From: Charles Baylis Date: Wed, 11 Nov 2015 01:05:16 +0000 (+0000) Subject: [ARM] PR63870 Add qualifiers for NEON builtins X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=2f7d18ddd7f99fc8a67f13a2d97c1305bdcd05cc;p=gcc.git [ARM] PR63870 Add qualifiers for NEON builtins 2015-11-11 Charles Baylis PR target/63870 * config/arm/arm-builtins.c (enum arm_type_qualifiers): New enumerator qualifier_struct_load_store_lane_index. (builtin_arg): New enumerator NEON_ARG_STRUCT_LOAD_STORE_LANE_INDEX. (arm_expand_neon_args): New parameter. Remove ellipsis. Handle NEON argument qualifiers. (arm_expand_neon_builtin): Handle new NEON argument qualifier. * config/arm/arm.h (NEON_ENDIAN_LANE_N): New macro. From-SVN: r230142 --- diff --git a/gcc/ChangeLog b/gcc/ChangeLog index a1d54b05e73..90ab5853c08 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -1,3 +1,14 @@ +2015-11-11 Charles Baylis + + PR target/63870 + * config/arm/arm-builtins.c (enum arm_type_qualifiers): New enumerator + qualifier_struct_load_store_lane_index. + (builtin_arg): New enumerator NEON_ARG_STRUCT_LOAD_STORE_LANE_INDEX. + (arm_expand_neon_args): New parameter. Remove ellipsis. Handle NEON + argument qualifiers. + (arm_expand_neon_builtin): Handle new NEON argument qualifier. + * config/arm/arm.h (NEON_ENDIAN_LANE_N): New macro. + 2015-11-10 Nathan Sidwell * config/nvptx/nvptx.opt (moptimize): New flag. diff --git a/gcc/config/arm/arm-builtins.c b/gcc/config/arm/arm-builtins.c index bad3dc381a1..d0bd7775704 100644 --- a/gcc/config/arm/arm-builtins.c +++ b/gcc/config/arm/arm-builtins.c @@ -67,7 +67,9 @@ enum arm_type_qualifiers /* Polynomial types. */ qualifier_poly = 0x100, /* Lane indices - must be within range of previous argument = a vector. */ - qualifier_lane_index = 0x200 + qualifier_lane_index = 0x200, + /* Lane indices for single lane structure loads and stores. */ + qualifier_struct_load_store_lane_index = 0x400 }; /* The qualifier_internal allows generation of a unary builtin from @@ -1963,6 +1965,7 @@ typedef enum { NEON_ARG_COPY_TO_REG, NEON_ARG_CONSTANT, NEON_ARG_LANE_INDEX, + NEON_ARG_STRUCT_LOAD_STORE_LANE_INDEX, NEON_ARG_MEMORY, NEON_ARG_STOP } builtin_arg; @@ -2020,9 +2023,9 @@ neon_dereference_pointer (tree exp, tree type, machine_mode mem_mode, /* Expand a Neon builtin. */ static rtx arm_expand_neon_args (rtx target, machine_mode map_mode, int fcode, - int icode, int have_retval, tree exp, ...) + int icode, int have_retval, tree exp, + builtin_arg *args) { - va_list ap; rtx pat; tree arg[SIMD_MAX_BUILTIN_ARGS]; rtx op[SIMD_MAX_BUILTIN_ARGS]; @@ -2037,13 +2040,11 @@ arm_expand_neon_args (rtx target, machine_mode map_mode, int fcode, || !(*insn_data[icode].operand[0].predicate) (target, tmode))) target = gen_reg_rtx (tmode); - va_start (ap, exp); - formals = TYPE_ARG_TYPES (TREE_TYPE (arm_builtin_decls[fcode])); for (;;) { - builtin_arg thisarg = (builtin_arg) va_arg (ap, int); + builtin_arg thisarg = args[argc]; if (thisarg == NEON_ARG_STOP) break; @@ -2079,6 +2080,18 @@ arm_expand_neon_args (rtx target, machine_mode map_mode, int fcode, op[argc] = copy_to_mode_reg (mode[argc], op[argc]); break; + case