diff options
author | dorit <dorit@138bc75d-0d04-0410-961f-82ee72b054a4> | 2004-09-23 14:34:35 +0000 |
---|---|---|
committer | dorit <dorit@138bc75d-0d04-0410-961f-82ee72b054a4> | 2004-09-23 14:34:35 +0000 |
commit | b056d8127419206eaa5c4eb583f3eb70804ea922 (patch) | |
tree | 5b0812849a44aab255ae7d9ac2f99b6111c1359c /gcc/config/rs6000/altivec.md | |
parent | b974179016bff8e2c129e3a6c9d76fde3a9dd450 (diff) | |
download | gcc-b056d8127419206eaa5c4eb583f3eb70804ea922.tar.gz |
2004-09-23 Dorit Naishlos <dorit@il.ibm.com>
* tree.def (ALIGN_INDIRECT_REF, MISALIGNED_INDIRECT_REF):
New tree-codes.
* tree.h (REF_ORIGINAL): Consider ALIGN_INDIRECT_REF and
MISALIGNED_INDIRECT_REF.
* alias.c (get_alias_set, nonoverlapping_memrefs_p): Likewise.
* emit-rtl.c (mem_expr_equal_p, set_mem_attributes_minus_bitpos):
Likewise.
* expr.c (safe_from_p, expand_expr_real_1, rewrite_address_base)
(find_interesting_uses_address): Likewise.
* fold-const.c (non_lvalue, operand_equal_p): Likewise.
(build_fold_addr_expr_with_type): Likewise.
* gimplify.c (gimplify_addr_expr, gimplify_expr): Likewise.
* print-rtl.c (print_mem_expr): Likewise.
* tree-dump.c (dequeue_and_dump): Likewise.
* tree-eh.c (tree_could_trap_p): Likewise.
* tree-gimple.c (is_gimple_addressable, get_base_address): Likewise.
* tree-pretty-print.c (op_prio, op_symbol, dump_generic_node): Likewise.
* tree-ssa-alias.c (find_ptr_dereference, ptr_is_dereferenced_by):
Likewise.
* tree-ssa-dce.c (mark_stmt_if_obviously_necessary): Likewise.
* tree-ssa-dom.c (record_equivalences_from_stmt): Likewise.
* tree-ssa-loop-im.c (for_each_index, is_call_clobbered_ref): Likewise.
* tree-ssa-loop-ivopts.c (find_interesting_uses_address): Likewise.
(add_address_candidates, rewrite_address_base): Likewise.
* tree-ssa-operands.c (get_expr_operands, get_indirect_ref_operands):
Likewise.
* tree.c (staticp, build1_stat): Likewise.
* tree.def (REALIGN_LOAD_EXPR, REALIGN_STORE_EXPR): New tree-codes.
* tree-pretty-print.c (dump_generic_node): Consider REALIGN_LOAD_EXPR.
* tree-ssa-operands.c (get_expr_operands): Likewise.
* expr.c (expand_expr_real_1): Likewise.
* optabs.h (vec_realign_store_optab, vec_realign_load_optab): New
optabs.
(OTI_vec_realign_store, OTI_vec_realign_load): New optab_index values
for the new optabs.
(expand_ternary_op): New function.
* genopinit.c (optabs): Handle the new optabs.
* optabs.c (optab_for_tree_code): Add cases for the new tree-codes.
(init_optabs): Initialize vec_realign_load_optab.
(expand_ternary_op): New functions.
* target-def.h (TARGET_VECTORIZE): New member for struct gcc_target.
(TARGET_VECTORIZE_MISALIGNED_MEM_OK): New member for targetm.vectorize.
(TARGET_VECTORIZE_BUILTIN_MASK_FOR_LOAD): Likewise.
(TARGET_VECTORIZE_BUILTIN_MASK_FOR_STORE): Likewise.
* target.h (struct vectorize): New member for struct gcc_target.
(misaligned_mem_ok): New member for targetm.vectorize.
(builtin_mask_for_load): Likewise.
(builtin_mask_for_store): Likewise.
* targethooks.c (default_vect_misaligned_mem_ok): New function.
* targethooks.h (default_vect_misaligned_mem_ok): New function.
* config/rs6000/altivec.md (build_vector_mask_for_load): New
define_expand.
(vec_realign_load_v4si, vec_realign_load_v4sf, vec_realign_load_v8hi)
(vec_realign_load_v16qi): New define_insn.
* config/rs6000/rs6000.h (ALTIVEC_BUILTIN_MASK_FOR_LOAD):
(ALTIVEC_BUILTIN_MASK_FOR_STORE): New target builtins.
* config/rs6000/rs6000.c (altivec_builtin_mask_for_load):
(altivec_builtin_mask_for_store): New variables.
(rs6000_builtin_mask_for_load): New function. Implements
TARGET_VECTORIZE_BUILTIN_MASK_FOR_LOAD.
(rs6000_builtin_mask_for_store): New function. Implements
TARGET_VECTORIZE_BUILTIN_MASK_FOR_STORE.
