0)); + if (TARGET_HAVE_MVE) + { + rtx vpr_p0; + if (vcond_mve) + vpr_p0 = target; + else + vpr_p0 = gen_reg_rtx (HImode); + + emit_insn (gen_mve_vcmpq (swap_condition (code), cmp_mode, vpr_p0, force_reg (cmp_mode, op1), op0)); + if (!vcond_mve) + { + rtx zero = gen_reg_rtx (cmp_result_mode); + rtx one = gen_reg_rtx (cmp_result_mode); + emit_move_insn (zero, CONST0_RTX (cmp_result_mode)); + emit_move_insn (one, CONST1_RTX (cmp_result_mode)); + emit_insn (gen_mve_vpselq (VPSELQ_S, cmp_result_mode, target, one, zero, vpr_p0)); + } + } + else + emit_insn (gen_neon_vc (swap_condition (code), cmp_mode, + target, force_reg (cmp_mode, op1), op0)); return inverted; /* These need a combination of two comparisons. */ @@ -31047,8 +31132,8 @@ arm_expand_vector_compare (rtx target, rtx_code code, rtx op0, rtx op1, rtx gt_res = gen_reg_rtx (cmp_result_mode); rtx alt_res = gen_reg_rtx (cmp_result_mode); rtx_code alt_code = (code == LTGT ? LT : LE); - if (arm_expand_vector_compare (gt_res, GT, op0, op1, true) - || arm_expand_vector_compare (alt_res, alt_code, op0, op1, true)) + if (arm_expand_vector_compare (gt_res, GT, op0, op1, true, vcond_mve) + || arm_expand_vector_compare (alt_res, alt_code, op0, op1, true, vcond_mve)) gcc_unreachable (); emit_insn (gen_rtx_SET (target, gen_rtx_IOR (cmp_result_mode, gt_res, alt_res))); @@ -31066,13 +31151,47 @@ arm_expand_vector_compare (rtx target, rtx_code code, rtx op0, rtx op1, void arm_expand_vcond (rtx *operands, machine_mode cmp_result_mode) { - rtx mask = gen_reg_rtx (cmp_result_mode); + /* When expanding for MVE, we do not want to emit a (useless) vpsel in + arm_expand_vector_compare, and another one here. */ + bool vcond_mve=false; + rtx mask; + + if (TARGET_HAVE_MVE) + { + vcond_mve=true; + mask = gen_reg_rtx (HImode); + } + else + mask = gen_reg_rtx (cmp_result_mode); + bool inverted = arm_expand_vector_compare (mask, GET_CODE (operands[3]), - operands[4], operands[5], true); + operands[4], operands[5], true, vcond_mve); if (inverted) std::swap (operands[1], operands[2]); + if (TARGET_NEON) emit_insn (gen_neon_vbsl (GET_MODE (operands[0]), operands[0], mask, operands[1], operands[2])); + else + { + machine_mode cmp_mode = GET_MODE (operands[4]); + rtx vpr_p0 = mask; + rtx zero = gen_reg_rtx (cmp_mode); + rtx one = gen_reg_rtx (cmp_mode); + emit_move_insn (zero, CONST0_RTX (cmp_mode)); + emit_move_insn (one, CONST1_RTX (cmp_mode)); + switch (GET_MODE_CLASS (cmp_mode)) + { + case MODE_VECTOR_INT: + emit_insn (gen_mve_vpselq (VPSELQ_S, cmp_result_mode, operands[0], one, zero, vpr_p0)); + break; + case MODE_VECTOR_FLOAT: + if (TARGET_HAVE_MVE_FLOAT) + emit_insn (gen_mve_vpselq_f (cmp_mode, operands[0], one, zero, vpr_p0)); + break; + default: + gcc_unreachable (); + } + } } #define MAX_VECT_LEN 16 diff --git a/gcc/config/arm/iterators.md b/gcc/config/arm/iterators.md index 95df8bd..a128465 100644 --- a/gcc/config/arm/iterators.md +++ b/gcc/config/arm/iterators.md @@ -1288,12 +1288,11 @@ (VCREATEQ_U "u") (VCREATEQ_S "s") (VSHRQ_N_S "s") (VSHRQ_N_U "u") (VCVTQ_N_FROM_F_S "s") (VSHLQ_U "u") (VCVTQ_N_FROM_F_U "u") (VADDLVQ_P_S "s") (VSHLQ_S "s") - (VADDLVQ_P_U "u") (VCMPNEQ_S "s") + (VADDLVQ_P_U "u") (VABDQ_M_S "s") (VABDQ_M_U "u") (VABDQ_S "s") (VABDQ_U "u") (VADDQ_N_S "s") (VADDQ_N_U "u") (VADDVQ_P_S "s") (VADDVQ_P_U "u") (VBRSRQ_N_S "s") - (VBRSRQ_N_U "u") (VCMPEQQ_S "s") - (VCMPEQQ_N_S "s") (VCMPNEQ_N_S "s") + (VBRSRQ_N_U "u") (VHADDQ_N_S "s") (VHADDQ_N_U "u") (VHADDQ_S "s") (VHADDQ_U "u") (VHSUBQ_N_S "s") (VHSUBQ_N_U "u") (VHSUBQ_S "s") (VMAXQ_S "s") (VMAXQ_U "u") (VHSUBQ_U "u") @@ -1549,16 +1548,12 @@ (define_int_iterator VSHRQ_N [VSHRQ_N_S VSHRQ_N_U]) (define_int_iterator VCVTQ_N_FROM_F [VCVTQ_N_FROM_F_S VCVTQ_N_FROM_F_U]) (define_int_iterator VADDLVQ_P [VADDLVQ_P_S VADDLVQ_P_U]) -(define_int_iterator VCMPNEQ [VCMPNEQ_S]) (define_int_iterator VSHLQ [VSHLQ_S VSHLQ_U]) (define_int_iterator VABDQ [VABDQ_S VABDQ_U]) (define_int_iterator VADDQ_N [VADDQ_N_S VADDQ_N_U]) (define_int_iterator VADDVAQ [VADDVAQ_S VADDVAQ_U]) (define_int_iterator VADDVQ_P [VADDVQ_P_U VADDVQ_P_S]) (define_int_iterator VBRSRQ_N [VBRSRQ_N_U VBRSRQ_N_S]) -(define_int_iterator VCMPEQQ [VCMPEQQ_S]) -(define_int_iterator VCMPEQQ_N [VCMPEQQ_N_S]) -(define_int_iterator VCMPNEQ_N [VCMPNEQ_N_S]) (define_int_iterator VHADDQ [VHADDQ_S VHADDQ_U]) (define_int_iterator VHADDQ_N [VHADDQ_N_U VHADDQ_N_S]) (define_int_iterator VHSUBQ [VHSUBQ_S VHSUBQ_U]) diff --git a/gcc/config/arm/mve.md b/gcc/config/arm/mve.md index 45df211..133ebe9 100644 --- a/gcc/config/arm/mve.md +++ b/gcc/config/arm/mve.md @@ -813,7 +813,7 @@ ;; ;; [vcmpneq_, vcmpcsq_, vcmpeqq_, vcmpgeq_, vcmpgtq_, vcmphiq_, vcmpleq_, vcmpltq_]) ;; -(define_insn "mve_vcmpq_" +(define_insn "@mve_vcmpq_" [ (set (match_operand:HI 0 "vpr_register_operand" "=Up") (MVE_COMPARISONS:HI (match_operand:MVE_2 1 "s_register_operand" "w") @@ -1903,7 +1903,7 @@ ;; ;; [vcmpeqq_f, vcmpgeq_f, vcmpgtq_f, vcmpleq_f, vcmpltq_f, vcmpneq_f]) ;; -(define_insn "mve_vcmpq_f" +(define_insn "@mve_vcmpq_f" [ (set (match_operand:HI 0 "vpr_register_operand" "=Up") (MVE_FP_COMPARISONS:HI (match_operand:MVE_0 1 "s_register_operand" "w") @@ -1917,7 +1917,7 @@ ;; ;; [vcmpeqq_n_f, vcmpgeq_n_f, vcmpgtq_n_f, vcmpleq_n_f, vcmpltq_n_f, vcmpneq_n_f]) ;; -(define_insn "mve_vcmpq_n_f" +(define_insn "@mve_vcmpq_n_f" [ (set (match_operand:HI 0 "vpr_register_operand" "=Up") (MVE_FP_COMPARISONS:HI (match_operand:MVE_0 1 "s_register_operand" "w") @@ -3282,7 +3282,7 @@ ;; ;; [vpselq_u, vpselq_s]) ;; -(define_insn "mve_vpselq_" +(define_insn "@mve_vpselq_" [ (set (match_operand:MVE_1 0 "s_register_operand" "=w") (unspec:MVE_1 [(match_operand:MVE_1 1 "s_register_operand" "w") @@ -4377,7 +4377,7 @@ ;; ;; [vpselq_f]) ;; -(define_insn "mve_vpselq_f" +(define_insn "@mve_vpselq_f" [ (set (match_operand:MVE_0 0 "s_register_operand" "=w") (unspec:MVE_0 [(match_operand:MVE_0 1 "s_register_operand" "w") diff --git a/gcc/config/arm/neon.md b/gcc/config/arm/neon.md index 641d26f..cc82d06 100644 --- a/gcc/config/arm/neon.md +++ b/gcc/config/arm/neon.md @@ -1416,93 +1416,6 @@ [(set_attr "type" "neon_qsub")] ) -(define_expand "vec_cmp" - [(set (match_operand: 0 "s_register_operand") - (match_operator: 1 "comparison_operator" - [(match_operand:VDQW 