target/arm: Create gen_gvec_{ceq,clt,cle,cgt,cge}0

Provide a functional interface for the vector expansion.
This fits better with the existing set of helpers that
we provide for other operations.

Macro-ize the 5 nearly identical comparisons.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20200513163245.17915-7-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

3 files changed, 74 insertions, 218 deletions

diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index d5e77f34a7..fef93dc27a 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -577,14 +577,6 @@ static void gen_gvec_fn4(DisasContext *s, bool is_q, int rd, int rn, int rm,
             is_q ? 16 : 8, vec_full_reg_size(s));
 }
 
-/* Expand a 2-operand AdvSIMD vector operation using an op descriptor. */
-static void gen_gvec_op2(DisasContext *s, bool is_q, int rd,
-                         int rn, const GVecGen2 *gvec_op)
-{
-    tcg_gen_gvec_2(vec_full_reg_offset(s, rd), vec_full_reg_offset(s, rn),
-                   is_q ? 16 : 8, vec_full_reg_size(s), gvec_op);
-}
-
 /* Expand a 3-operand AdvSIMD vector operation using an op descriptor.  */
 static void gen_gvec_op3(DisasContext *s, bool is_q, int rd,
                          int rn, int rm, const GVecGen3 *gvec_op)
@@ -12310,13 +12302,21 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn)
         }
         break;
     case 0x8: /* CMGT, CMGE */
-        gen_gvec_op2(s, is_q, rd, rn, u ? &cge0_op[size] : &cgt0_op[size]);
+        if (u) {
+            gen_gvec_fn2(s, is_q, rd, rn, gen_gvec_cge0, size);
+        } else {
+            gen_gvec_fn2(s, is_q, rd, rn, gen_gvec_cgt0, size);
+        }
         return;
     case 0x9: /* CMEQ, CMLE */
-        gen_gvec_op2(s, is_q, rd, rn, u ? &cle0_op[size] : &ceq0_op[size]);
+        if (u) {
+            gen_gvec_fn2(s, is_q, rd, rn, gen_gvec_cle0, size);
+        } else {
+            gen_gvec_fn2(s, is_q, rd, rn, gen_gvec_ceq0, size);
+        }
         return;
     case 0xa: /* CMLT */
-        gen_gvec_op2(s, is_q, rd, rn, &clt0_op[size]);
+        gen_gvec_fn2(s, is_q, rd, rn, gen_gvec_clt0, size);
         return;
     case 0xb:
         if (u) { /* ABS, NEG */
diff --git a/target/arm/translate.c b/target/arm/translate.c
index 2eec689c5e..010a158e63 100644
--- a/target/arm/translate.c
+++ b/target/arm/translate.c
@@ -3645,204 +3645,59 @@ static int do_v81_helper(DisasContext *s, gen_helper_gvec_3_ptr *fn,
     return 1;
 }
 
