[PATCH 3/3] tcg: Implement 256-bit dup for tcg_gen_gvec_dup_mem

[Richard Henderson <richard.henderson@linaro.org>]

We already support duplication of 128-bit blocks.  This extends
that support to 256-bit blocks.  This will be needed by SVE2.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 tcg/tcg-op-gvec.c | 52 ++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 49 insertions(+), 3 deletions(-)

diff --git a/tcg/tcg-op-gvec.c b/tcg/tcg-op-gvec.c
index fcc25b04e6..7ebd9e8298 100644
--- a/tcg/tcg-op-gvec.c
+++ b/tcg/tcg-op-gvec.c
@@ -1570,12 +1570,10 @@ void tcg_gen_gvec_dup_mem(unsigned vece, uint32_t dofs, uint32_t aofs,
             do_dup(vece, dofs, oprsz, maxsz, NULL, in, 0);
             tcg_temp_free_i64(in);
         }
-    } else {
+    } else if (vece == 4) {
         /* 128-bit duplicate.  */
-        /* ??? Dup to 256-bit vector.  */
         int i;
 
-        tcg_debug_assert(vece == 4);
         tcg_debug_assert(oprsz >= 16);
         if (TCG_TARGET_HAS_v128) {
             TCGv_vec in = tcg_temp_new_vec(TCG_TYPE_V128);
@@ -1601,6 +1599,54 @@ void tcg_gen_gvec_dup_mem(unsigned vece, uint32_t dofs, uint32_t aofs,
         if (oprsz < maxsz) {
             expand_clr(dofs + oprsz, maxsz - oprsz);
         }
+    } else if (vece == 5) {
+        /* 256-bit duplicate.  */
+        int i;
+
+        tcg_debug_assert(oprsz >= 32);
+        tcg_debug_assert(oprsz % 32 == 0);
+        if (TCG_TARGET_HAS_v256) {
+            TCGv_vec in = tcg_temp_new_vec(TCG_TYPE_V256);
+
+            tcg_gen_ld_vec(in, cpu_env, aofs);
+            for (i = (aofs == dofs) * 32; i < oprsz; i += 32) {
+                tcg_gen_st_vec(in, cpu_env, dofs + i);
+            }
+            tcg_temp_free_vec(in);
+        } else if (TCG_TARGET_HAS_v128) {
+            TCGv_vec in0 = tcg_temp_new_vec(TCG_TYPE_V128);
+            TCGv_vec in1 = tcg_temp_new_vec(TCG_TYPE_V128);
+
+            tcg_gen_ld_vec(in0, cpu_env, aofs);
+            tcg_gen_ld_vec(in1, cpu_env, aofs + 16);
+            for (i = (aofs == dofs) * 32; i < oprsz; i += 32) {
+                tcg_gen_st_vec(in0, cpu_env, dofs + i);
+                tcg_gen_st_vec(in1, cpu_env, dofs + i + 16);
+            }
+            tcg_temp_free_vec(in0);
+            tcg_temp_free_vec(in1);
+        } else {
+            TCGv_i64 in[4];
+            int j;
+
+            for (j = 0; j < 4; ++j) {
+                in[j] = tcg_temp_new_i64();
+                tcg_gen_ld_i64(in[j], cpu_env, aofs + j * 8);
+            }
+            for (i = (aofs == dofs) * 32; i < oprsz; i += 32) {
+                for (j = 0; j < 4; ++j) {
+                    tcg_gen_st_i64(in[j], cpu_env, dofs + i + j * 8);
+                }
+            }
+            for (j = 0; j < 4; ++j) {
+                tcg_temp_free_i64(in[j]);
+            }
+        }
+        if (oprsz < maxsz) {
+            expand_clr(dofs + oprsz, maxsz - oprsz);
+        }
+    } else {
+        g_assert_not_reached();
     }
 }
 
-- 
2.25.1