2 "s_register_operand") - (match_operand:VDQW 3 "reg_or_zero_operand")]))] - "TARGET_NEON && (! || flag_unsafe_math_optimizations)" -{ - arm_expand_vector_compare (operands[0], GET_CODE (operands[1]), - operands[2], operands[3], false); - DONE; -}) - -(define_expand "vec_cmpu" - [(set (match_operand:VDQIW 0 "s_register_operand") - (match_operator:VDQIW 1 "comparison_operator" - [(match_operand:VDQIW 2 "s_register_operand") - (match_operand:VDQIW 3 "reg_or_zero_operand")]))] - "TARGET_NEON" -{ - arm_expand_vector_compare (operands[0], GET_CODE (operands[1]), - operands[2], operands[3], false); - DONE; -}) - -;; Conditional instructions. These are comparisons with conditional moves for -;; vectors. They perform the assignment: -;; -;; Vop0 = (Vop4 Vop5) ? Vop1 : Vop2; -;; -;; where op3 is <, <=, ==, !=, >= or >. Operations are performed -;; element-wise. - -(define_expand "vcond" - [(set (match_operand:VDQW 0 "s_register_operand") - (if_then_else:VDQW - (match_operator 3 "comparison_operator" - [(match_operand:VDQW 4 "s_register_operand") - (match_operand:VDQW 5 "reg_or_zero_operand")]) - (match_operand:VDQW 1 "s_register_operand") - (match_operand:VDQW 2 "s_register_operand")))] - "TARGET_NEON && (! || flag_unsafe_math_optimizations)" -{ - arm_expand_vcond (operands, mode); - DONE; -}) - -(define_expand "vcond" - [(set (match_operand: 0 "s_register_operand") - (if_then_else: - (match_operator 3 "comparison_operator" - [(match_operand:V32 4 "s_register_operand") - (match_operand:V32 5 "reg_or_zero_operand")]) - (match_operand: 1 "s_register_operand") - (match_operand: 2 "s_register_operand")))] - "TARGET_NEON && (! || flag_unsafe_math_optimizations)" -{ - arm_expand_vcond (operands, mode); - DONE; -}) - -(define_expand "vcondu" - [(set (match_operand:VDQW 0 "s_register_operand") - (if_then_else:VDQW - (match_operator 3 "arm_comparison_operator" - [(match_operand: 4 "s_register_operand") - (match_operand: 5 "reg_or_zero_operand")]) - (match_operand:VDQW 1 "s_register_operand") - (match_operand:VDQW 2 "s_register_operand")))] - "TARGET_NEON" -{ - arm_expand_vcond (operands, mode); - DONE; -}) - -(define_expand "vcond_mask_" - [(set (match_operand:VDQW 0 "s_register_operand") - (if_then_else:VDQW - (match_operand: 3 "s_register_operand") - (match_operand:VDQW 1 "s_register_operand") - (match_operand:VDQW 2 "s_register_operand")))] - "TARGET_NEON" -{ - emit_insn (gen_neon_vbsl (operands[0], operands[3], operands[1], - operands[2])); - DONE; -}) - ;; Patterns for builtins. ; good for plain vadd, vaddq. diff --git a/gcc/config/arm/unspecs.md b/gcc/config/arm/unspecs.md index 07ca53b..0778db1 100644 --- a/gcc/config/arm/unspecs.md +++ b/gcc/config/arm/unspecs.md @@ -596,8 +596,6 @@ VCVTQ_N_FROM_F_U VADDLVQ_P_S VADDLVQ_P_U - VCMPNEQ_U - VCMPNEQ_S VSHLQ_S VSHLQ_U VABDQ_S @@ -605,9 +603,6 @@ VADDVAQ_S VADDVQ_P_S VBRSRQ_N_S - VCMPEQQ_S - VCMPEQQ_N_S - VCMPNEQ_N_S VHADDQ_S VHADDQ_N_S VHSUBQ_S @@ -645,9 +640,6 @@ VADDVAQ_U VADDVQ_P_U VBRSRQ_N_U - VCMPEQQ_U - VCMPEQQ_N_U - VCMPNEQ_N_U VHADDQ_U VHADDQ_N_U VHSUBQ_U @@ -680,14 +672,6 @@ VSHLQ_R_U VSUBQ_U