NEON_ARG_STRUCT_LOAD_STORE_LANE_INDEX: + gcc_assert (argc > 1); + if (CONST_INT_P (op[argc])) + { + neon_lane_bounds (op[argc], 0, + GET_MODE_NUNITS (map_mode), exp); + /* Keep to GCC-vector-extension lane indices in the RTL. */ + op[argc] = + GEN_INT (NEON_ENDIAN_LANE_N (map_mode, INTVAL (op[argc]))); + } + goto constant_arg; + case NEON_ARG_LANE_INDEX: /* Previous argument must be a vector, which this indexes. */ gcc_assert (argc > 0); @@ -2089,19 +2102,22 @@ arm_expand_neon_args (rtx target, machine_mode map_mode, int fcode, } /* Fall through - if the lane index isn't a constant then the next case will error. */ + case NEON_ARG_CONSTANT: +constant_arg: if (!(*insn_data[icode].operand[opno].predicate) (op[argc], mode[argc])) - error_at (EXPR_LOCATION (exp), "incompatible type for argument %d, " - "expected %", argc + 1); + { + error ("%Kargument %d must be a constant immediate", + exp, argc + 1); + return const0_rtx; + } break; + case NEON_ARG_MEMORY: /* Check if expand failed. */ if (op[argc] == const0_rtx) - { - va_end (ap); return 0; - } gcc_assert (MEM_P (op[argc])); PUT_MODE (op[argc], mode[argc]); /* ??? arm_neon.h uses the same built-in functions for signed @@ -2122,8 +2138,6 @@ arm_expand_neon_args (rtx target, machine_mode map_mode, int fcode, } } - va_end (ap); - if (have_retval) switch (argc) { @@ -2235,6 +2249,8 @@ arm_expand_neon_builtin (int fcode, tree exp, rtx target) if (d->qualifiers[qualifiers_k] & qualifier_lane_index) args[k] = NEON_ARG_LANE_INDEX; + else if (d->qualifiers[qualifiers_k] & qualifier_struct_load_store_lane_index) + args[k] = NEON_ARG_STRUCT_LOAD_STORE_LANE_INDEX; else if (d->qualifiers[qualifiers_k] & qualifier_immediate) args[k] = NEON_ARG_CONSTANT; else if (d->qualifiers[qualifiers_k] & qualifier_maybe_immediate) @@ -2260,11 +2276,7 @@ arm_expand_neon_builtin (int fcode, tree exp, rtx target) the function is void, and a 1 if it is not. */ return arm_expand_neon_args (target, d->mode, fcode, icode, !is_void, exp, - args[1], - args[2], - args[3], - args[4], - NEON_ARG_STOP); + &args[1]); } /* Expand an expression EXP that calls a built-in function, diff --git a/gcc/config/arm/arm.c b/gcc/config/arm/arm.c index 736e6c8f025..59034b55f25 100644 --- a/gcc/config/arm/arm.c +++ b/gcc/config/arm/arm.c @@ -30103,4 +30103,5 @@ arm_sched_fusion_priority (rtx_insn *insn, int max_pri, *pri = tmp; return; } + #include "gt-arm.h" diff --git a/gcc/config/arm/arm.h b/gcc/config/arm/arm.h index a1a04a94ef2..313fed5b450 100644 --- a/gcc/config/arm/arm.h +++ b/gcc/config/arm/arm.h @@ -284,6 +284,12 @@ extern void (*arm_lang_output_object_attributes_hook)(void); #define TARGET_BPABI false #endif +/* Transform lane numbers on big endian targets. This is used to allow for the + endianness difference between NEON architectural lane numbers and those + used in RTL */ +#define NEON_ENDIAN_LANE_N(mode, n) \ + (BYTES_BIG_ENDIAN ? GET_MODE_NUNITS (mode) - 1 - n : n) + /* Support for a compile-time default CPU, et cetera. The rules are: --with-arch is ignored if -march or -mcpu are specified. --with-cpu is ignored if -march or -mcpu are specified, and is overridden