aboutsummaryrefslogtreecommitdiff
path: root/gcc/config
diff options
context:
space:
mode:
authorTakayuki 'January June' Suwa <jjsuwa_sys3175@yahoo.co.jp>2023-01-08 14:03:49 +0900
committerMax Filippov <jcmvbkbc@gmail.com>2023-01-08 14:14:39 -0800
commite3a4bd0bbdccdde0cff85f93064b01a44fb10d2a (patch)
treeaf5850f8f6f9e67c813cfad94e50d3dc3763edab /gcc/config
parentd901bf8a44a85e1285b7f678056aa2eed0118f56 (diff)
downloadgcc-e3a4bd0bbdccdde0cff85f93064b01a44fb10d2a.zip
gcc-e3a4bd0bbdccdde0cff85f93064b01a44fb10d2a.tar.gz
gcc-e3a4bd0bbdccdde0cff85f93064b01a44fb10d2a.tar.bz2
xtensa: Optimize bitwise splicing operation
This patch optimizes the operation of cutting and splicing two register values at a specified bit position, in other words, combining (bitwise ORing) bits 0 through (C-1) of the register with bits C through 31 of the other, where C is the specified immediate integer 17 through 31. This typically applies to signed copy of floating point number and __builtin_return_address() if the windowed register ABI, and saves one instruction compared to four shifts and a bitwise OR by the default RTL combination pass. gcc/ChangeLog: * config/xtensa/xtensa.md (*splice_bits): New insn_and_split pattern.
Diffstat (limited to 'gcc/config')
-rw-r--r--gcc/config/xtensa/xtensa.md47
1 files changed, 47 insertions, 0 deletions
diff --git a/gcc/config/xtensa/xtensa.md b/gcc/config/xtensa/xtensa.md
index 0a26d3d..db1d68e 100644
--- a/gcc/config/xtensa/xtensa.md
+++ b/gcc/config/xtensa/xtensa.md
@@ -746,6 +746,53 @@
(set_attr "mode" "SI")
(set_attr "length" "3")])
+(define_insn_and_split "*splice_bits"
+ [(set (match_operand:SI 0 "register_operand" "=a")
+ (ior:SI (and:SI (match_operand:SI 1 "register_operand" "r")
+ (match_operand:SI 3 "const_int_operand" "i"))
+ (and:SI (match_operand:SI 2 "register_operand" "r")
+ (match_operand:SI 4 "const_int_operand" "i"))))]
+
+ "!optimize_debug && optimize
+ && INTVAL (operands[3]) + INTVAL (operands[4]) == -1
+ && (exact_log2 (INTVAL (operands[3]) + 1) > 16
+ || exact_log2 (INTVAL (operands[4]) + 1) > 16)"
+ "#"
+ "&& can_create_pseudo_p ()"
+ [(set (match_dup 5)
+ (ashift:SI (match_dup 1)
+ (match_dup 4)))
+ (set (match_dup 6)
+ (lshiftrt:SI (match_dup 2)
+ (match_dup 3)))
+ (set (match_dup 0)
+ (ior:SI (lshiftrt:SI (match_dup 5)
+ (match_dup 4))
+ (ashift:SI (match_dup 6)
+ (match_dup 3))))]
+{
+ int shift;
+ if (INTVAL (operands[3]) < 0)
+ {
+ rtx x;
+ x = operands[1], operands[1] = operands[2], operands[2] = x;
+ x = operands[3], operands[3] = operands[4], operands[4] = x;
+ }
+ shift = floor_log2 (INTVAL (operands[3]) + 1);
+ operands[3] = GEN_INT (shift);
+ operands[4] = GEN_INT (32 - shift);
+ operands[5] = gen_reg_rtx (SImode);
+ operands[6] = gen_reg_rtx (SImode);
+}
+ [(set_attr "type" "arith")
+ (set_attr "mode" "SI")
+ (set (attr "length")
+ (if_then_else (match_test "TARGET_DENSITY
+ && (INTVAL (operands[3]) == 0x7FFFFFFF
+ || INTVAL (operands[4]) == 0x7FFFFFFF)")
+ (const_int 11)
+ (const_int 12)))])
+
;; Zero-extend instructions.