Hi, Please find attached the patch that implements load pair(ldp) and store pair(stp) peephole for aarch64 target.
Please review the same and let me know if its okay. Build and tested on aarch64-thunder-elf (using Cavium's internal simulator). No new regressions. Thanks, Naveen gcc/ 2013-03-26 Naveen H.S <naveen.hurugalaw...@caviumnetworks.com> * config/aarch64/aarch64.md (peephole2s to generate ldp instruction for 2 consecutive loads from memory): New. (peephole2s to generate stp instruction for 2 consecutive stores to memory in integer mode): New. (peephole2s to generate ldp instruction for 2 consecutive loads from memory in floating point mode): New. (peephole2s to generate stp instruction for 2 consecutive stores to memory in floating point mode): New.
--- gcc/config/aarch64/aarch64.md 2013-03-14 16:04:19.705897493 +0530 +++ gcc/config/aarch64/aarch64.md 2013-03-19 15:45:49.808730935 +0530 @@ -1013,6 +1013,26 @@ (set_attr "mode" "<MODE>")] ) +(define_peephole2 + [(set (match_operand:GPI 0 "register_operand") + (match_operand:GPI 1 "aarch64_mem_pair_operand")) + (set (match_operand:GPI 2 "register_operand") + (match_operand:GPI 3 "memory_operand"))] + "GET_CODE (operands[1]) == MEM + && GET_CODE (XEXP (operands[1], 0)) == PLUS + && GET_CODE (XEXP (XEXP (operands[1], 0), 0)) == REG + && GET_CODE (XEXP (XEXP (operands[1], 0), 1)) == CONST_INT + && REGNO (operands[0]) != REGNO (operands[2]) + && REGNO_REG_CLASS (REGNO (operands[0])) + == REGNO_REG_CLASS (REGNO (operands[2])) + && rtx_equal_p (XEXP (operands[3], 0), + plus_constant (Pmode, XEXP (operands[1], 0), + GET_MODE_SIZE (<MODE>mode))) + && optimize_size" + [(parallel [(set (match_dup 0) (match_dup 1)) + (set (match_dup 2) (match_dup 3))])] +) + ;; Operands 0 and 2 are tied together by the final condition; so we allow ;; fairly lax checking on the second memory operation. (define_insn "store_pair<mode>" @@ -1029,6 +1049,26 @@ (set_attr "mode" "<MODE>")] ) +(define_peephole2 + [(set (match_operand:GPI 0 "aarch64_mem_pair_operand") + (match_operand:GPI 1 "register_operand")) + (set (match_operand:GPI 2 "memory_operand") + (match_operand:GPI 3 "register_operand"))] + "GET_CODE (operands[0]) == MEM + && GET_CODE (XEXP (operands[0], 0)) == PLUS + && GET_CODE (XEXP (XEXP (operands[0], 0), 0)) == REG + && GET_CODE (XEXP (XEXP (operands[0], 0), 1)) == CONST_INT + && REGNO (operands[1]) != REGNO (operands[3]) + && REGNO_REG_CLASS (REGNO (operands[1])) + == REGNO_REG_CLASS (REGNO (operands[3])) + && rtx_equal_p (XEXP (operands[2], 0), + plus_constant (Pmode, XEXP (operands[0], 0), + GET_MODE_SIZE (<MODE>mode))) + && optimize_size" + [(parallel [(set (match_dup 0) (match_dup 1)) + (set (match_dup 2) (match_dup 3))])] +) + ;; Operands 1 and 3 are tied together by the final condition; so we allow ;; fairly lax checking on the second memory operation. (define_insn "load_pair<mode>" @@ -1045,6 +1085,27 @@ (set_attr "mode" "<MODE>")] ) +(define_peephole2 + [(set (match_operand:GPF 0 "register_operand") + (match_operand:GPF 1 "aarch64_mem_pair_operand")) + (set (match_operand:GPF 2 "register_operand") + (match_operand:GPF 3 "memory_operand"))] + "GET_CODE (operands[1]) == MEM + && GET_CODE (XEXP (operands[1], 0)) == PLUS + && GET_CODE (XEXP (XEXP (operands[1], 0), 0)) == REG + && GET_CODE (XEXP (XEXP (operands[1], 0), 1)) == CONST_INT + && REGNO (operands[0]) != REGNO (operands[2]) + && REGNO (operands[0]) >= 32 && REGNO (operands[2]) >= 32 + && REGNO_REG_CLASS (REGNO (operands[0])) + == REGNO_REG_CLASS (REGNO (operands[2])) + && rtx_equal_p (XEXP (operands[3], 0), + plus_constant (Pmode, XEXP (operands[1], 0), + GET_MODE_SIZE (<MODE>mode))) + && optimize_size" + [(parallel [(set (match_dup 0) (match_dup 1)) + (set (match_dup 2) (match_dup 3))])] +) + ;; Operands 0 and 2 are tied together by the final condition; so we allow ;; fairly lax checking on the second memory operation. (define_insn "store_pair<mode>" @@ -1061,6 +1122,27 @@ (set_attr "mode" "<MODE>")] ) +(define_peephole2 + [(set (match_operand:GPF 0 "aarch64_mem_pair_operand") + (match_operand:GPF 1 "register_operand")) + (set (match_operand:GPF 2 "memory_operand") + (match_operand:GPF 3 "register_operand"))] + "GET_CODE (operands[0]) == MEM + && GET_CODE (XEXP (operands[0], 0)) == PLUS + && GET_CODE (XEXP (XEXP (operands[0], 0), 0)) == REG + && GET_CODE (XEXP (XEXP (operands[0], 0), 1)) == CONST_INT + && REGNO (operands[1]) != REGNO (operands[3]) + && REGNO (operands[1]) >= 32 && REGNO (operands[3]) >= 32 + && REGNO_REG_CLASS (REGNO (operands[1])) + == REGNO_REG_CLASS (REGNO (operands[3])) + && rtx_equal_p (XEXP (operands[2], 0), + plus_constant (Pmode, XEXP (operands[0], 0), + GET_MODE_SIZE (<MODE>mode))) + && optimize_size" + [(parallel [(set (match_dup 0) (match_dup 1)) + (set (match_dup 2) (match_dup 3))])] +) + ;; Load pair with writeback. This is primarily used in function epilogues ;; when restoring [fp,lr] (define_insn "loadwb_pair<GPI:mode>_<PTR:mode>"