target-arm: Move Neon VZIP to helper functions
Move the implementation of the Neon VUZP unzip instruction from inline
code to helper functions. (At 50+ TCG ops it was well over the
recommended limit for coding inline.) The helper implementations also
give the correct answers where the inline implementation did not.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
diff --git a/target-arm/translate.c b/target-arm/translate.c
index 398764e..16d2ebf 100644
--- a/target-arm/translate.c
+++ b/target-arm/translate.c
@@ -3653,59 +3653,43 @@
return 0;
}
-static void gen_neon_zip_u8(TCGv t0, TCGv t1)
-{
- TCGv rd, rm, tmp;
-
- rd = new_tmp();
- rm = new_tmp();
- tmp = new_tmp();
-
- tcg_gen_andi_i32(rd, t0, 0xff);
- tcg_gen_shli_i32(tmp, t1, 8);
- tcg_gen_andi_i32(tmp, tmp, 0xff00);
- tcg_gen_or_i32(rd, rd, tmp);
- tcg_gen_shli_i32(tmp, t0, 16);
- tcg_gen_andi_i32(tmp, tmp, 0xff0000);
- tcg_gen_or_i32(rd, rd, tmp);
- tcg_gen_shli_i32(tmp, t1, 24);
- tcg_gen_andi_i32(tmp, tmp, 0xff000000);
- tcg_gen_or_i32(rd, rd, tmp);
-
- tcg_gen_andi_i32(rm, t1, 0xff000000);
- tcg_gen_shri_i32(tmp, t0, 8);
- tcg_gen_andi_i32(tmp, tmp, 0xff0000);
- tcg_gen_or_i32(rm, rm, tmp);
- tcg_gen_shri_i32(tmp, t1, 8);
- tcg_gen_andi_i32(tmp, tmp, 0xff00);
- tcg_gen_or_i32(rm, rm, tmp);
- tcg_gen_shri_i32(tmp, t0, 16);
- tcg_gen_andi_i32(tmp, tmp, 0xff);
- tcg_gen_or_i32(t1, rm, tmp);
- tcg_gen_mov_i32(t0, rd);
-
- dead_tmp(tmp);
- dead_tmp(rm);
- dead_tmp(rd);
-}
-
-static void gen_neon_zip_u16(TCGv t0, TCGv t1)
+static int gen_neon_zip(int rd, int rm, int size, int q)
{
TCGv tmp, tmp2;
-
- tmp = new_tmp();
- tmp2 = new_tmp();
-
- tcg_gen_andi_i32(tmp, t0, 0xffff);
- tcg_gen_shli_i32(tmp2, t1, 16);
- tcg_gen_or_i32(tmp, tmp, tmp2);
- tcg_gen_andi_i32(t1, t1, 0xffff0000);
- tcg_gen_shri_i32(tmp2, t0, 16);
- tcg_gen_or_i32(t1, t1, tmp2);
- tcg_gen_mov_i32(t0, tmp);
-
- dead_tmp(tmp2);
- dead_tmp(tmp);
+ if (size == 3 || (!q && size == 2)) {
+ return 1;
+ }
+ tmp = tcg_const_i32(rd);
+ tmp2 = tcg_const_i32(rm);
+ if (q) {
+ switch (size) {
+ case 0:
+ gen_helper_neon_qzip8(cpu_env, tmp, tmp2);
+ break;
+ case 1:
+ gen_helper_neon_qzip16(cpu_env, tmp, tmp2);
+ break;
+ case 2:
+ gen_helper_neon_qzip32(cpu_env, tmp, tmp2);
+ break;
+ default:
+ abort();
+ }
+ } else {
+ switch (size) {
+ case 0:
+ gen_helper_neon_zip8(cpu_env, tmp, tmp2);
+ break;
+ case 1:
+ gen_helper_neon_zip16(cpu_env, tmp, tmp2);
+ break;
+ default:
+ abort();
+ }
+ }
+ tcg_temp_free_i32(tmp);
+ tcg_temp_free_i32(tmp2);
+ return 0;
}
static void gen_neon_trn_u8(TCGv t0, TCGv t1)
@@ -5429,29 +5413,8 @@
}
break;
case 35: /* VZIP */
- /* Reg Before After
- Rd A3 A2 A1 A0 B1 A1 B0 A0
- Rm B3 B2 B1 B0 B3 A3 B2 A2
- */
- if (size == 3)
+ if (gen_neon_zip(rd, rm, size, q)) {
return 1;
- count = (q ? 4 : 2);
- for (n = 0; n < count; n++) {
- tmp = neon_load_reg(rd, n);
- tmp2 = neon_load_reg(rd, n);
- switch (size) {
- case 0: gen_neon_zip_u8(tmp, tmp2); break;
- case 1: gen_neon_zip_u16(tmp, tmp2); break;
- case 2: /* no-op */; break;
- default: abort();
- }
- neon_store_scratch(n * 2, tmp);
- neon_store_scratch(n * 2 + 1, tmp2);
- }
- for (n = 0; n < count * 2; n++) {
- int reg = (n < count) ? rd : rm;
- tmp = neon_load_scratch(n);
- neon_store_reg(reg, n % count, tmp);
}
break;
case 36: case 37: /* VMOVN, VQMOVUN, VQMOVN */
