target/arm: Convert handle_2misc_pairwise to decodetree

This includes SADDLP, UADDLP, SADALP, UADALP.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20241211163036.2297116-47-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode
index 05f1bc99b52b861e3784eb83fc259a54e17cc342..f3488766b21b57f7599fc8f42e3454f0c15f9135 100644 (file)
--- a/target/arm/tcg/a64.decode
+++ b/target/arm/tcg/a64.decode
@@ -1662,3 +1662,8 @@ CMLT0_v         0.00 1110 ..1 00000 10101 0 ..... .....     @qrr_e
 REV16_v         0.00 1110 001 00000 00011 0 ..... .....     @qrr_b
 REV32_v         0.10 1110 0.1 00000 00001 0 ..... .....     @qrr_bh
 REV64_v         0.00 1110 ..1 00000 00001 0 ..... .....     @qrr_e
+
+SADDLP_v        0.00 1110 ..1 00000 00101 0 ..... .....     @qrr_e
+UADDLP_v        0.10 1110 ..1 00000 00101 0 ..... .....     @qrr_e
+SADALP_v        0.00 1110 ..1 00000 01101 0 ..... .....     @qrr_e
+UADALP_v        0.10 1110 ..1 00000 01101 0 ..... .....     @qrr_e

diff --git a/target/arm/tcg/helper-a64.c b/target/arm/tcg/helper-a64.c
index 9b3c407be3cdd8c9b5a5898666d6a48b61ef020b..3de564e0fefd9bfeef38654a158c37cfe025ed50 100644 (file)
--- a/target/arm/tcg/helper-a64.c
+++ b/target/arm/tcg/helper-a64.c
@@ -306,24 +306,6 @@ float64 HELPER(rsqrtsf_f64)(float64 a, float64 b, void *fpstp)
     return float64_muladd(a, b, float64_three, float_muladd_halve_result, fpst);
 }
 
-uint64_t HELPER(neon_addlp_u8)(uint64_t a)
-{
-    uint64_t tmp;
-
-    tmp = a & 0x00ff00ff00ff00ffULL;
-    tmp += (a >> 8) & 0x00ff00ff00ff00ffULL;
-    return tmp;
-}
-
-uint64_t HELPER(neon_addlp_u16)(uint64_t a)
-{
-    uint64_t tmp;
-
-    tmp = a & 0x0000ffff0000ffffULL;
-    tmp += (a >> 16) & 0x0000ffff0000ffffULL;
-    return tmp;
-}
-
 /* Floating-point reciprocal exponent - see FPRecpX in ARM ARM */
 uint32_t HELPER(frecpx_f16)(uint32_t a, void *fpstp)
 {

diff --git a/target/arm/tcg/helper-a64.h b/target/arm/tcg/helper-a64.h
index f811bb85dcb06ce8961c2e3c7fb6a83b4755bcf3..ac7ca190fac66ee5f6045a088aaebb1b8ae42989 100644 (file)
--- a/target/arm/tcg/helper-a64.h
+++ b/target/arm/tcg/helper-a64.h
@@ -41,8 +41,6 @@ DEF_HELPER_FLAGS_3(recpsf_f64, TCG_CALL_NO_RWG, f64, f64, f64, ptr)
 DEF_HELPER_FLAGS_3(rsqrtsf_f16, TCG_CALL_NO_RWG, f16, f16, f16, ptr)
 DEF_HELPER_FLAGS_3(rsqrtsf_f32, TCG_CALL_NO_RWG, f32, f32, f32, ptr)
 DEF_HELPER_FLAGS_3(rsqrtsf_f64, TCG_CALL_NO_RWG, f64, f64, f64, ptr)
-DEF_HELPER_FLAGS_1(neon_addlp_u8, TCG_CALL_NO_RWG_SE, i64, i64)
-DEF_HELPER_FLAGS_1(neon_addlp_u16, TCG_CALL_NO_RWG_SE, i64, i64)
 DEF_HELPER_FLAGS_2(frecpx_f64, TCG_CALL_NO_RWG, f64, f64, ptr)
 DEF_HELPER_FLAGS_2(frecpx_f32, TCG_CALL_NO_RWG, f32, f32, ptr)
 DEF_HELPER_FLAGS_2(frecpx_f16, TCG_CALL_NO_RWG, f16, f16, ptr)

diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index f57b5e285560f5e30a2c946f7eb525ece5a238de..717d30dd5b9b15695dbd64bbfaae6f2b513efcf1 100644 (file)
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -8956,6 +8956,10 @@ static bool do_gvec_fn2_bhs(DisasContext *s, arg_qrr_e *a, GVecGen2Fn *fn)
 TRANS(CLS_v, do_gvec_fn2_bhs, a, gen_gvec_cls)
 TRANS(CLZ_v, do_gvec_fn2_bhs, a, gen_gvec_clz)
 TRANS(REV64_v, do_gvec_fn2_bhs, a, gen_gvec_rev64)
+TRANS(SADDLP_v, do_gvec_fn2_bhs, a, gen_gvec_saddlp)
+TRANS(UADDLP_v, do_gvec_fn2_bhs, a, gen_gvec_uaddlp)
+TRANS(SADALP_v, do_gvec_fn2_bhs, a, gen_gvec_sadalp)
+TRANS(UADALP_v, do_gvec_fn2_bhs, a, gen_gvec_uadalp)
 