-static void gen_ceq0_i32(TCGv_i32 d, TCGv_i32 a)
-{
-    tcg_gen_setcondi_i32(TCG_COND_EQ, d, a, 0);
-    tcg_gen_neg_i32(d, d);
-}
-
-static void gen_ceq0_i64(TCGv_i64 d, TCGv_i64 a)
-{
-    tcg_gen_setcondi_i64(TCG_COND_EQ, d, a, 0);
-    tcg_gen_neg_i64(d, d);
-}
-
-static void gen_ceq0_vec(unsigned vece, TCGv_vec d, TCGv_vec a)
-{
-    TCGv_vec zero = tcg_const_zeros_vec_matching(d);
-    tcg_gen_cmp_vec(TCG_COND_EQ, vece, d, a, zero);
-    tcg_temp_free_vec(zero);
-}
+#define GEN_CMP0(NAME, COND)                                            \
+    static void gen_##NAME##0_i32(TCGv_i32 d, TCGv_i32 a)               \
+    {                                                                   \
+        tcg_gen_setcondi_i32(COND, d, a, 0);                            \
+        tcg_gen_neg_i32(d, d);                                          \
+    }                                                                   \
+    static void gen_##NAME##0_i64(TCGv_i64 d, TCGv_i64 a)               \
+    {                                                                   \
+        tcg_gen_setcondi_i64(COND, d, a, 0);                            \
+        tcg_gen_neg_i64(d, d);                                          \
+    }                                                                   \
+    static void gen_##NAME##0_vec(unsigned vece, TCGv_vec d, TCGv_vec a) \
+    {                                                                   \
+        TCGv_vec zero = tcg_const_zeros_vec_matching(d);                \
+        tcg_gen_cmp_vec(COND, vece, d, a, zero);                        \
+        tcg_temp_free_vec(zero);                                        \
+    }                                                                   \
+    void gen_gvec_##NAME##0(unsigned vece, uint32_t d, uint32_t m,      \
+                            uint32_t opr_sz, uint32_t max_sz)           \
+    {                                                                   \
+        const GVecGen2 op[4] = {                                        \
+            { .fno = gen_helper_gvec_##NAME##0_b,                       \
+              .fniv = gen_##NAME##0_vec,                                \
+              .opt_opc = vecop_list_cmp,                                \
+              .vece = MO_8 },                                           \
+            { .fno = gen_helper_gvec_##NAME##0_h,                       \
+              .fniv = gen_##NAME##0_vec,                                \
+              .opt_opc = vecop_list_cmp,                                \
+              .vece = MO_16 },                                          \
+            { .fni4 = gen_##NAME##0_i32,                                \
+              .fniv = gen_##NAME##0_vec,                                \
+              .opt_opc = vecop_list_cmp,                                \
+              .vece = MO_32 },                                          \
+            { .fni8 = gen_##NAME##0_i64,                                \
+              .fniv = gen_##NAME##0_vec,                                \
+              .opt_opc = vecop_list_cmp,                                \
+              .prefer_i64 = TCG_TARGET_REG_BITS == 64,                  \
+              .vece = MO_64 },                                          \
+        };                                                              \
+        tcg_gen_gvec_2(d, m, opr_sz, max_sz, &op[vece]);                \
+    }
 
 static const TCGOpcode vecop_list_cmp[] = {
     INDEX_op_cmp_vec, 0
 };
 
