[v4,10/16] target/arm: Create gen_gvec_{uqadd, sqadd, uqsub, sqsub}

Message ID 20200513163245.17915-11-richard.henderson@linaro.org
State New
Headers show
Series
  • target/arm: partial vector cleanup
Related show

Commit Message

Richard Henderson May 13, 2020, 4:32 p.m.
Provide a functional interface for the vector expansion.
This fits better with the existing set of helpers that
we provide for other operations.

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

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

---
 target/arm/translate.h          |  13 +-
 target/arm/translate-a64.c      |  22 ++-
 target/arm/translate-neon.inc.c |  19 +--
 target/arm/translate.c          | 228 +++++++++++++++++---------------
 4 files changed, 147 insertions(+), 135 deletions(-)

-- 
2.20.1

Patch

diff --git a/target/arm/translate.h b/target/arm/translate.h
index a02a54cabf..4e1778c5e0 100644
--- a/target/arm/translate.h
+++ b/target/arm/translate.h
@@ -298,16 +298,21 @@  void gen_gvec_sshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
 void gen_gvec_ushl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
                    uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz);
 
-extern const GVecGen4 uqadd_op[4];
-extern const GVecGen4 sqadd_op[4];
-extern const GVecGen4 uqsub_op[4];
-extern const GVecGen4 sqsub_op[4];
 void gen_cmtst_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b);
 void gen_ushl_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b);
 void gen_sshl_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b);
 void gen_ushl_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b);
 void gen_sshl_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b);
 
+void gen_gvec_uqadd_qc(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_sqadd_qc(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_uqsub_qc(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_sqsub_qc(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_ssra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
                    int64_t shift, uint32_t opr_sz, uint32_t max_sz);
 void gen_gvec_usra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index 3956c19ed8..ea5f6ceadc 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -11168,20 +11168,18 @@  static void disas_simd_3same_int(DisasContext *s, uint32_t insn)
 
     switch (opcode) {
     case 0x01: /* SQADD, UQADD */
-        tcg_gen_gvec_4(vec_full_reg_offset(s, rd),
-                       offsetof(CPUARMState, vfp.qc),
-                       vec_full_reg_offset(s, rn),
-                       vec_full_reg_offset(s, rm),
-                       is_q ? 16 : 8, vec_full_reg_size(s),
-                       (u ? uqadd_op : sqadd_op) + size);
+        if (u) {
+            gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_uqadd_qc, size);
+        } else {
+            gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_sqadd_qc, size);
+        }
         return;
     case 0x05: /* SQSUB, UQSUB */
-        tcg_gen_gvec_4(vec_full_reg_offset(s, rd),
-                       offsetof(CPUARMState, vfp.qc),
-                       vec_full_reg_offset(s, rn),
-                       vec_full_reg_offset(s, rm),
-                       is_q ? 16 : 8, vec_full_reg_size(s),
-                       (u ? uqsub_op : sqsub_op) + size);
+        if (u) {
+            gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_uqsub_qc, size);
+        } else {
+            gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_sqsub_qc, size);
+        }
         return;
     case 0x08: /* SSHL, USHL */
         if (u) {
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
index e16475c212..099491b16f 100644
--- a/target/arm/translate-neon.inc.c
+++ b/target/arm/translate-neon.inc.c
@@ -605,6 +605,10 @@  DO_3SAME(VORN, tcg_gen_gvec_orc)
 DO_3SAME(VEOR, tcg_gen_gvec_xor)
 DO_3SAME(VSHL_S, gen_gvec_sshl)
 DO_3SAME(VSHL_U, gen_gvec_ushl)
+DO_3SAME(VQADD_S, gen_gvec_sqadd_qc)
+DO_3SAME(VQADD_U, gen_gvec_uqadd_qc)
+DO_3SAME(VQSUB_S, gen_gvec_sqsub_qc)
+DO_3SAME(VQSUB_U, gen_gvec_uqsub_qc)
 