VSUBQ_N_U - VCMPGEQ_N_S - VCMPGEQ_S - VCMPGTQ_N_S - VCMPGTQ_S - VCMPLEQ_N_S - VCMPLEQ_S - VCMPLTQ_N_S - VCMPLTQ_S VHCADDQ_ROT270_S VHCADDQ_ROT90_S VMAXAQ_S @@ -702,10 +686,6 @@ VQRDMULHQ_N_S VQRDMULHQ_S VQSHLUQ_N_S - VCMPCSQ_N_U - VCMPCSQ_U - VCMPHIQ_N_U - VCMPHIQ_U VABDQ_M_S VABDQ_M_U VABDQ_F diff --git a/gcc/config/arm/vec-common.md b/gcc/config/arm/vec-common.md index 0b2b3b1..448731f 100644 --- a/gcc/config/arm/vec-common.md +++ b/gcc/config/arm/vec-common.md @@ -362,3 +362,111 @@ DONE; } }) + +(define_expand "vec_cmp" + [(set (match_operand: 0 "s_register_operand") + (match_operator: 1 "comparison_operator" + [(match_operand:VDQW 2 "s_register_operand") + (match_operand:VDQW 3 "reg_or_zero_operand")]))] + "ARM_HAVE__ARITH + && !TARGET_REALLY_IWMMXT + && (! || flag_unsafe_math_optimizations)" +{ + arm_expand_vector_compare (operands[0], GET_CODE (operands[1]), + operands[2], operands[3], false, false); + DONE; +}) + +(define_expand "vec_cmpu" + [(set (match_operand:VDQIW 0 "s_register_operand") + (match_operator:VDQIW 1 "comparison_operator" + [(match_operand:VDQIW 2 "s_register_operand") + (match_operand:VDQIW 3 "reg_or_zero_operand")]))] + "ARM_HAVE__ARITH + && !TARGET_REALLY_IWMMXT" +{ + arm_expand_vector_compare (operands[0], GET_CODE (operands[1]), + operands[2], operands[3], false, false); + DONE; +}) + +;; Conditional instructions. These are comparisons with conditional moves for +;; vectors. They perform the assignment: +;; +;; Vop0 = (Vop4 Vop5) ? Vop1 : Vop2; +;; +;; where op3 is <, <=, ==, !=, >= or >. Operations are performed +;; element-wise. + +(define_expand "vcond" + [(set (match_operand:VDQW 0 "s_register_operand") + (if_then_else:VDQW + (match_operator 3 "comparison_operator" + [(match_operand:VDQW 4 "s_register_operand") + (match_operand:VDQW 5 "reg_or_zero_operand")]) + (match_operand:VDQW 1 "s_register_operand") + (match_operand:VDQW 2 "s_register_operand")))] + "ARM_HAVE__ARITH + && !TARGET_REALLY_IWMMXT + && (! || flag_unsafe_math_optimizations)" +{ + arm_expand_vcond (operands, mode); + DONE; +}) + +(define_expand "vcond" + [(set (match_operand: 0 "s_register_operand") + (if_then_else: + (match_operator 3 "comparison_operator" + [(match_operand:V32 4 "s_register_operand") + (match_operand:V32 5 "reg_or_zero_operand")]) + (match_operand: 1 "s_register_operand") + (match_operand: 2 "s_register_operand")))] + "ARM_HAVE__ARITH + && !TARGET_REALLY_IWMMXT + && (! || flag_unsafe_math_optimizations)" +{ + arm_expand_vcond (operands, mode); + DONE; +}) + +(define_expand "vcondu" + [(set (match_operand:VDQW 0 "s_register_operand") + (if_then_else:VDQW + (match_operator 3 "arm_comparison_operator" + [(match_operand: 4 "s_register_operand") + (match_operand: 5 "reg_or_zero_operand")]) + (match_operand:VDQW 1 "s_register_operand") + (match_operand:VDQW 2 "s_register_operand")))] + "ARM_HAVE__ARITH + && !TARGET_REALLY_IWMMXT" +{ + arm_expand_vcond (operands, mode); + DONE; +}) + +(define_expand "vcond_mask_" + [(set (match_operand:VDQW 0 "s_register_operand") + (if_then_else:VDQW + (match_operand: 3 "s_register_operand") + (match_operand:VDQW 