-const GVecGen2 ceq0_op[4] = {
-    { .fno = gen_helper_gvec_ceq0_b,
-      .fniv = gen_ceq0_vec,
-      .opt_opc = vecop_list_cmp,
-      .vece = MO_8 },
-    { .fno = gen_helper_gvec_ceq0_h,
-      .fniv = gen_ceq0_vec,
-      .opt_opc = vecop_list_cmp,
-      .vece = MO_16 },
-    { .fni4 = gen_ceq0_i32,
-      .fniv = gen_ceq0_vec,
-      .opt_opc = vecop_list_cmp,
-      .vece = MO_32 },
-    { .fni8 = gen_ceq0_i64,
-      .fniv = gen_ceq0_vec,
-      .opt_opc = vecop_list_cmp,
-      .prefer_i64 = TCG_TARGET_REG_BITS == 64,
-      .vece = MO_64 },
-};
-
-static void gen_cle0_i32(TCGv_i32 d, TCGv_i32 a)
-{
-    tcg_gen_setcondi_i32(TCG_COND_LE, d, a, 0);
-    tcg_gen_neg_i32(d, d);
-}
-
-static void gen_cle0_i64(TCGv_i64 d, TCGv_i64 a)
-{
-    tcg_gen_setcondi_i64(TCG_COND_LE, d, a, 0);
-    tcg_gen_neg_i64(d, d);
-}
-
-static void gen_cle0_vec(unsigned vece, TCGv_vec d, TCGv_vec a)
-{
-    TCGv_vec zero = tcg_const_zeros_vec_matching(d);
-    tcg_gen_cmp_vec(TCG_COND_LE, vece, d, a, zero);
-    tcg_temp_free_vec(zero);
-}
-
-const GVecGen2 cle0_op[4] = {
-    { .fno = gen_helper_gvec_cle0_b,
-      .fniv = gen_cle0_vec,
-      .opt_opc = vecop_list_cmp,
-      .vece = MO_8 },
-    { .fno = gen_helper_gvec_cle0_h,
-      .fniv = gen_cle0_vec,
-      .opt_opc = vecop_list_cmp,
-      .vece = MO_16 },
-    { .fni4 = gen_cle0_i32,
-      .fniv = gen_cle0_vec,
-      .opt_opc = vecop_list_cmp,
-      .vece = MO_32 },
-    { .fni8 = gen_cle0_i64,
-      .fniv = gen_cle0_vec,
-      .opt_opc = vecop_list_cmp,
-      .prefer_i64 = TCG_TARGET_REG_BITS == 64,
-      .vece = MO_64 },
-};
-
-static void gen_cge0_i32(TCGv_i32 d, TCGv_i32 a)
-{
-    tcg_gen_setcondi_i32(TCG_COND_GE, d, a, 0);
-    tcg_gen_neg_i32(d, d);
-}
-
-static void gen_cge0_i64(TCGv_i64 d, TCGv_i64 a)
-{
-    tcg_gen_setcondi_i64(TCG_COND_GE, d, a, 0);
-    tcg_gen_neg_i64(d, d);
-}
-
-static void gen_cge0_vec(unsigned vece, TCGv_vec d, TCGv_vec a)
-{
-    TCGv_vec zero = tcg_const_zeros_vec_matching(d);
-    tcg_gen_cmp_vec(TCG_COND_GE, vece, d, a, zero);
-    tcg_temp_free_vec(zero);
-}
-
-const GVecGen2 cge0_op[4] = {
-    { .fno = gen_helper_gvec_cge0_b,
-      .fniv = gen_cge0_vec,
-      .opt_opc = vecop_list_cmp,
-      .vece = MO_8 },
-    { .fno = gen_helper_gvec_cge0_h,
-      .fniv = gen_cge0_vec,
-      .opt_opc = vecop_list_cmp,
-      .vece = MO_16 },
-    { .fni4 = gen_cge0_i32,
-      .fniv = gen_cge0_vec,
-      .opt_opc = vecop_list_cmp,
-      .vece = MO_32 },
-    { .fni8 = gen_cge0_i64,
-      .fniv = gen_cge0_vec,
-      .opt_opc = vecop_list_cmp,
-      .prefer_i64 = TCG_TARGET_REG_BITS == 64,
-      .vece = MO_64 },
-};
-
-static void gen_clt0_i32(TCGv_i32 d, TCGv_i32 a)
-{
-    tcg_gen_setcondi_i32(TCG_COND_LT, d, a, 0);
-    tcg_gen_neg_i32(d, d);
-}
-
-static void gen_clt0_i64(TCGv_i64 d, TCGv_i64 a)
-{
-    tcg_gen_setcondi_i64(TCG_COND_LT, d, a, 0);
-    tcg_gen_neg_i64(d, d);
-}
-
-static void gen_clt0_vec(unsigned vece, TCGv_vec d, TCGv_vec a)
-{
-    TCGv_vec zero = tcg_const_zeros_vec_matching(d);
-    tcg_gen_cmp_vec(TCG_COND_LT, vece, d, a, zero);
-    tcg_temp_free_vec(zero);
-}
-
-const GVecGen2 clt0_op[4] = {
-    { .fno = gen_helper_gvec_clt0_b,
-      .fniv = gen_clt0_vec,
-      .opt_opc = vecop_list_cmp,
-      .vece = MO_8 },
-    { .fno = gen_helper_gvec_clt0_h,
-      .fniv = gen_clt0_vec,
-      .opt_opc = vecop_list_cmp,
-      .vece = MO_16 },
-    { .fni4 = gen_clt0_i32,
-      .fniv = gen_clt0_vec,
-      .opt_opc = vecop_list_cmp,
-      .vece = MO_32 },
-    { .fni8 = gen_clt0_i64,
-      .fniv = gen_clt0_vec,
-      .opt_opc = vecop_list_cmp,
-      .prefer_i64 = TCG_TARGET_REG_BITS == 64,
-      .vece = MO_64 },
-};
-
-static void gen_cgt0_i32(TCGv_i32 d, TCGv_i32 a)
-{
-    tcg_gen_setcondi_i32(TCG_COND_GT, d, a, 0);
-    tcg_gen_neg_i32(d, d);
-}
-
-static void gen_cgt0_i64(TCGv_i64 d, TCGv_i64 a)
-{
-    tcg_gen_setcondi_i64(TCG_COND_GT, d, a, 0);
-    tcg_gen_neg_i64(d, d);
-}
-
-static void gen_cgt0_vec(unsigned vece, TCGv_vec d, TCGv_vec a)
-{
-    TCGv_vec zero = tcg_const_zeros_vec_matching(d);
-    tcg_gen_cmp_vec(TCG_COND_GT, vece, d, a, zero);
-    tcg_temp_free_vec(zero);
-}
+GEN_CMP0(ceq, TCG_COND_EQ)
+GEN_CMP0(cle, TCG_COND_LE)
+GEN_CMP0(cge, TCG_COND_GE)
+GEN_CMP0(clt, TCG_COND_LT)
+GEN_CMP0(cgt, TCG_COND_GT)
 
