[Qemu-devel] [PATCH for-2.0 v2 1/2] target-arm: A64: Add saturating int ops (SQNEG/SQABS)

[Peter Maydell <peter.maydell@linaro.org>]

From: Alex Bennée <alex.bennee@linaro.org>

This mostly re-uses the existing NEON helpers with an additional two for
the 64 bit case. I also took the opportunity to add TCG_CALL_NO_RWG
options to the helpers as they don't modify globals (saturation flags
are in the CPU Environment).

Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <rth@twiddle.net>
---
 target-arm/helper.h        | 14 +++++++------
 target-arm/neon_helper.c   | 22 ++++++++++++++++++++
 target-arm/translate-a64.c | 51 ++++++++++++++++++++++++++++++++++++++++------
 3 files changed, 75 insertions(+), 12 deletions(-)

diff --git a/target-arm/helper.h b/target-arm/helper.h
index a3d6f32..b006fd5 100644
--- a/target-arm/helper.h
+++ b/target-arm/helper.h
@@ -375,12 +375,14 @@ DEF_HELPER_2(neon_mull_s16, i64, i32, i32)
 DEF_HELPER_1(neon_negl_u16, i64, i64)
 DEF_HELPER_1(neon_negl_u32, i64, i64)
 
-DEF_HELPER_2(neon_qabs_s8, i32, env, i32)
-DEF_HELPER_2(neon_qabs_s16, i32, env, i32)
-DEF_HELPER_2(neon_qabs_s32, i32, env, i32)
-DEF_HELPER_2(neon_qneg_s8, i32, env, i32)
-DEF_HELPER_2(neon_qneg_s16, i32, env, i32)
-DEF_HELPER_2(neon_qneg_s32, i32, env, i32)
+DEF_HELPER_FLAGS_2(neon_qabs_s8, TCG_CALL_NO_RWG, i32, env, i32)
+DEF_HELPER_FLAGS_2(neon_qabs_s16, TCG_CALL_NO_RWG, i32, env, i32)
+DEF_HELPER_FLAGS_2(neon_qabs_s32, TCG_CALL_NO_RWG, i32, env, i32)
+DEF_HELPER_FLAGS_2(neon_qabs_s64, TCG_CALL_NO_RWG, i64, env, i64)
+DEF_HELPER_FLAGS_2(neon_qneg_s8, TCG_CALL_NO_RWG, i32, env, i32)
+DEF_HELPER_FLAGS_2(neon_qneg_s16, TCG_CALL_NO_RWG, i32, env, i32)
+DEF_HELPER_FLAGS_2(neon_qneg_s32, TCG_CALL_NO_RWG, i32, env, i32)
+DEF_HELPER_FLAGS_2(neon_qneg_s64, TCG_CALL_NO_RWG, i64, env, i64)
 
 DEF_HELPER_3(neon_abd_f32, i32, i32, i32, ptr)
 DEF_HELPER_3(neon_ceq_f32, i32, i32, i32, ptr)
diff --git a/target-arm/neon_helper.c b/target-arm/neon_helper.c
index 13752ba..e23f224 100644
--- a/target-arm/neon_helper.c
+++ b/target-arm/neon_helper.c
@@ -1776,6 +1776,28 @@ uint32_t HELPER(neon_qneg_s32)(CPUARMState *env, uint32_t x)
     return x;
 }
 
+uint64_t HELPER(neon_qabs_s64)(CPUARMState *env, uint64_t x)
+{
+    if (x == SIGNBIT64) {
+        SET_QC();
+        x = ~SIGNBIT64;
+    } else if ((int64_t)x < 0) {
+        x = -x;
+    }
+    return x;
+}
+
+uint64_t HELPER(neon_qneg_s64)(CPUARMState *env, uint64_t x)
+{
+    if (x == SIGNBIT64) {
+        SET_QC();
+        x = ~SIGNBIT64;
+    } else {
+        x = -x;
+    }
+    return x;
+}
+
 /* NEON Float helpers.  */
 uint32_t HELPER(neon_abd_f32)(uint32_t a, uint32_t b, void *fpstp)
 {
diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index befffac..18659d7 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -73,6 +73,7 @@ typedef struct AArch64DecodeTable {
 } AArch64DecodeTable;
 
