aboutsummaryrefslogtreecommitdiff
path: root/gcc/config/loongarch
diff options
context:
space:
mode:
authorXi Ruoyao <xry111@xry111.site>2022-07-06 13:45:55 +0800
committerXi Ruoyao <xry111@xry111.site>2022-07-10 11:36:11 +0800
commita5d3826f7648c4c7763dba8882e6722deae0c116 (patch)
tree4b69cbd80c7182ef0e5d1e116f0fb16f2ad46cbe /gcc/config/loongarch
parent1fa42d62140b56589771eb3d46f89c810bfc8e0a (diff)
downloadgcc-a5d3826f7648c4c7763dba8882e6722deae0c116.zip
gcc-a5d3826f7648c4c7763dba8882e6722deae0c116.tar.gz
gcc-a5d3826f7648c4c7763dba8882e6722deae0c116.tar.bz2
loongarch: add alternatives for idiv insns to improve code generation
Currently in the description of LoongArch integer division instructions, the output is marked as earlyclobbered ('&'). It's necessary when loongarch_check_zero_div_p() because clobbering operand 2 (divisor) will make the checking for zero divisor impossible. But, for -mno-check-zero-division (the default of GCC >= 12.2 for optimized code), the output is not earlyclobbered at all. And, the read of operand 1 only occurs before clobbering the output. So we make three alternatives for an idiv instruction: * (=r,r,r): For -mno-check-zero-division. * (=&r,r,r): For -mcheck-zero-division. * (=&r,0,r): For -mcheck-zero-division, to explicitly allow patterns like "div.d $a0, $a0, $a1". gcc/ChangeLog: * config/loongarch/loongarch.cc (loongarch_check_zero_div_p): Remove static, for use in the machine description file. * config/loongarch/loongarch-protos.h: (loongarch_check_zero_div_p): Add prototype. * config/loongarch/loongarch.md (enabled): New attr. (*<optab><mode>3): Add (=r,r,r) and (=&r,0,r) alternatives for idiv. Conditionally enable the alternatives using loongarch_check_zero_div_p. (<optab>di3_fake): Likewise. gcc/testsuite/ChangeLog: * gcc.target/loongarch/div-1.c: New test. * gcc.target/loongarch/div-2.c: New test. * gcc.target/loongarch/div-3.c: New test.
Diffstat (limited to 'gcc/config/loongarch')
-rw-r--r--gcc/config/loongarch/loongarch-protos.h1
-rw-r--r--gcc/config/loongarch/loongarch.cc2
-rw-r--r--gcc/config/loongarch/loongarch.md28
3 files changed, 22 insertions, 9 deletions
diff --git a/gcc/config/loongarch/loongarch-protos.h b/gcc/config/loongarch/loongarch-protos.h
index 2144c24..2287fd37 100644
--- a/gcc/config/loongarch/loongarch-protos.h
+++ b/gcc/config/loongarch/loongarch-protos.h
@@ -130,6 +130,7 @@ extern bool loongarch_symbol_binds_local_p (const_rtx);
extern const char *current_section_name (void);
extern unsigned int current_section_flags (void);
extern bool loongarch_use_ins_ext_p (rtx, HOST_WIDE_INT, HOST_WIDE_INT);
+extern bool loongarch_check_zero_div_p (void);
union loongarch_gen_fn_ptrs
{
diff --git a/gcc/config/loongarch/loongarch.cc b/gcc/config/loongarch/loongarch.cc
index 5c9a33c1..8b0d7f4 100644
--- a/gcc/config/loongarch/loongarch.cc
+++ b/gcc/config/loongarch/loongarch.cc
@@ -2110,7 +2110,7 @@ loongarch_load_store_insns (rtx mem, rtx_insn *insn)
/* Return true if we need to trap on division by zero. */
-static bool
+bool
loongarch_check_zero_div_p (void)
{
/* if -m[no-]check-zero-division is given explicitly. */
diff --git a/gcc/config/loongarch/loongarch.md b/gcc/config/loongarch/loongarch.md
index 8f8412f..6bca2ed 100644
--- a/gcc/config/loongarch/loongarch.md
+++ b/gcc/config/loongarch/loongarch.md
@@ -110,6 +110,8 @@
;;
;; ....................
+(define_attr "enabled" "no,yes" (const_string "yes"))
+
(define_attr "got" "unset,load"
(const_string "unset"))
@@ -763,26 +765,36 @@
})
(define_insn "*<optab><mode>3"
- [(set (match_operand:GPR 0 "register_operand" "=&r")
- (any_div:GPR (match_operand:GPR 1 "register_operand" "r")
- (match_operand:GPR 2 "register_operand" "r")))]
+ [(set (match_operand:GPR 0 "register_operand" "=r,&r,&r")
+ (any_div:GPR (match_operand:GPR 1 "register_operand" "r,r,0")
+ (match_operand:GPR 2 "register_operand" "r,r,r")))]
""
{
return loongarch_output_division ("<insn>.<d><u>\t%0,%1,%2", operands);
}
[(set_attr "type" "idiv")
- (set_attr "mode" "<MODE>")])
+ (set_attr "mode" "<MODE>")
+ (set (attr "enabled")
+ (if_then_else
+ (match_test "!!which_alternative == loongarch_check_zero_div_p()")
+ (const_string "yes")
+ (const_string "no")))])
(define_insn "<optab>di3_fake"
- [(set (match_operand:SI 0 "register_operand" "=&r")
- (any_div:SI (match_operand:DI 1 "register_operand" "r")
- (match_operand:DI 2 "register_operand" "r")))]
+ [(set (match_operand:SI 0 "register_operand" "=r,&r,&r")
+ (any_div:SI (match_operand:DI 1 "register_operand" "r,r,0")
+ (match_operand:DI 2 "register_operand" "r,r,r")))]
""
{
return loongarch_output_division ("<insn>.w<u>\t%0,%1,%2", operands);
}
[(set_attr "type" "idiv")
- (set_attr "mode" "SI")])
+ (set_attr "mode" "SI")
+ (set (attr "enabled")
+ (if_then_else
+ (match_test "!!which_alternative == loongarch_check_zero_div_p()")
+ (const_string "yes")
+ (const_string "no")))])
;; Floating point multiply accumulate instructions.