[gcc r15-1723] [to-be-committed, RISC-V, V4] movmem for RISCV with V extension

[Jeff Law]

https://gcc.gnu.org/g:42946aa9b3228262e413481a3193bda85c20ef4b

commit r15-1723-g42946aa9b3228262e413481a3193bda85c20ef4b
Author: Sergei Lewis <slewis@rivosinc.com>
Date:   Sat Jun 29 14:34:31 2024 -0600

    [to-be-committed,RISC-V,V4] movmem for RISCV with V extension
    
    I hadn't updated my repo on the host where I handle email, so it picked
    up the older version of this patch without the testsuite fix.  So, V4
    with the testsuite option for lmul fixed.
    
    --
    
    And Sergei's movmem patch.  Just trivial testsuite adjustment for an
    option name change and a whitespace fix from me.
    
    I've spun this in my tester for rv32 and rv64.  I'll wait for pre-commit
    CI before taking further action.
    
    Just a reminder, this patch is designed to handle the case where we can
    issue a single vector load/store which avoids all the complexities of
    determining which direction to copy.
    
    --
    
    gcc/ChangeLog
    
            * config/riscv/riscv.md (movmem<mode>): New expander.
    
    gcc/testsuite/ChangeLog
    
            PR target/112109
            * gcc.target/riscv/rvv/base/movmem-1.c: New test

Diff:
---
 gcc/config/riscv/riscv.md                          | 22 ++++++++
 gcc/testsuite/gcc.target/riscv/rvv/base/movmem-1.c | 60 ++++++++++++++++++++++
 2 files changed, 82 insertions(+)

diff --git a/gcc/config/riscv/riscv.md b/gcc/config/riscv/riscv.md
index ff37125e3f2..c0c960353eb 100644
--- a/gcc/config/riscv/riscv.md
+++ b/gcc/config/riscv/riscv.md
@@ -2723,6 +2723,28 @@
     FAIL;
 })
 
+;; Inlining general memmove is a pessimisation: we can't avoid having to decide
+;; which direction to go at runtime, which is costly in instruction count
+;; however for situations where the entire move fits in one vector operation
+;; we can do all reads before doing any writes so we don't have to worry
+;; so generate the inline vector code in such situations
+;; nb. prefer scalar path for tiny memmoves.
+(define_expand "movmem<mode>"
+  [(parallel [(set (match_operand:BLK 0 "general_operand")
+   (match_operand:BLK 1 "general_operand"))
+    (use (match_operand:P 2 "const_int_operand"))
+    (use (match_operand:SI 3 "const_int_operand"))])]
+  "TARGET_VECTOR"
+{
+  if ((INTVAL (operands[2]) >= TARGET_MIN_VLEN / 8)
+	&& (INTVAL (operands[2]) <= TARGET_MIN_VLEN)
+	&& riscv_vector::expand_block_move (operands[0], operands[1],
+	     operands[2]))
+    DONE;
+  else
+    FAIL;
+})
+
 ;; Expand in-line code to clear the instruction cache between operand[0] and
 ;; operand[1].
 (define_expand "clear_cache"
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/movmem-1.c b/gcc/testsuite/gcc.target/riscv/rvv/base/movmem-1.c
new file mode 100644
index 00000000000..d9d4a70a392
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/movmem-1.c
@@ -0,0 +1,60 @@
+/* { dg-do compile } */
+/* { dg-add-options riscv_v } */
+/* { dg-additional-options "-O3 -mrvv-max-lmul=dynamic" } */
+/* { dg-final { check-function-bodies "**" "" } } */
+
+#define MIN_VECTOR_BYTES (__riscv_v_min_vlen / 8)
+
+/* Tiny memmoves should not be vectorised.
+** f1:
+**  li\s+a2,\d+
+**  tail\s+memmove
+*/
+char *
+f1 (char *a, char const *b)
+{
+  return __builtin_memmove (a, b, MIN_VECTOR_BYTES - 1);
+}
+
+/* Vectorise+inline minimum vector register width with LMUL=1
+** f2:
+**  (
+**  vsetivli\s+zero,16,e8,m1,ta,ma
+**  |
+**  li\s+[ta][0-7],\d+
+**  vsetvli\s+zero,[ta][0-7],e8,m1,ta,ma
+**  )
+**  vle8\.v\s+v\d+,0\(a1\)
+**  vse8\.v\s+v\d+,0\(a0\)
+**  ret
+*/
+char *
+f2 (char *a, char const *b)
+{
+  return __builtin_memmove (a, b, MIN_VECTOR_BYTES);
+}
+
+/* Vectorise+inline up to LMUL=8
+** f3:
+**  li\s+[ta][0-7],\d+
+**  vsetvli\s+zero,[ta][0-7],e8,m8,ta,ma
+**  vle8\.v\s+v\d+,0\(a1\)
+**  vse8\.v\s+v\d+,0\(a0\)
+**  ret
+*/
+char *
+f3 (char *a, char const *b)
+{
+  return __builtin_memmove (a, b, MIN_VECTOR_BYTES * 8);
+}
+
+/* Don't vectorise if the move is too large for one operation
+** f4:
+**  li\s+a2,\d+
+**  tail\s+memmove
+*/
+char *
+f4 (char *a, char const *b)
+{
+  return __builtin_memmove (a, b, MIN_VECTOR_BYTES * 8 + 1);
+}