 /* Function prototype for gen_ functions for calling Neon helpers */
+typedef void NeonGenOneOpEnvFn(TCGv_i32, TCGv_ptr, TCGv_i32);
 typedef void NeonGenTwoOpFn(TCGv_i32, TCGv_i32, TCGv_i32);
 typedef void NeonGenTwoOpEnvFn(TCGv_i32, TCGv_ptr, TCGv_i32, TCGv_i32);
 typedef void NeonGenTwo64OpFn(TCGv_i64, TCGv_i64, TCGv_i64);
@@ -6942,6 +6943,13 @@ static void handle_2misc_64(DisasContext *s, int opcode, bool u,
          */
         tcg_gen_not_i64(tcg_rd, tcg_rn);
         break;
+    case 0x7: /* SQABS, SQNEG */
+        if (u) {
+            gen_helper_neon_qneg_s64(tcg_rd, cpu_env, tcg_rn);
+        } else {
+            gen_helper_neon_qabs_s64(tcg_rd, cpu_env, tcg_rn);
+        }
+        break;
     case 0xa: /* CMLT */
         /* 64 bit integer comparison against zero, result is
          * test ? (2^64 - 1) : 0. We implement via setcond(!test) and
@@ -7332,6 +7340,8 @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn)
     TCGv_ptr tcg_fpstatus;
 
     switch (opcode) {
+    case 0x7: /* SQABS / SQNEG */
+        break;
     case 0xa: /* CMLT */
         if (u) {
             unallocated_encoding(s);
@@ -7441,11 +7451,25 @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn)
         write_fp_dreg(s, rd, tcg_rd);
         tcg_temp_free_i64(tcg_rd);
         tcg_temp_free_i64(tcg_rn);
-    } else if (size == 2) {
-        TCGv_i32 tcg_rn = read_fp_sreg(s, rn);
+    } else {
+        TCGv_i32 tcg_rn = tcg_temp_new_i32();
         TCGv_i32 tcg_rd = tcg_temp_new_i32();
 
+        read_vec_element_i32(s, tcg_rn, rn, 0, size);
+
         switch (opcode) {
+        case 0x7: /* SQABS, SQNEG */
+        {
+            NeonGenOneOpEnvFn *genfn;
+            static NeonGenOneOpEnvFn * const fns[3][2] = {
+                { gen_helper_neon_qabs_s8, gen_helper_neon_qneg_s8 },
+                { gen_helper_neon_qabs_s16, gen_helper_neon_qneg_s16 },
+                { gen_helper_neon_qabs_s32, gen_helper_neon_qneg_s32 },
+            };
+            genfn = fns[size][u];
+            genfn(tcg_rd, cpu_env, tcg_rn);
+            break;
+        }
         case 0x1a: /* FCVTNS */
         case 0x1b: /* FCVTMS */
         case 0x1c: /* FCVTAS */
@@ -7475,8 +7499,6 @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn)
         write_fp_sreg(s, rd, tcg_rd);
         tcg_temp_free_i32(tcg_rd);
         tcg_temp_free_i32(tcg_rn);
-    } else {
-        g_assert_not_reached();
     }
 
     if (is_fcvt) {
@@ -9177,8 +9199,7 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn)
             unallocated_encoding(s);
             return;
         }
-        unsupported_encoding(s, insn);
-        return;
+        break;
     case 0xc ... 0xf:
     case 0x16 ... 0x1d:
     case 0x1f:
@@ -9389,6 +9410,13 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn)
                         gen_helper_cls32(tcg_res, tcg_op);
                     }
                     break;
+                case 0x7: /* SQABS, SQNEG */
+                    if (u) {
+                        gen_helper_neon_qneg_s32(tcg_res, cpu_env, tcg_op);
+                    } else {
+                        gen_helper_neon_qabs_s32(tcg_res, cpu_env, tcg_op);
+                    }
+                    break;
                 case 0xb: /* ABS, NEG */
                     if (u) {
                         tcg_gen_neg_i32(tcg_res, tcg_op);
@@ -9463,6 +9491,17 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn)
                         gen_helper_neon_cnt_u8(tcg_res, tcg_op);
                     }
                     break;
+                case 0x7: /* SQABS, SQNEG */
+                {
+                    NeonGenOneOpEnvFn *genfn;
+                    static NeonGenOneOpEnvFn * const fns[2][2] = {
+                        { gen_helper_neon_qabs_s8, gen_helper_neon_qneg_s8 },
+                        { gen_helper_neon_qabs_s16, gen_helper_neon_qneg_s16 },
+                    };
+                    genfn = fns[size][u];
+                    genfn(tcg_res, cpu_env, tcg_op);
+                    break;
+                }
                 case 0x8: /* CMGT, CMGE */
                 case 0x9: /* CMEQ, CMLE */
                 case 0xa: /* CMLT */
-- 
1.9.0