diff mbox series

[v3,07/16] target/arm: Create gen_gvec_{mla,mls}

Message ID 20200508152200.6547-8-richard.henderson@linaro.org
State Superseded
Headers show
Series target/arm: partial vector cleanup | expand

Commit Message

Richard Henderson May 8, 2020, 3:21 p.m. UTC 
Provide a functional interface for the vector expansion.
This fits better with the existing set of helpers that
we provide for other operations.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

---
 target/arm/translate.h          |   7 +-
 target/arm/translate-a64.c      |   4 +-
 target/arm/translate-neon.inc.c |  16 +----
 target/arm/translate.c          | 117 +++++++++++++++++---------------
 4 files changed, 71 insertions(+), 73 deletions(-)

-- 
2.20.1

Comments

Peter Maydell May 12, 2020, 2:11 p.m. UTC | #1 
On Fri, 8 May 2020 at 16:22, Richard Henderson
<richard.henderson@linaro.org> wrote:
>

> Provide a functional interface for the vector expansion.

> This fits better with the existing set of helpers that

> we provide for other operations.

>

> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

> ---


Reviewed-by: Peter Maydell <peter.maydell@linaro.org>


thanks
-- PMM
diff mbox series

Patch

diff --git a/target/arm/translate.h b/target/arm/translate.h
index e35c812cc5..9354ceba35 100644
--- a/target/arm/translate.h
+++ b/target/arm/translate.h
@@ -286,8 +286,11 @@  void gen_gvec_cle0(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
 void gen_gvec_cge0(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
                    uint32_t opr_sz, uint32_t max_sz);
 
-extern const GVecGen3 mla_op[4];
-extern const GVecGen3 mls_op[4];
+void gen_gvec_mla(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+                  uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz);
+void gen_gvec_mls(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+                  uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz);
+
 extern const GVecGen3 cmtst_op[4];
 extern const GVecGen3 sshl_op[4];
 extern const GVecGen3 ushl_op[4];
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index fef93dc27a..ab9df12e44 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -11226,9 +11226,9 @@  static void disas_simd_3same_int(DisasContext *s, uint32_t insn)
         return;
     case 0x12: /* MLA, MLS */
         if (u) {
-            gen_gvec_op3(s, is_q, rd, rn, rm, &mls_op[size]);
+            gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_mls, size);
         } else {
-            gen_gvec_op3(s, is_q, rd, rn, rm, &mla_op[size]);
+            gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_mla, size);
         }
         return;
     case 0x11:
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
index 50b77b6d71..aefeff498a 100644
--- a/target/arm/translate-neon.inc.c
+++ b/target/arm/translate-neon.inc.c
@@ -632,6 +632,8 @@  DO_3SAME_NO_SZ_3(VMAX_U, tcg_gen_gvec_umax)
 DO_3SAME_NO_SZ_3(VMIN_S, tcg_gen_gvec_smin)
 DO_3SAME_NO_SZ_3(VMIN_U, tcg_gen_gvec_umin)
 DO_3SAME_NO_SZ_3(VMUL, tcg_gen_gvec_mul)
+DO_3SAME_NO_SZ_3(VMLA, gen_gvec_mla)
+DO_3SAME_NO_SZ_3(VMLS, gen_gvec_mls)
 
 #define DO_3SAME_CMP(INSN, COND)                                        \
     static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs,         \
@@ -685,20 +687,6 @@  static bool trans_VMUL_p_3s(DisasContext *s, arg_3same *a)
     return do_3same(s, a, gen_VMUL_p_3s);
 }
 