 /* These insns are all gvec_bitsel but with the inputs in various orders. */
 #define DO_3SAME_BITSEL(INSN, O1, O2, O3)                               \
@@ -653,21 +657,6 @@  DO_3SAME_CMP(VCGE_S, TCG_COND_GE)
 DO_3SAME_CMP(VCGE_U, TCG_COND_GEU)
 DO_3SAME_CMP(VCEQ, TCG_COND_EQ)
 
-#define DO_3SAME_GVEC4(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_4(rd_ofs, offsetof(CPUARMState, vfp.qc),           \
-                       rn_ofs, rm_ofs, oprsz, maxsz, &OPARRAY[vece]);   \
-    }                                                                   \
-    DO_3SAME(INSN, gen_##INSN##_3s)
-
-DO_3SAME_GVEC4(VQADD_S, sqadd_op)
-DO_3SAME_GVEC4(VQADD_U, uqadd_op)
-DO_3SAME_GVEC4(VQSUB_S, sqsub_op)
-DO_3SAME_GVEC4(VQSUB_U, uqsub_op)
-
 static void gen_VMUL_p_3s(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
                            uint32_t rm_ofs, uint32_t oprsz, uint32_t maxsz)
 {
diff --git a/target/arm/translate.c b/target/arm/translate.c
index df91ff73e3..7eb30cde60 100644
--- a/target/arm/translate.c
+++ b/target/arm/translate.c
@@ -4925,32 +4925,37 @@  static void gen_uqadd_vec(unsigned vece, TCGv_vec t, TCGv_vec sat,
     tcg_temp_free_vec(x);
 }
 
-static const TCGOpcode vecop_list_uqadd[] = {
-    INDEX_op_usadd_vec, INDEX_op_cmp_vec, INDEX_op_add_vec, 0
-};
-
-const GVecGen4 uqadd_op[4] = {
-    { .fniv = gen_uqadd_vec,
-      .fno = gen_helper_gvec_uqadd_b,
-      .write_aofs = true,
-      .opt_opc = vecop_list_uqadd,
-      .vece = MO_8 },
-    { .fniv = gen_uqadd_vec,
-      .fno = gen_helper_gvec_uqadd_h,
-      .write_aofs = true,
-      .opt_opc = vecop_list_uqadd,
-      .vece = MO_16 },
-    { .fniv = gen_uqadd_vec,
-      .fno = gen_helper_gvec_uqadd_s,
-      .write_aofs = true,
-      .opt_opc = vecop_list_uqadd,
-      .vece = MO_32 },
-    { .fniv = gen_uqadd_vec,
-      .fno = gen_helper_gvec_uqadd_d,
-      .write_aofs = true,
-      .opt_opc = vecop_list_uqadd,
-      .vece = MO_64 },
-};
+void gen_gvec_uqadd_qc(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_usadd_vec, INDEX_op_cmp_vec, INDEX_op_add_vec, 0
+    };
+    static const GVecGen4 ops[4] = {
+        { .fniv = gen_uqadd_vec,
+          .fno = gen_helper_gvec_uqadd_b,
+          .write_aofs = true,
+          .opt_opc = vecop_list,
+          .vece = MO_8 },
+        { .fniv = gen_uqadd_vec,
+          .fno = gen_helper_gvec_uqadd_h,
+          .write_aofs = true,
+          .opt_opc = vecop_list,
+          .vece = MO_16 },
+        { .fniv = gen_uqadd_vec,
+          .fno = gen_helper_gvec_uqadd_s,
+          .write_aofs = true,
+          .opt_opc = vecop_list,
+          .vece = MO_32 },
+        { .fniv = gen_uqadd_vec,
+          .fno = gen_helper_gvec_uqadd_d,
+          .write_aofs = true,
+          .opt_opc = vecop_list,
+          .vece = MO_64 },
+    };
+    tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc),
+                   rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]);
+}
 
 static void gen_sqadd_vec(unsigned vece, TCGv_vec t, TCGv_vec sat,
                           TCGv_vec a, TCGv_vec b)
@@ -4963,32 +4968,37 @@  static void gen_sqadd_vec(unsigned vece, TCGv_vec t, TCGv_vec sat,
     tcg_temp_free_vec(x);
 }
 