1 "s_register_operand") + (match_operand:VDQW 2 "s_register_operand")))] + "ARM_HAVE__ARITH + && !TARGET_REALLY_IWMMXT + && (! || flag_unsafe_math_optimizations)" +{ + if (TARGET_NEON) + { + emit_insn (gen_neon_vbsl (mode, operands[0], operands[3], + operands[1], operands[2])); + } + else if (TARGET_HAVE_MVE) + { + emit_insn (gen_mve_vpselq (VPSELQ_S, mode, operands[0], + operands[1], operands[2], operands[3])); + } + else + gcc_unreachable (); + + DONE; +}) diff --git a/gcc/testsuite/gcc.target/arm/simd/mve-compare-1.c b/gcc/testsuite/gcc.target/arm/simd/mve-compare-1.c new file mode 100644 index 0000000..029c931 --- /dev/null +++ b/gcc/testsuite/gcc.target/arm/simd/mve-compare-1.c @@ -0,0 +1,80 @@ +/* { dg-do assemble } */ +/* { dg-require-effective-target arm_v8_1m_mve_ok } */ +/* { dg-add-options arm_v8_1m_mve } */ +/* { dg-additional-options "-O3" } */ + +/* Integer tests. */ + +#define COMPARE_REG(NAME, OP, TYPE) \ + TYPE \ + cmp_##NAME##_##TYPE##_reg (TYPE a, TYPE b) \ + { \ + return a OP b; \ + } + +#define COMPARE_REG_AND_ZERO(NAME, OP, TYPE) \ + COMPARE_REG (NAME, OP, TYPE) \ + \ + TYPE \ + cmp_##NAME##_##TYPE##_zero (TYPE a) \ + { \ + return a OP (TYPE) {}; \ + } + +#define COMPARE_TYPE(TYPE, COMPARE_ORDERED) \ + COMPARE_REG_AND_ZERO (eq, ==, TYPE) \ + COMPARE_REG_AND_ZERO (ne, !=, TYPE) \ + COMPARE_ORDERED (lt, <, TYPE) \ + COMPARE_ORDERED (le, <=, TYPE) \ + COMPARE_ORDERED (gt, >, TYPE) \ + COMPARE_ORDERED (ge, >=, TYPE) + +#define TEST_TYPE(NAME, ELEM, COMPARE_ORDERED, SIZE) \ + typedef ELEM NAME##SIZE __attribute__((vector_size(SIZE))); \ + COMPARE_TYPE (NAME##SIZE, COMPARE_ORDERED) + +/* 64-bits vectors, not vectorized. */ +TEST_TYPE (vs8, __INT8_TYPE__, COMPARE_REG_AND_ZERO, 8) +TEST_TYPE (vu8, __UINT8_TYPE__, COMPARE_REG, 8) +TEST_TYPE (vs16, __INT16_TYPE__, COMPARE_REG_AND_ZERO, 8) +TEST_TYPE (vu16, __UINT16_TYPE__, COMPARE_REG, 8) +TEST_TYPE (vs32, __INT32_TYPE__, COMPARE_REG_AND_ZERO, 8) +TEST_TYPE (vu32, __UINT32_TYPE__, COMPARE_REG, 8) + +/* 128-bits vectors. */ +TEST_TYPE (vs8, __INT8_TYPE__, COMPARE_REG_AND_ZERO, 16) +TEST_TYPE (vu8, __UINT8_TYPE__, COMPARE_REG, 16) +TEST_TYPE (vs16, __INT16_TYPE__, COMPARE_REG_AND_ZERO, 16) +TEST_TYPE (vu16, __UINT16_TYPE__, COMPARE_REG, 16) +TEST_TYPE (vs32, __INT32_TYPE__, COMPARE_REG_AND_ZERO, 16) +TEST_TYPE (vu32, __UINT32_TYPE__, COMPARE_REG, 16) + +/* { 8 bits } x { eq, ne, lt, le, gt, ge, hi, cs }. +/* { dg-final { scan-assembler-times {\tvcmp.i8 eq, q[0-9]+, q[0-9]+\n} 4 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.i8 ne, q[0-9]+, q[0-9]+\n} 4 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.s8 lt, q[0-9]+, q[0-9]+\n} 2 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.s8 le, q[0-9]+, q[0-9]+\n} 2 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.s8 gt, q[0-9]+, q[0-9]+\n} 2 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.s8 ge, q[0-9]+, q[0-9]+\n} 2 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.u8 hi, q[0-9]+, q[0-9]+\n} 2 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.u8 cs, q[0-9]+, q[0-9]+\n} 2 } } */ + +/* { 16 bits } x { eq, ne, lt, le, gt, ge, hi, cs }. +/* { dg-final { scan-assembler-times {\tvcmp.i16 eq, q[0-9]+, q[0-9]+\n} 4 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.i16 ne, q[0-9]+, q[0-9]+\n} 4 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.s16 lt, q[0-9]+, q[0-9]+\n} 2 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.s16 le, q[0-9]+, q[0-9]+\n} 2 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.s16 gt, q[0-9]+, q[0-9]+\n} 2 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.s16 ge, q[0-9]+, q[0-9]+\n} 2 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.u16 hi, q[0-9]+, q[0-9]+\n} 2 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.u16 cs, q[0-9]+, q[0-9]+\n} 2 } } */ + +/* { 32 bits } x { eq, ne, lt, le, gt, ge, hi, cs }. +/* { dg-final { scan-assembler-times {\tvcmp.i32 eq, q[0-9]+, q[0-9]+\n} 4 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.i32 ne, q[0-9]+, q[0-9]+\n} 4 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.s32 lt, q[0-9]+, q[0-9]+\n} 2 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.s32 le, q[0-9]+, q[0-9]+\n} 2 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.s32 gt, q[0-9]+, q[0-9]+\n} 2 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.s32 ge, q[0-9]+, q[0-9]+\n} 2 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.u32 hi, q[0-9]+, q[0-9]+\n} 2 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.u32 cs, q[0-9]+, q[0-9]+\n} 2 } } */ diff --git a/gcc/testsuite/gcc.target/arm/simd/mve-compare-2.c b/gcc/testsuite/gcc.target/arm/simd/mve-compare-2.c new file mode 100644 index 0000000..8515195 --- /dev/null +++ b/gcc/testsuite/gcc.target/arm/simd/mve-compare-2.c @@ -0,0 +1,38 @@ +/* { dg-do assemble } */ +/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */ +/* { dg-add-options arm_v8_1m_mve_fp } */ +/* { dg-additional-options "-O3 -funsafe-math-optimizations" } */ + +/* float 32 tests. */ + +#ifndef ELEM_TYPE +#define ELEM_TYPE float +#endif +#ifndef INT_ELEM_TYPE +#define INT_ELEM_TYPE __INT32_TYPE__ +#endif + +#define COMPARE(NAME, OP) \ + int_vec \ + cmp_##NAME##_reg (vec a, vec b) \ + { \ + return a OP b; \ + } + +typedef INT_ELEM_TYPE int_vec __attribute__((vector_size(16))); +typedef ELEM_TYPE vec __attribute__((vector_size(16))); + +COMPARE (eq, ==) +COMPARE (ne, !=) +COMPARE (lt, <) +COMPARE (le, <=) +COMPARE (gt, >) +COMPARE (ge, >=) + +/* eq, ne, lt, le, gt, ge. +/* { dg-final { scan-assembler-times {\tvcmp.f32\teq, q[0-9]+, q[0-9]+\n} 1 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.f32\tne, q[0-9]+, q[0-9]+\n} 1 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.f32\tlt, q[0-9]+, q[0-9]+\n} 1 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.f32\tle, q[0-9]+, q[0-9]+\n} 1 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.f32\tgt, q[0-9]+, q[0-9]+\n} 1 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.f32\tge, q[0-9]+, q[0-9]+\n} 1 } } */ diff --git a/gcc/testsuite/gcc.target/arm/simd/mve-compare-scalar-1.c b/gcc/testsuite/gcc.target/arm/simd/mve-compare-scalar-1.c new file mode 100644 index 0000000..7774972 --- /dev/null +++ b/gcc/testsuite/gcc.target/arm/simd/mve-compare-scalar-1.c @@ -0,0 +1,69 @@ +/* { dg-do assemble } */ +/* { dg-require-effective-target arm_v8_1m_mve_ok } */ +/* { dg-add-options arm_v8_1m_mve } */ +/* { dg-additional-options "-O3" } */ + +#define COMPARE_REG(NAME, OP, TYPE, SCALAR) \ + TYPE \ + cmp_##NAME##_##TYPE##_scalar (TYPE a, SCALAR b) \ + { \ + return a OP b; \ + } + +#define COMPARE_TYPE(SCALAR, TYPE) \ + COMPARE_REG (eq, ==, TYPE, SCALAR) \ + COMPARE_REG (ne, !