(rs6000_expand_builtin): Expand the target builtins
builtin_mask_for_load and builtin_mask_for_store.
(altivec_init_builtins): Initialize the new target builtins.
* config/i386/i386.c (ix86_misaligned_mem_ok): New function.
Implements the target hook TARGET_VECTORIZE_MISALIGNED_MEM_OK.
* tree-vectorizer.c (vect_create_data_ref): Renamed to
vect_create_data_ref_ptr. Returns a pointer instead of an array-ref.
(vect_create_addr_base_for_vector_ref): Additional argument (offset).
(vectorizable_store): Call vect_create_data_ref_ptr with additional
arguments, and create an indirect_ref with its return value data_ref.
Check aligned_access_p.
(vectorizable_load): Handle misaligned loads, using software-pipelined
scheme with REALIGN_LOAD_EXPR and ALIGN_INDIRECT_REF if
vec_realign_load_optab is supported, or using a scheme without
software-pipelining with MISALIGNED_INDIRECT_REF if the target hook
misaligned_mem_ok is supported.
(vect_finish_stmt_generation): Typo.
(vect_enhance_data_refs_alignment): Rename loop_vinfo to loop_info.
(vect_analyze_data_refs_alignment): Don't fail vectorization in the
presence of misaligned loads.
(vect_analyze_data_ref_access): Add check for constant init.
(vect_get_symbl_and_dr): Remove duplicate line.
* tree-vectorizer.h (DR_MISALIGNMENT): Add comment.
git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@87948 138bc75d-0d04-0410-961f-82ee72b054a4
Diffstat (limited to 'gcc/config/rs6000/altivec.md')
-rw-r--r-- | gcc/config/rs6000/altivec.md | 58 |
1 files changed, 58 insertions, 0 deletions
diff --git a/gcc/config/rs6000/altivec.md b/gcc/config/rs6000/altivec.md index ff58d8e3fa8..0eb29b1ea37 100644 --- a/gcc/config/rs6000/altivec.md +++ b/gcc/config/rs6000/altivec.md @@ -1902,6 +1902,27 @@ "lvsr %0,%y1" [(set_attr "type" "vecload")]) +(define_expand "build_vector_mask_for_load" + [(set (match_operand:V16QI 0 "register_operand" "=v") + (unspec:V16QI [(match_operand 1 "memory_operand" "m")] 195))] + "TARGET_ALTIVEC" + " +{ + rtx addr; + rtx temp; + + if (GET_CODE (operands[1]) != MEM) + abort (); + + addr = XEXP (operands[1], 0); + temp = gen_reg_rtx (GET_MODE (addr)); + emit_insn (gen_rtx_SET (VOIDmode, temp, + gen_rtx_NEG (GET_MODE (addr), addr))); + emit_insn (gen_altivec_lvsr (operands[0], + gen_rtx_MEM (GET_MODE (operands[1]), temp))); + DONE; +}") + ;; Parallel some of the LVE* and STV*'s with unspecs because some have ;; identical rtl but different instructions-- and gcc gets confused. @@ -2062,3 +2083,40 @@ "vspltisb %2,0\;vsubsws %3,%2,%1\;vmaxsw %0,%1,%3" [(set_attr "type" "vecsimple") (set_attr "length" "12")]) + +(define_insn "vec_realign_load_v4si" + [(set (match_operand:V4SI 0 "register_operand" "=v") + (unspec:V4SI [(match_operand:V4SI 1 "register_operand" "v") + (match_operand:V4SI 2 "register_operand" "v") + (match_operand:V16QI 3 "register_operand" "v")] 215))] + "TARGET_ALTIVEC" + "vperm %0,%1,%2,%3" + [(set_attr "type" "vecperm")]) + +(define_insn "vec_realign_load_v4sf" + [(set (match_operand:V4SF 0 "register_operand" "=v") + (unspec:V4SF [(match_operand:V4SF 1 "register_operand" "v") + (match_operand:V4SF 2 "register_operand" "v") + (match_operand:V16QI 3 "register_operand" "v")] 216))] + "TARGET_ALTIVEC" + "vperm %0,%1,%2,%3" + [(set_attr "type" "vecperm")]) + +(define_insn "vec_realign_load_v8hi" + [(set (match_operand:V8HI 0 "register_operand" "=v") + (unspec:V8HI [(match_operand:V8HI 1 "register_operand" "v") + (match_operand:V8HI 2 "register_operand" "v") + (match_operand:V16QI 3 "register_operand" "v")] 217))] + "TARGET_ALTIVEC" + "vperm %0,%1,%2,%3" + [(set_attr "type" "vecperm")]) + +(define_insn "vec_realign_load_v16qi" + [(set (match_operand:V16QI 0 "register_operand" "=v") + (unspec:V16QI [(match_operand:V16QI 1 "register_operand" "v") + (match_operand:V16QI 2 "register_operand" "v") + (match_operand:V16QI 3 "register_operand" "v")] 218))] + "TARGET_ALTIVEC" + "vperm %0,%1,%2,%3" + [(set_attr "type" "vecperm")]) + |