[PATCH v2 19/29] target/arm: Convert SSHLL, USHLL to decodetree

Richard Henderson posted 29 patches 2 months, 2 weeks ago
There is a newer version of this series
[PATCH v2 19/29] target/arm: Convert SSHLL, USHLL to decodetree
Posted by Richard Henderson 2 months, 2 weeks ago
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/tcg/translate-a64.c | 81 ++++++++++++++++------------------
 target/arm/tcg/a64.decode      |  8 ++++
 2 files changed, 45 insertions(+), 44 deletions(-)

diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index 740620074a..e00d7fbf48 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -6983,6 +6983,42 @@ TRANS(SRI_v, do_vec_shift_imm, a, gen_gvec_sri)
 TRANS(SHL_v, do_vec_shift_imm, a, tcg_gen_gvec_shli)
 TRANS(SLI_v, do_vec_shift_imm, a, gen_gvec_sli);
 
+static bool do_vec_shift_imm_wide(DisasContext *s, arg_qrri_e *a, bool is_u)
+{
+    TCGv_i64 tcg_rn, tcg_rd;
+    int esz = a->esz;
+    int esize;
+
+    if (!fp_access_check(s)) {
+        return true;
+    }
+
+    /*
+     * For the LL variants the store is larger than the load,
+     * so if rd == rn we would overwrite parts of our input.
+     * So load everything right now and use shifts in the main loop.
+     */
+    tcg_rd = tcg_temp_new_i64();
+    tcg_rn = tcg_temp_new_i64();
+    read_vec_element(s, tcg_rn, a->rn, a->q, MO_64);
+
+    esize = 8 << esz;
+    for (int i = 0, elements = 8 >> esz; i < elements; i++) {
+        if (is_u) {
+            tcg_gen_extract_i64(tcg_rd, tcg_rn, i * esize, esize);
+        } else {
+            tcg_gen_sextract_i64(tcg_rd, tcg_rn, i * esize, esize);
+        }
+        tcg_gen_shli_i64(tcg_rd, tcg_rd, a->imm);
+        write_vec_element(s, tcg_rd, a->rd, i, esz + 1);
+    }
+    clear_vec_high(s, true, a->rd);
+    return true;
+}
+
+TRANS(SSHLL_v, do_vec_shift_imm_wide, a, false)
+TRANS(USHLL_v, do_vec_shift_imm_wide, a, true)
+
 /* Shift a TCGv src by TCGv shift_amount, put result in dst.
  * Note that it is the caller's responsibility to ensure that the
  * shift amount is in range (ie 0..31 or 0..63) and provide the ARM
@@ -10447,47 +10483,6 @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn)
     }
 }
 
-/* USHLL/SHLL - Vector shift left with widening */
-static void handle_vec_simd_wshli(DisasContext *s, bool is_q, bool is_u,
-                                 int immh, int immb, int opcode, int rn, int rd)
-{
-    int size = 32 - clz32(immh) - 1;
-    int immhb = immh << 3 | immb;
-    int shift = immhb - (8 << size);
-    int dsize = 64;
-    int esize = 8 << size;
-    int elements = dsize/esize;
-    TCGv_i64 tcg_rn = tcg_temp_new_i64();
-    TCGv_i64 tcg_rd = tcg_temp_new_i64();
-    int i;
-
-    if (size >= 3) {
-        unallocated_encoding(s);
-        return;
-    }
-
-    if (!fp_access_check(s)) {
-        return;
-    }
-
-    /* For the LL variants the store is larger than the load,
-     * so if rd == rn we would overwrite parts of our input.
-     * So load everything right now and use shifts in the main loop.
-     */
-    read_vec_element(s, tcg_rn, rn, is_q ? 1 : 0, MO_64);
-
-    for (i = 0; i < elements; i++) {
-        if (is_u) {
-            tcg_gen_extract_i64(tcg_rd, tcg_rn, i * esize, esize);
-        } else {
-            tcg_gen_sextract_i64(tcg_rd, tcg_rn, i * esize, esize);
-        }
-        tcg_gen_shli_i64(tcg_rd, tcg_rd, shift);
-        write_vec_element(s, tcg_rd, rd, i, size + 1);
-    }
-    clear_vec_high(s, true, rd);
-}
-
 /* SHRN/RSHRN - Shift right with narrowing (and potential rounding) */
 static void handle_vec_simd_shrn(DisasContext *s, bool is_q,
                                  int immh, int immb, int opcode, int rn, int rd)
@@ -10577,9 +10572,6 @@ static void disas_simd_shift_imm(DisasContext *s, uint32_t insn)
         handle_vec_simd_sqshrn(s, false, is_q, is_u, is_u, immh, immb,
                                opcode, rn, rd);
         break;
-    case 0x14: /* SSHLL / USHLL */
-        handle_vec_simd_wshli(s, is_q, is_u, immh, immb, opcode, rn, rd);
-        break;
     case 0x1c: /* SCVTF / UCVTF */
         handle_simd_shift_intfp_conv(s, false, is_q, is_u, immh, immb,
                                      opcode, rn, rd);
@@ -10604,6 +10596,7 @@ static void disas_simd_shift_imm(DisasContext *s, uint32_t insn)
     case 0x06: /* SRSRA / URSRA (accum + rounding) */
     case 0x08: /* SRI */
     case 0x0a: /* SHL / SLI */
+    case 0x14: /* SSHLL / USHLL */
         unallocated_encoding(s);
         return;
     }
diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode
index 77b860a3f2..bf67f8a357 100644
--- a/target/arm/tcg/a64.decode
+++ b/target/arm/tcg/a64.decode
@@ -1269,3 +1269,11 @@ SLI_v           0.10 11110 .... ... 01010 1 ..... .....     @q_shli_b
 SLI_v           0.10 11110 .... ... 01010 1 ..... .....     @q_shli_h
 SLI_v           0.10 11110 .... ... 01010 1 ..... .....     @q_shli_s
 SLI_v           0.10 11110 .... ... 01010 1 ..... .....     @q_shli_d
+
+SSHLL_v         0.00 11110 .... ... 10100 1 ..... .....     @q_shli_b
+SSHLL_v         0.00 11110 .... ... 10100 1 ..... .....     @q_shli_h
+SSHLL_v         0.00 11110 .... ... 10100 1 ..... .....     @q_shli_s
+
+USHLL_v         0.10 11110 .... ... 10100 1 ..... .....     @q_shli_b
+USHLL_v         0.10 11110 .... ... 10100 1 ..... .....     @q_shli_h
+USHLL_v         0.10 11110 .... ... 10100 1 ..... .....     @q_shli_s
-- 
2.43.0