aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorJivan Hakobyan <jivanhakobyan9@gmail.com>2023-09-29 13:41:48 -0600
committerJeff Law <jlaw@ventanamicro.com>2023-09-29 13:42:47 -0600
commit51d09e67df52164c2025afa24531cf79820ff4c8 (patch)
tree22d5d7a20c87c83b7ac605652cc2bf5effbce24d
parenteaa41a6dc127d8d8a38646aaadc37681691fc311 (diff)
downloadgcc-51d09e67df52164c2025afa24531cf79820ff4c8.zip
gcc-51d09e67df52164c2025afa24531cf79820ff4c8.tar.gz
gcc-51d09e67df52164c2025afa24531cf79820ff4c8.tar.bz2
RISC-V: Replace not + bitwise_imm with li + bitwise_not
In the case when we have C code like this int foo (int a) { return 100 & ~a; } GCC generates the following instruction sequence foo: not a0,a0 andi a0,a0,100 ret This patch replaces that with this sequence foo: li a5,100 andn a0,a5,a0 ret The profitability comes from an out-of-order processor being able to issue the "li a5, 100" at any time after it's fetched while "not a0, a0" has to wait until any prior setter of a0 has reached completion. gcc/ChangeLog: * config/riscv/bitmanip.md (*<optab>_not_const<mode>): New split pattern. gcc/testsuite/ChangeLog: * gcc.target/riscv/zbb-andn-orn-01.c: New test. * gcc.target/riscv/zbb-andn-orn-02.c: Likewise.
-rw-r--r--gcc/config/riscv/bitmanip.md12
-rw-r--r--gcc/testsuite/gcc.target/riscv/zbb-andn-orn-01.c17
-rw-r--r--gcc/testsuite/gcc.target/riscv/zbb-andn-orn-02.c17
3 files changed, 46 insertions, 0 deletions
diff --git a/gcc/config/riscv/bitmanip.md b/gcc/config/riscv/bitmanip.md
index 0d126a8..0f45bad 100644
--- a/gcc/config/riscv/bitmanip.md
+++ b/gcc/config/riscv/bitmanip.md
@@ -215,6 +215,18 @@
[(set_attr "type" "bitmanip")
(set_attr "mode" "<X:MODE>")])
+(define_insn_and_split "*<optab>_not_const<mode>"
+ [(set (match_operand:X 0 "register_operand" "=r")
+ (bitmanip_bitwise:X (not:X (match_operand:X 1 "register_operand" "r"))
+ (match_operand:X 2 "const_arith_operand" "I")))
+ (clobber (match_scratch:X 3 "=&r"))]
+ "(TARGET_ZBB || TARGET_ZBKB) && !TARGET_ZCB
+ && !optimize_function_for_size_p (cfun)"
+ "#"
+ "&& reload_completed"
+ [(set (match_dup 3) (match_dup 2))
+ (set (match_dup 0) (bitmanip_bitwise:X (not:X (match_dup 1)) (match_dup 3)))])
+
;; '(a >= 0) ? b : 0' is emitted branchless (from if-conversion). Without a
;; bit of extra help for combine (i.e., the below split), we end up emitting
;; not/srai/and instead of combining the not into an andn.
diff --git a/gcc/testsuite/gcc.target/riscv/zbb-andn-orn-01.c b/gcc/testsuite/gcc.target/riscv/zbb-andn-orn-01.c
new file mode 100644
index 0000000..f9f3222
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/zbb-andn-orn-01.c
@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gc_zbb -mabi=lp64" } */
+/* { dg-skip-if "" { *-*-* } { "-O0" "-g" "-Oz" "-Os" } } */
+
+int foo1(int rs1)
+{
+ return 100 & ~rs1;
+}
+
+int foo2(int rs1)
+{
+ return 100 | ~rs1;
+}
+
+/* { dg-final { scan-assembler-times "andn\t" 1 } } */
+/* { dg-final { scan-assembler-times "orn\t" 1 } } */
+/* { dg-final { scan-assembler-times "li\t" 2 } } */
diff --git a/gcc/testsuite/gcc.target/riscv/zbb-andn-orn-02.c b/gcc/testsuite/gcc.target/riscv/zbb-andn-orn-02.c
new file mode 100644
index 0000000..112c0fa
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/zbb-andn-orn-02.c
@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv32gc_zbb -mabi=ilp32" } */
+/* { dg-skip-if "" { *-*-* } { "-O0" "-g" "-Oz" "-Os" } } */
+
+int foo1(int rs1)
+{
+ return 100 & ~rs1;
+}
+
+int foo2(int rs1)
+{
+ return 100 | ~rs1;
+}
+
+/* { dg-final { scan-assembler-times "andn\t" 1 } } */
+/* { dg-final { scan-assembler-times "orn\t" 1 } } */
+/* { dg-final { scan-assembler-times "li\t" 2 } } */