-static const TCGOpcode vecop_list_sqadd[] = {
-    INDEX_op_ssadd_vec, INDEX_op_cmp_vec, INDEX_op_add_vec, 0
-};
-
-const GVecGen4 sqadd_op[4] = {
-    { .fniv = gen_sqadd_vec,
-      .fno = gen_helper_gvec_sqadd_b,
-      .opt_opc = vecop_list_sqadd,
-      .write_aofs = true,
-      .vece = MO_8 },
-    { .fniv = gen_sqadd_vec,
-      .fno = gen_helper_gvec_sqadd_h,
-      .opt_opc = vecop_list_sqadd,
-      .write_aofs = true,
-      .vece = MO_16 },
-    { .fniv = gen_sqadd_vec,
-      .fno = gen_helper_gvec_sqadd_s,
-      .opt_opc = vecop_list_sqadd,
-      .write_aofs = true,
-      .vece = MO_32 },
-    { .fniv = gen_sqadd_vec,
-      .fno = gen_helper_gvec_sqadd_d,
-      .opt_opc = vecop_list_sqadd,
-      .write_aofs = true,
-      .vece = MO_64 },
-};
+void gen_gvec_sqadd_qc(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_ssadd_vec, INDEX_op_cmp_vec, INDEX_op_add_vec, 0
+    };
+    static const GVecGen4 ops[4] = {
+        { .fniv = gen_sqadd_vec,
+          .fno = gen_helper_gvec_sqadd_b,
+          .opt_opc = vecop_list,
+          .write_aofs = true,
+          .vece = MO_8 },
+        { .fniv = gen_sqadd_vec,
+          .fno = gen_helper_gvec_sqadd_h,
+          .opt_opc = vecop_list,
+          .write_aofs = true,
+          .vece = MO_16 },
+        { .fniv = gen_sqadd_vec,
+          .fno = gen_helper_gvec_sqadd_s,
+          .opt_opc = vecop_list,
+          .write_aofs = true,
+          .vece = MO_32 },
+        { .fniv = gen_sqadd_vec,
+          .fno = gen_helper_gvec_sqadd_d,
+          .opt_opc = vecop_list,
+          .write_aofs = true,
+          .vece = MO_64 },
+    };
+    tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc),
+                   rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]);
+}
 
 static void gen_uqsub_vec(unsigned vece, TCGv_vec t, TCGv_vec sat,
                           TCGv_vec a, TCGv_vec b)
@@ -5001,32 +5011,37 @@  static void gen_uqsub_vec(unsigned vece, TCGv_vec t, TCGv_vec sat,
     tcg_temp_free_vec(x);
 }
 
