Improve handling of constants where the high half can be constructed
by shifting the low half.
gcc/ChangeLog:
* config/riscv/riscv.cc (riscv_build_integer): Detect constants
were the higher half is a shift of the lower half.
gcc/testsuite/ChangeLog:
* gcc.target/riscv/synthesis-12.c: New test.
---
gcc/config/riscv/riscv.cc | 39 +++++++++++++++++++
gcc/testsuite/gcc.target/riscv/synthesis-12.c | 27 +++++++++++++
2 files changed, 66 insertions(+)
create mode 100644 gcc/testsuite/gcc.target/riscv/synthesis-12.c
diff --git a/gcc/config/riscv/riscv.cc b/gcc/config/riscv/riscv.cc
index 454220d8ba4..a3e8a243f15 100644
--- a/gcc/config/riscv/riscv.cc
+++ b/gcc/config/riscv/riscv.cc
@@ -1259,6 +1259,45 @@ riscv_build_integer (struct riscv_integer_op *codes,
HOST_WIDE_INT value,
cost = alt_cost;
}
}
+
+ if (cost > 4 && !bit31)
+ {
+ int trailing_shift = ctz_hwi (loval) - ctz_hwi (hival);
+ int leading_shift = clz_hwi (loval) - clz_hwi (hival);
+ alt_cost = 2 + riscv_build_integer_1 (alt_codes, sext_hwi (loval, 32),
+ mode);
+ /* For constants where the upper half is a shift of the lower half we
+ can do a similar transformation as for constants with the same
+ halves. */
+ if (alt_cost < cost)
+ {
+ alt_codes[alt_cost - 3].save_temporary = true;
+ alt_codes[alt_cost - 2].code = ASHIFT;
+ alt_codes[alt_cost - 2].use_uw = false;
+ alt_codes[alt_cost - 2].save_temporary = false;
+ alt_codes[alt_cost - 1].code = CONCAT;
+ alt_codes[alt_cost - 1].value = 0;
+ alt_codes[alt_cost - 1].use_uw = false;
+ alt_codes[alt_cost - 1].save_temporary = false;
+
+ /* Adjust the shift into the high half accordingly. */
+ if ((trailing_shift > 0 && hival == (loval >> trailing_shift)) ||
+ (trailing_shift < 0 && hival == (loval << trailing_shift)))
+ {
+ alt_codes[alt_cost - 2].value = 32 - trailing_shift;
+ memcpy (codes, alt_codes, sizeof (alt_codes));
+ cost = alt_cost;
+ }
+ else if ((leading_shift < 0 && hival == (loval >> leading_shift))
+ || (leading_shift > 0
+ && hival == (loval << leading_shift)))
+ {
+ alt_codes[alt_cost - 2].value = 32 + leading_shift;
+ memcpy (codes, alt_codes, sizeof (alt_codes));
+ cost = alt_cost;
+ }
+ }
+ }
}
return cost;
diff --git a/gcc/testsuite/gcc.target/riscv/synthesis-12.c
b/gcc/testsuite/gcc.target/riscv/synthesis-12.c
new file mode 100644
index 00000000000..0265a2d6f13
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/synthesis-12.c
@@ -0,0 +1,27 @@
+
+/* { dg-do compile } */
+/* { dg-require-effective-target rv64 } */
+/* We aggressively skip as we really just need to test the basic synthesis
+ which shouldn't vary based on the optimization level. -O1 seems to work
+ and eliminates the usual sources of extraneous dead code that would throw
+ off the counts. */
+/* { dg-skip-if "" { *-*-* } { "-O0" "-Og" "-O2" "-O3" "-Os" "-Oz" "-flto" } }
*/
+/* { dg-options "-march=rv64gc" } */
+
+/* Rather than test for a specific synthesis of all these constants or
+ having thousands of tests each testing one variant, we just test the
+ total number of instructions.
+
+ This isn't expected to change much and any change is worthy of a look. */
+/* { dg-final { scan-assembler-times
"\\t(add|addi|bseti|li|pack|ret|sh1add|sh2add|sh3add|slli|srli|xori|or)" 45 } }
*/
+
+
+unsigned long foo_0x7857f2de7857f2de(void) { return 0x7857f2de7857f2deUL; }
+unsigned long foo_0x7fffdffe3fffefff(void) { return 0x7fffdffe3fffefffUL; }
+unsigned long foo_0x1ffff7fe3fffeffc(void) { return 0x1ffff7fe3fffeffcUL; }
+unsigned long foo_0x0a3fdbf0028ff6fc(void) { return 0x0a3fdbf0028ff6fcUL; }
+unsigned long foo_0x014067e805019fa0(void) { return 0x014067e805019fa0UL; }
+unsigned long foo_0x09d87e90009d87e9(void) { return 0x09d87e90009d87e9UL; }
+unsigned long foo_0x2302320000118119(void) { return 0x2302320000118119UL; }
+unsigned long foo_0x000711eb00e23d60(void) { return 0x000711eb00e23d60UL; }
+unsigned long foo_0x5983800001660e00(void) { return 0x5983800001660e00UL; }
--
2.42.0