 /* Common vector code for handling integer to FP conversion */
 static void handle_simd_intfp_conv(DisasContext *s, int rd, int rn,
@@ -9885,73 +9889,6 @@ static void handle_2misc_widening(DisasContext *s, int opcode, bool is_q,
     }
 }
 
-static void handle_2misc_pairwise(DisasContext *s, int opcode, bool u,
-                                  bool is_q, int size, int rn, int rd)
-{
-    /* Implement the pairwise operations from 2-misc:
-     * SADDLP, UADDLP, SADALP, UADALP.
-     * These all add pairs of elements in the input to produce a
-     * double-width result element in the output (possibly accumulating).
-     */
-    bool accum = (opcode == 0x6);
-    int maxpass = is_q ? 2 : 1;
-    int pass;
-    TCGv_i64 tcg_res[2];
-
-    if (size == 2) {
-        /* 32 + 32 -> 64 op */
-        MemOp memop = size + (u ? 0 : MO_SIGN);
-
-        for (pass = 0; pass < maxpass; pass++) {
-            TCGv_i64 tcg_op1 = tcg_temp_new_i64();
-            TCGv_i64 tcg_op2 = tcg_temp_new_i64();
-
-            tcg_res[pass] = tcg_temp_new_i64();
-
-            read_vec_element(s, tcg_op1, rn, pass * 2, memop);
-            read_vec_element(s, tcg_op2, rn, pass * 2 + 1, memop);
-            tcg_gen_add_i64(tcg_res[pass], tcg_op1, tcg_op2);
-            if (accum) {
-                read_vec_element(s, tcg_op1, rd, pass, MO_64);
-                tcg_gen_add_i64(tcg_res[pass], tcg_res[pass], tcg_op1);
-            }
-        }
-    } else {
-        for (pass = 0; pass < maxpass; pass++) {
-            TCGv_i64 tcg_op = tcg_temp_new_i64();
-            NeonGenOne64OpFn *genfn;
-            static NeonGenOne64OpFn * const fns[2][2] = {
-                { gen_helper_neon_addlp_s8,  gen_helper_neon_addlp_u8 },
-                { gen_helper_neon_addlp_s16,  gen_helper_neon_addlp_u16 },
-            };
-
-            genfn = fns[size][u];
-
-            tcg_res[pass] = tcg_temp_new_i64();
-
-            read_vec_element(s, tcg_op, rn, pass, MO_64);
-            genfn(tcg_res[pass], tcg_op);
-
-            if (accum) {
-                read_vec_element(s, tcg_op, rd, pass, MO_64);
-                if (size == 0) {
-                    gen_helper_neon_addl_u16(tcg_res[pass],
-                                             tcg_res[pass], tcg_op);
-                } else {
-                    gen_helper_neon_addl_u32(tcg_res[pass],
-                                             tcg_res[pass], tcg_op);
-                }
-            }
-        }
-    }
-    if (!is_q) {
-        tcg_res[1] = tcg_constant_i64(0);
-    }
-    for (pass = 0; pass < 2; pass++) {
-        write_vec_element(s, tcg_res[pass], rd, pass, MO_64);
-    }
-}
-
 static void handle_shll(DisasContext *s, bool is_q, int size, int rn, int rd)
 {
     /* Implement SHLL and SHLL2 */
@@ -10011,17 +9948,6 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn)
 
         handle_2misc_narrow(s, false, opcode, u, is_q, size, rn, rd);
         return;
-    case 0x2: /* SADDLP, UADDLP */
-    case 0x6: /* SADALP, UADALP */
-        if (size == 3) {
-            unallocated_encoding(s);
-            return;
-        }
-        if (!fp_access_check(s)) {
-            return;
-        }
-        handle_2misc_pairwise(s, opcode, u, is_q, size, rn, rd);
-        return;
     case 0x13: /* SHLL, SHLL2 */
         if (u == 0 || size == 3) {
             unallocated_encoding(s);
@@ -10203,9 +10129,11 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn)
     default:
     case 0x0: /* REV64, REV32 */
     case 0x1: /* REV16 */
+    case 0x2: /* SADDLP, UADDLP */
     case 0x3: /* SUQADD, USQADD */
     case 0x4: /* CLS, CLZ */
     case 0x5: /* CNT, NOT, RBIT */
+    case 0x6: /* SADALP, UADALP */
     case 0x7: /* SQABS, SQNEG */
     case 0x8: /* CMGT, CMGE */
     case 0x9: /* CMEQ, CMLE */