-static const TCGOpcode vecop_list_uqsub[] = {
-    INDEX_op_ussub_vec, INDEX_op_cmp_vec, INDEX_op_sub_vec, 0
-};
-
-const GVecGen4 uqsub_op[4] = {
-    { .fniv = gen_uqsub_vec,
-      .fno = gen_helper_gvec_uqsub_b,
-      .opt_opc = vecop_list_uqsub,
-      .write_aofs = true,
-      .vece = MO_8 },
-    { .fniv = gen_uqsub_vec,
-      .fno = gen_helper_gvec_uqsub_h,
-      .opt_opc = vecop_list_uqsub,
-      .write_aofs = true,
-      .vece = MO_16 },
-    { .fniv = gen_uqsub_vec,
-      .fno = gen_helper_gvec_uqsub_s,
-      .opt_opc = vecop_list_uqsub,
-      .write_aofs = true,
-      .vece = MO_32 },
-    { .fniv = gen_uqsub_vec,
-      .fno = gen_helper_gvec_uqsub_d,
-      .opt_opc = vecop_list_uqsub,
-      .write_aofs = true,
-      .vece = MO_64 },
-};
+void gen_gvec_uqsub_qc(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_ussub_vec, INDEX_op_cmp_vec, INDEX_op_sub_vec, 0
+    };
+    static const GVecGen4 ops[4] = {
+        { .fniv = gen_uqsub_vec,
+          .fno = gen_helper_gvec_uqsub_b,
+          .opt_opc = vecop_list,
+          .write_aofs = true,
+          .vece = MO_8 },
+        { .fniv = gen_uqsub_vec,
+          .fno = gen_helper_gvec_uqsub_h,
+          .opt_opc = vecop_list,
+          .write_aofs = true,
+          .vece = MO_16 },
+        { .fniv = gen_uqsub_vec,
+          .fno = gen_helper_gvec_uqsub_s,
+          .opt_opc = vecop_list,
+          .write_aofs = true,
+          .vece = MO_32 },
+        { .fniv = gen_uqsub_vec,
+          .fno = gen_helper_gvec_uqsub_d,
+          .opt_opc = vecop_list,
+          .write_aofs = true,
+          .vece = MO_64 },
+    };
+    tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc),
+                   rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]);
+}
 
 static void gen_sqsub_vec(unsigned vece, TCGv_vec t, TCGv_vec sat,
                           TCGv_vec a, TCGv_vec b)
@@ -5039,32 +5054,37 @@  static void gen_sqsub_vec(unsigned vece, TCGv_vec t, TCGv_vec sat,
     tcg_temp_free_vec(x);
 }
 
-static const TCGOpcode vecop_list_sqsub[] = {
-    INDEX_op_sssub_vec, INDEX_op_cmp_vec, INDEX_op_sub_vec, 0
-};
-
-const GVecGen4 sqsub_op[4] = {
-    { .fniv = gen_sqsub_vec,
-      .fno = gen_helper_gvec_sqsub_b,
-      .opt_opc = vecop_list_sqsub,
-      .write_aofs = true,
-      .vece = MO_8 },
-    { .fniv = gen_sqsub_vec,
-      .fno = gen_helper_gvec_sqsub_h,
-      .opt_opc = vecop_list_sqsub,
-      .write_aofs = true,
-      .vece = MO_16 },
-    { .fniv = gen_sqsub_vec,
-      .fno = gen_helper_gvec_sqsub_s,
-      .opt_opc = vecop_list_sqsub,
-      .write_aofs = true,
-      .vece = MO_32 },
-    { .fniv = gen_sqsub_vec,
-      .fno = gen_helper_gvec_sqsub_d,
-      .opt_opc = vecop_list_sqsub,
-      .write_aofs = true,
-      .vece = MO_64 },
-};
+void gen_gvec_sqsub_qc(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_sssub_vec, INDEX_op_cmp_vec, INDEX_op_sub_vec, 0
+    };
+    static const GVecGen4 ops[4] = {
+        { .fniv = gen_sqsub_vec,
+          .fno = gen_helper_gvec_sqsub_b,
+          .opt_opc = vecop_list,
+          .write_aofs = true,
+          .vece = MO_8 },
+        { .fniv = gen_sqsub_vec,
+          .fno = gen_helper_gvec_sqsub_h,
+          .opt_opc = vecop_list,
+          .write_aofs = true,
+          .vece = MO_16 },
+        { .fniv = gen_sqsub_vec,
+          .fno = gen_helper_gvec_sqsub_s,
+          .opt_opc = vecop_list,
+          .write_aofs = true,
+          .vece = MO_32 },
+        { .fniv = gen_sqsub_vec,
+          .fno = gen_helper_gvec_sqsub_d,
+          .opt_opc = vecop_list,
+          .write_aofs = true,
+          .vece = MO_64 },
+    };
+    tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc),
+                   rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]);
+}
 
 /* Translate a NEON data processing instruction.  Return nonzero if the
    instruction is invalid.