https://gcc.gnu.org/g:0200c300bd8b0d364c885637482a10cb9467580c

commit r17-394-g0200c300bd8b0d364c885637482a10cb9467580c
Author: Jeff Law <[email protected]>
Date:   Thu May 7 16:52:25 2026 -0600

    [RISC-V][tree-optimization/106244] Improve code when generating (1 << N) & 
0x1
    
    So as noted in the PR, GCC fails to optimize this well:
    
    int8_t f(int8_t x)
    {
        int8_t sh = 1 << x;
        return sh & 1;
    }
    
    I strongly suspect this kind of code is exceedingly rare in practice.  I 
just
    happened to notice that it could be improved when looking for bugs to pass
    along to Shreya & Austin.  As noted in the PR, most of the time this is 
cleaned
    up in gimple, but in some cases it slips through.
    
    I'd love to tackle this in simplify-rtx, but SHIFT_COUNT_TRUNCATED, mode
    handling for shift counts, subregs to deal with 32 bit objects on 64 bit
    targets, etc make it fairly messy.  Rather than spend a ton of time on it, 
I've
    just created a simple risc-v splitter to handle the case of a 32bit shift on
    rv64.  The other cases can't be optimized.
    
    For rv64 we generate:
    
            li      a5,1            # 7     [c=4 l=4] *movsi_internal/1
            sllw    a0,a5,a0        # 8     [c=8 l=4]  ashlsi3_extend
            andi    a0,a0,1 # 17    [c=4 l=4]  *anddi3/1
    
    Instead we can generate:
    
            andi    a0,a0,31        # 8     [c=4 l=4]  *anddi3/1
            seqz    a0,a0   # 17    [c=4 l=4]  *seq_zero_didi
    
    I purposefully added the masking of the shift count.  While the RISC-V port
    does not define SHIFT_COUNT_TRUNCATED, it does have patterns that optimize 
away
    the the masking when they can.  If the masking got optimized away on the
    assumption the count would be used in a shift/rotate and thus masked by the
    hardware, we could have junk in the upper bits.   It's worth noting that
    because of the need to sanitize the shift count we're generating 2 insns, 
thus
    we can't really improve for rv32 or for 64 bit objects on rv64.  If we 
didn't
    need to do that this would be a define_insn that generated a single
    instruction.
    
    Bootstrapped and regression tested on rv64 for on both the BPI and the 
Pioneer.
    Also regression tested on riscv32-elf and riscv64-elf.  Planning to push 
once
    pre-commit CI gives the green light.
    
            PR tree-optimization/106244
    gcc/
            * config/riscv/riscv.md ((and (ashift X Y) const_int 1)): New 
splitter.
    
    gcc/testsuite/
            * gcc.target/riscv/pr106244.c: New test.

Diff:
---
 gcc/config/riscv/riscv.md                 | 18 +++++++++++++++---
 gcc/testsuite/gcc.target/riscv/pr106244.c | 15 +++++++++++++++
 2 files changed, 30 insertions(+), 3 deletions(-)

diff --git a/gcc/config/riscv/riscv.md b/gcc/config/riscv/riscv.md
index 4a49e778fed5..b7fba2e88a38 100644
--- a/gcc/config/riscv/riscv.md
+++ b/gcc/config/riscv/riscv.md
@@ -5168,10 +5168,22 @@
 }
   [(set_attr "type" "branch")
    (set_attr "mode" "none")])
-                                       
-       
 
-;; Standard extensions and pattern for optimization
+;; We can save an instruction for this case.  Essentially we can
+;; test the (sanitized) shift count against zero.  This only comes
+;; up for 32 bit objects on rv64.
+(define_split
+  [(set (match_operand:DI 0 "register_operand")
+       (and:DI (subreg:DI
+                (ashift:SI (const_int 1)
+                           (match_operand:QI 1 "register_operand")) 0)
+               (const_int 1)))
+   (clobber (match_operand:DI 2 "register_operand"))]
+  "TARGET_64BIT"
+  [(set (match_dup 2) (and:DI (match_dup 1) (const_int 31)))
+   (set (match_dup 0) (eq:DI (match_dup 2) (const_int 0)))]
+  { operands[1] = gen_lowpart (DImode, operands[1]); })
+
 (include "bitmanip.md")
 (include "crypto.md")
 (include "sync.md")
diff --git a/gcc/testsuite/gcc.target/riscv/pr106244.c 
b/gcc/testsuite/gcc.target/riscv/pr106244.c
new file mode 100644
index 000000000000..18c2e1b49504
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/pr106244.c
@@ -0,0 +1,15 @@
+/* { dg-do compile { target rv64 } } */
+/* { dg-additional-options "-march=rv64gc_zicond -mabi=lp64d" } */
+/* { dg-skip-if "" { *-*-* } { "-O0" "-Og"} } */
+
+typedef signed char int8_t;
+int8_t f(int8_t x)
+{
+    int8_t sh = 1 << x;
+    return sh & 1;
+}
+
+/* { dg-final { scan-assembler-not "li\t" } } */
+/* { dg-final { scan-assembler-not "sllw\t" } } */
+/* { dg-final { scan-assembler-times "andi\t" 1 } } */
+/* { dg-final { scan-assembler-times "seqz\t" 1 } } */

Reply via email to