Enable anchors for vector constants - like FP, expand vector constants early
and place them in the constdata section.  Performance on SPECFP2017 is ~0.03%
better.  There is a slight 0.08% increase in codesize due to extra const data
and a latent CSE issue which results in aarch64/vect-cse-codegen.c failing.

Passes regress, OK for commit?

gcc:
        PR target/121240
        * config/aarch64/aarch64-simd.md (mov<mode>): Expand vector constants
        early.
        * config/aarch64/aarch64.cc (aarch64_select_rtx_section): Force 
        vector immediates <= 16 bytes to constdata.
 
gcc/testsuite:
        PR target/121240
        * gcc.target/aarch64/const_create_using_fmov.c: Adjust anchor label.
        * gcc.target/aarch64/pr121240.c: Add new test.
        * gcc.target/aarch64/vec-init-single-const.c: Adjust anchor label.

---

diff --git a/gcc/config/aarch64/aarch64-simd.md 
b/gcc/config/aarch64/aarch64-simd.md
index 
505e8b1126fa021a22f1ee37cecae1fc8098ae78..264b681f9f2d79e6e8e478a0ba490a4016c1031b
 100644
--- a/gcc/config/aarch64/aarch64-simd.md
+++ b/gcc/config/aarch64/aarch64-simd.md
@@ -70,11 +70,22 @@ (define_expand "mov<mode>"
      contains CONST_POLY_INTs), build it up from individual elements instead.
      We should only need to do this before RA; aarch64_legitimate_constant_p
      should ensure that we don't try to rematerialize the constant later.  */
-  if (GET_CODE (operands[1]) == CONST_VECTOR
-      && targetm.cannot_force_const_mem (<MODE>mode, operands[1]))
+  if (GET_CODE (operands[1]) == CONST_VECTOR)
     {
-      aarch64_expand_vector_init (operands[0], operands[1]);
-      DONE;
+      if (targetm.cannot_force_const_mem (<MODE>mode, operands[1]))
+       {
+         aarch64_expand_vector_init (operands[0], operands[1]);
+         DONE;
+       }
+      else if (!aarch64_simd_imm_zero (operands[1], <MODE>mode)
+              && !aarch64_simd_special_constant_p (operands[1], <MODE>mode)
+              && !aarch64_simd_valid_mov_imm (operands[1]))
+       {
+         /* Expand into a literal load using anchors.  */
+         operands[1] = force_const_mem (<MODE>mode, operands[1]);
+         emit_move_insn (operands[0], operands[1]);
+         DONE;
+       }
     }
   "
 )
diff --git a/gcc/config/aarch64/aarch64.cc b/gcc/config/aarch64/aarch64.cc
index 
29d2400a6e9d6277ee5ed283ff8e11041d920435..f5285ed45962f3fe795348cc77534b3dfa010b52
 100644
--- a/gcc/config/aarch64/aarch64.cc
+++ b/gcc/config/aarch64/aarch64.cc
@@ -14311,8 +14311,8 @@ aarch64_select_rtx_section (machine_mode mode,
     return function_section (current_function_decl);
 
   /* When using anchors for constants use the readonly section.  */
-  if ((CONST_INT_P (x) || CONST_DOUBLE_P (x))
-      && known_le (GET_MODE_SIZE (mode), 8))
+  if ((CONST_INT_P (x) || CONST_DOUBLE_P (x) || CONST_VECTOR_P (x))
+      && known_le (GET_MODE_SIZE (mode), 16))
     return readonly_data_section;
 
   return default_elf_select_rtx_section (mode, x, align);
diff --git a/gcc/testsuite/gcc.target/aarch64/const_create_using_fmov.c 
b/gcc/testsuite/gcc.target/aarch64/const_create_using_fmov.c
index 
e080afed8aa3578660027979335bfc859ca6bc91..98060556e80d67835039b3e6ec9d2124357d0d06
 100644
--- a/gcc/testsuite/gcc.target/aarch64/const_create_using_fmov.c
+++ b/gcc/testsuite/gcc.target/aarch64/const_create_using_fmov.c
@@ -78,8 +78,8 @@ uint16x8_t f5() {
 
 /*
 ** f6:
-**     adrp    x0, \.LC0
-**     ldr     q0, \[x0, #:lo12:\.LC0\]
+**     adrp    x0, \.L.+
+**     ldr     q0, \[x0, #:lo12:\.L.+\]
 **     ret
 */
 uint32x4_t f6() {
diff --git a/gcc/testsuite/gcc.target/aarch64/pr121240.c 
b/gcc/testsuite/gcc.target/aarch64/pr121240.c
new file mode 100644
index 
0000000000000000000000000000000000000000..f04574d411c3fd4d6ac2313fc27f2274e8926080
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/pr121240.c
@@ -0,0 +1,15 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mcmodel=small" } */
+
+const double b[4] = {0.2435334343f, 0.2233535343f, 0.4232433f, 0.34343434f};
+typedef double v2df __attribute__ ((vector_size (16)));
+typedef double v2df __attribute__ ((vector_size (16)));
+
+v2df f (v2df c1, v2df c2)
+{
+   v2df a1 = *(v2df *)&b[0];
+   v2df a2 = *(v2df *)&b[2];
+   return (a1 * c1) + (a2 * c2);
+}
+
+/* { dg-final { scan-assembler-times "adrp" 1 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/vec-init-single-const.c 
b/gcc/testsuite/gcc.target/aarch64/vec-init-single-const.c
index 
274b0b39ac434d887b43a07c30fb41218bdf8768..ec9a74b8bdef426c5bd43e8a9247d53821fc7286
 100644
--- a/gcc/testsuite/gcc.target/aarch64/vec-init-single-const.c
+++ b/gcc/testsuite/gcc.target/aarch64/vec-init-single-const.c
@@ -46,8 +46,8 @@ int32x4_t f_s32(int32_t x)
 
 /*
 ** f_s64:
-**     adrp    x[0-9]+, .LC[0-9]+
-**     ldr     q0, \[x[0-9]+, #:lo12:.LC[0-9]+\]
+**     adrp    x[0-9]+, .L.+
+**     ldr     q0, \[x[0-9]+, #:lo12:.L.+\]
 **     ins     v0\.d\[0\], x0
 **     ret
 */

Reply via email to