-const GVecGen2 cgt0_op[4] = {
-    { .fno = gen_helper_gvec_cgt0_b,
-      .fniv = gen_cgt0_vec,
-      .opt_opc = vecop_list_cmp,
-      .vece = MO_8 },
-    { .fno = gen_helper_gvec_cgt0_h,
-      .fniv = gen_cgt0_vec,
-      .opt_opc = vecop_list_cmp,
-      .vece = MO_16 },
-    { .fni4 = gen_cgt0_i32,
-      .fniv = gen_cgt0_vec,
-      .opt_opc = vecop_list_cmp,
-      .vece = MO_32 },
-    { .fni8 = gen_cgt0_i64,
-      .fniv = gen_cgt0_vec,
-      .opt_opc = vecop_list_cmp,
-      .prefer_i64 = TCG_TARGET_REG_BITS == 64,
-      .vece = MO_64 },
-};
+#undef GEN_CMP0
 
 static void gen_ssra8_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift)
 {
@@ -6772,24 +6627,19 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
                     break;
 
                 case NEON_2RM_VCEQ0:
-                    tcg_gen_gvec_2(rd_ofs, rm_ofs, vec_size,
-                                   vec_size, &ceq0_op[size]);
+                    gen_gvec_ceq0(size, rd_ofs, rm_ofs, vec_size, vec_size);
                     break;
                 case NEON_2RM_VCGT0:
-                    tcg_gen_gvec_2(rd_ofs, rm_ofs, vec_size,
-                                   vec_size, &cgt0_op[size]);
+                    gen_gvec_cgt0(size, rd_ofs, rm_ofs, vec_size, vec_size);
                     break;
                 case NEON_2RM_VCLE0:
-                    tcg_gen_gvec_2(rd_ofs, rm_ofs, vec_size,
-                                   vec_size, &cle0_op[size]);
+                    gen_gvec_cle0(size, rd_ofs, rm_ofs, vec_size, vec_size);
                     break;
                 case NEON_2RM_VCGE0:
-                    tcg_gen_gvec_2(rd_ofs, rm_ofs, vec_size,
-                                   vec_size, &cge0_op[size]);
+                    gen_gvec_cge0(size, rd_ofs, rm_ofs, vec_size, vec_size);
                     break;
                 case NEON_2RM_VCLT0:
-                    tcg_gen_gvec_2(rd_ofs, rm_ofs, vec_size,
-                                   vec_size, &clt0_op[size]);
+                    gen_gvec_clt0(size, rd_ofs, rm_ofs, vec_size, vec_size);
                     break;
 
                 default:
diff --git a/target/arm/translate.h b/target/arm/translate.h
index fa5c3f12b9..e35c812cc5 100644
--- a/target/arm/translate.h
+++ b/target/arm/translate.h
@@ -275,11 +275,17 @@ static inline void gen_swstep_exception(DisasContext *s, int isv, int ex)
 uint64_t vfp_expand_imm(int size, uint8_t imm8);
 
 /* Vector operations shared between ARM and AArch64.  */
-extern const GVecGen2 ceq0_op[4];
-extern const GVecGen2 clt0_op[4];
-extern const GVecGen2 cgt0_op[4];
-extern const GVecGen2 cle0_op[4];
-extern const GVecGen2 cge0_op[4];
+void gen_gvec_ceq0(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
+                   uint32_t opr_sz, uint32_t max_sz);
+void gen_gvec_clt0(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
+                   uint32_t opr_sz, uint32_t max_sz);
+void gen_gvec_cgt0(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
+                   uint32_t opr_sz, uint32_t max_sz);
+void gen_gvec_cle0(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
+                   uint32_t opr_sz, uint32_t max_sz);
+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];
 extern const GVecGen3 cmtst_op[4];