=, TYPE, SCALAR) \ + COMPARE_REG (lt, <, TYPE, SCALAR) \ + COMPARE_REG (le, <=, TYPE, SCALAR) \ + COMPARE_REG (gt, >, TYPE, SCALAR) \ + COMPARE_REG (ge, >=, TYPE, SCALAR) + +#define TEST_TYPE(NAME, ELEM, SIZE) \ + typedef ELEM NAME##SIZE __attribute__((vector_size(SIZE))); \ + COMPARE_TYPE (ELEM, NAME##SIZE) + +/* 64-bits vectors, not vectorized. */ +TEST_TYPE (vs8, __INT8_TYPE__, 8) +TEST_TYPE (vu8, __UINT8_TYPE__, 8) +TEST_TYPE (vs16, __INT16_TYPE__, 8) +TEST_TYPE (vu16, __UINT16_TYPE__, 8) +TEST_TYPE (vs32, __INT32_TYPE__, 8) +TEST_TYPE (vu32, __UINT32_TYPE__, 8) + +/* 128-bits vectors. */ +TEST_TYPE (vs8, __INT8_TYPE__, 16) +TEST_TYPE (vu8, __UINT8_TYPE__, 16) +TEST_TYPE (vs16, __INT16_TYPE__, 16) +TEST_TYPE (vu16, __UINT16_TYPE__, 16) +TEST_TYPE (vs32, __INT32_TYPE__, 16) +TEST_TYPE (vu32, __UINT32_TYPE__, 16) + +/* { 8 bits } x { eq, ne, lt, le, gt, ge, hi, cs }. +/* { dg-final { scan-assembler-times {\tvcmp.i8 eq, q[0-9]+, q[0-9]+\n} 2 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.i8 ne, q[0-9]+, q[0-9]+\n} 2 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.s8 lt, q[0-9]+, q[0-9]+\n} 1 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.s8 le, q[0-9]+, q[0-9]+\n} 1 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.s8 gt, q[0-9]+, q[0-9]+\n} 1 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.s8 ge, q[0-9]+, q[0-9]+\n} 1 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.u8 hi, q[0-9]+, q[0-9]+\n} 2 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.u8 cs, q[0-9]+, q[0-9]+\n} 2 } } */ + +/* { 16 bits } x { eq, ne, lt, le, gt, ge, hi, cs }. +/* { dg-final { scan-assembler-times {\tvcmp.i16 eq, q[0-9]+, q[0-9]+\n} 2 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.i16 ne, q[0-9]+, q[0-9]+\n} 2 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.s16 lt, q[0-9]+, q[0-9]+\n} 1 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.s16 le, q[0-9]+, q[0-9]+\n} 1 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.s16 gt, q[0-9]+, q[0-9]+\n} 1 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.s16 ge, q[0-9]+, q[0-9]+\n} 1 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.u16 hi, q[0-9]+, q[0-9]+\n} 2 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.u16 cs, q[0-9]+, q[0-9]+\n} 2 } } */ + +/* { 32 bits } x { eq, ne, lt, le, gt, ge, hi, cs }. +/* { dg-final { scan-assembler-times {\tvcmp.i32 eq, q[0-9]+, q[0-9]+\n} 2 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.i32 ne, q[0-9]+, q[0-9]+\n} 2 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.s32 lt, q[0-9]+, q[0-9]+\n} 1 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.s32 le, q[0-9]+, q[0-9]+\n} 1 