-#define DO_3SAME_GVEC3_NO_SZ_3(INSN, OPARRAY)                           \
-    static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs,         \
-                                uint32_t rn_ofs, uint32_t rm_ofs,       \
-                                uint32_t oprsz, uint32_t maxsz)         \
-    {                                                                   \
-        tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs,                          \
-                       oprsz, maxsz, &OPARRAY[vece]);                   \
-    }                                                                   \
-    DO_3SAME_NO_SZ_3(INSN, gen_##INSN##_3s)
-
-
-DO_3SAME_GVEC3_NO_SZ_3(VMLA, mla_op)
-DO_3SAME_GVEC3_NO_SZ_3(VMLS, mls_op)
-
 #define DO_3SAME_GVEC3_SHIFT(INSN, OPARRAY)                             \
     static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs,         \
                                 uint32_t rn_ofs, uint32_t rm_ofs,       \
diff --git a/target/arm/translate.c b/target/arm/translate.c
index 45df3743f6..52b6d32cf1 100644
--- a/target/arm/translate.c
+++ b/target/arm/translate.c
@@ -4520,62 +4520,69 @@  static void gen_mls_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b)
 /* Note that while NEON does not support VMLA and VMLS as 64-bit ops,
  * these tables are shared with AArch64 which does support them.
  */
+void gen_gvec_mla(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+                  uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_mul_vec, INDEX_op_add_vec, 0
+    };
+    static const GVecGen3 ops[4] = {
+        { .fni4 = gen_mla8_i32,
+          .fniv = gen_mla_vec,
+          .load_dest = true,
+          .opt_opc = vecop_list,
+          .vece = MO_8 },
+        { .fni4 = gen_mla16_i32,
+          .fniv = gen_mla_vec,
+          .load_dest = true,
+          .opt_opc = vecop_list,
+          .vece = MO_16 },
+        { .fni4 = gen_mla32_i32,
+          .fniv = gen_mla_vec,
+          .load_dest = true,
+          .opt_opc = vecop_list,
+          .vece = MO_32 },
+        { .fni8 = gen_mla64_i64,
+          .fniv = gen_mla_vec,
+          .prefer_i64 = TCG_TARGET_REG_BITS == 64,
+          .load_dest = true,
+          .opt_opc = vecop_list,
+          .vece = MO_64 },
+    };
+    tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]);
+}
 
-static const TCGOpcode vecop_list_mla[] = {
-    INDEX_op_mul_vec, INDEX_op_add_vec, 0
-};
-
-static const TCGOpcode vecop_list_mls[] = {
-    INDEX_op_mul_vec, INDEX_op_sub_vec, 0
-};
-
-const GVecGen3 mla_op[4] = {
-    { .fni4 = gen_mla8_i32,
-      .fniv = gen_mla_vec,
-      .load_dest = true,
-      .opt_opc = vecop_list_mla,
-      .vece = MO_8 },
-    { .fni4 = gen_mla16_i32,
-      .fniv = gen_mla_vec,
-      .load_dest = true,
-      .opt_opc = vecop_list_mla,
-      .vece = MO_16 },
-    { .fni4 = gen_mla32_i32,
-      .fniv = gen_mla_vec,
-      .load_dest = true,
-      .opt_opc = vecop_list_mla,
-      .vece = MO_32 },
-    { .fni8 = gen_mla64_i64,
-      .fniv = gen_mla_vec,
-      .prefer_i64 = TCG_TARGET_REG_BITS == 64,
-      .load_dest = true,
-      .opt_opc = vecop_list_mla,
-      .vece = MO_64 },
-};
-
-const GVecGen3 mls_op[4] = {
-    { .fni4 = gen_mls8_i32,
-      .fniv = gen_mls_vec,
-      .load_dest = true,
-      .opt_opc = vecop_list_mls,
-      .vece = MO_8 },
-    { .fni4 = gen_mls16_i32,
-      .fniv = gen_mls_vec,
-      .load_dest = true,
-      .opt_opc = vecop_list_mls,
-      .vece = MO_16 },
-    { .fni4 = gen_mls32_i32,
-      .fniv = gen_mls_vec,
-      .load_dest = true,
-      .opt_opc = vecop_list_mls,
-      .vece = MO_32 },
-    { .fni8 = gen_mls64_i64,
-      .fniv = gen_mls_vec,
-      .prefer_i64 = TCG_TARGET_REG_BITS == 64,
-      .load_dest = true,
-      .opt_opc = vecop_list_mls,
-      .vece = MO_64 },
-};
+void gen_gvec_mls(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+                  uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_mul_vec, INDEX_op_sub_vec, 0
+    };
+    static const GVecGen3 ops[4] = {
+        { .fni4 = gen_mls8_i32,
+          .fniv = gen_mls_vec,
+          .load_dest = true,
+          .opt_opc = vecop_list,
+          .vece = MO_8 },
+        { .fni4 = gen_mls16_i32,
+          .fniv = gen_mls_vec,
+          .load_dest = true,
+          .opt_opc = vecop_list,
+          .vece = MO_16 },
+        { .fni4 = gen_mls32_i32,
+          .fniv = gen_mls_vec,
+          .load_dest = true,
+          .opt_opc = vecop_list,
+          .vece = MO_32 },
+        { .fni8 = gen_mls64_i64,
+          .fniv = gen_mls_vec,
+          .prefer_i64 = TCG_TARGET_REG_BITS == 64,
+          .load_dest = true,
+          .opt_opc = vecop_list,
+          .vece = MO_64 },
+    };
+    tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]);
+}
 
 /* CMTST : test is "if (X & Y != 0)". */
 static void gen_cmtst_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)