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.s32 gt, q[0-9]+, q[0-9]+\n} 1 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.s32 ge, q[0-9]+, q[0-9]+\n} 1 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.u32 hi, q[0-9]+, q[0-9]+\n} 2 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.u32 cs, q[0-9]+, q[0-9]+\n} 2 } } */ diff --git a/gcc/testsuite/gcc.target/arm/simd/mve-vcmp-f32.c b/gcc/testsuite/gcc.target/arm/simd/mve-vcmp-f32.c new file mode 100644 index 0000000..4ed449e --- /dev/null +++ b/gcc/testsuite/gcc.target/arm/simd/mve-vcmp-f32.c @@ -0,0 +1,30 @@ +/* { dg-do assemble } */ +/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */ +/* { dg-add-options arm_v8_1m_mve_fp } */ +/* { dg-additional-options "-O3 -funsafe-math-optimizations" } */ + +#include + +#define NB 4 + +#define FUNC(OP, NAME) \ + void test_ ## NAME ##_f (float * __restrict__ dest, float *a, float *b) { \ + int i; \ + for (i=0; i, vcmpgt) +FUNC(>=, vcmpge) + +/* { dg-final { scan-assembler-times {\tvcmp.f32\teq, q[0-9]+, q[0-9]+\n} 1 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.f32\tne, q[0-9]+, q[0-9]+\n} 1 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.f32\tlt, q[0-9]+, q[0-9]+\n} 1 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.f32\tle, q[0-9]+, q[0-9]+\n} 1 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.f32\tgt, q[0-9]+, q[0-9]+\n} 1 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.f32\tge, q[0-9]+, q[0-9]+\n} 1 } } */ diff --git a/gcc/testsuite/gcc.target/arm/simd/mve-vcmp.c b/gcc/testsuite/gcc.target/arm/simd/mve-vcmp.c new file mode 100644 index 0000000..8da15e7 --- /dev/null +++ b/gcc/testsuite/gcc.target/arm/simd/mve-vcmp.c @@ -0,0 +1,50 @@ +/* { dg-do assemble } */ +/* { dg-require-effective-target arm_v8_1m_mve_ok } */ +/* { dg-add-options arm_v8_1m_mve } */ +/* { dg-additional-options "-O3" } */ + +#include + +#define FUNC(SIGN, TYPE, BITS, NB, OP, NAME) \ + void test_ ## NAME ##_ ## SIGN ## BITS ## x ## NB (TYPE##BITS##_t * __restrict__ dest, TYPE##BITS##_t *a, TYPE##BITS##_t *b) { \ + int i; \ + for (i=0; i, vcmpgt) +ALL_FUNCS(>=, vcmpge) + +/* MVE has only 128-bit vectors, so we can vectorize only half of the + functions above. */ +/* { dg-final { scan-assembler-times {\tvcmp.i[0-9]+ eq, q[0-9]+, q[0-9]+\n} 6 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.i[0-9]+ ne, q[0-9]+, q[0-9]+\n} 6 } } */ + +/* lt, le, gt, ge apply to signed types, cs and hi to unsigned types. */ +/* lt and le with unsigned types are replaced with the opposite condition, hence + the double number of matches for cs and hi. */ +/* { dg-final { scan-assembler-times {\tvcmp.s[0-9]+ lt, q[0-9]+, q[0-9]+\n} 3 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.s[0-9]+ le, q[0-9]+, q[0-9]+\n} 3 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.s[0-9]+ gt, q[0-9]+, q[0-9]+\n} 3 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.s[0-9]+ ge, q[0-9]+, q[0-9]+\n} 3 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.u[0-9]+ cs, q[0-9]+, q[0-9]+\n} 6 } } */ +/* { dg-final { scan-assembler-times {\tvcmp.u[0-9]+ hi, q[0-9]+, q[0-9]+\n} 6 } } */ -- 2.7.4