diff mbox series

[v2,09/32] arm/translate-a64: initial decode for simd_three_reg_same_fp16

Message ID 20180208173157.24705-10-alex.bennee@linaro.org
State Superseded
Headers show
Series Add ARMv8.2 half-precision functions | expand

Commit Message

Alex Bennée Feb. 8, 2018, 5:31 p.m. UTC 
This is the initial decode skeleton for the Advanced SIMD three same
instruction group.

The fprintf is purely to aid debugging as the additional instructions
are added. It will be removed once the group is complete.

Signed-off-by: Alex Bennée <alex.bennee@linaro.org>

---
 target/arm/translate-a64.c | 77 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 77 insertions(+)

-- 
2.15.1

Comments

Richard Henderson Feb. 8, 2018, 8:48 p.m. UTC | #1 
On 02/08/2018 09:31 AM, Alex Bennée wrote:
> This is the initial decode skeleton for the Advanced SIMD three same

> instruction group.

> 

> The fprintf is purely to aid debugging as the additional instructions

> are added. It will be removed once the group is complete.

> 

> Signed-off-by: Alex Bennée <alex.bennee@linaro.org>

> ---

>  target/arm/translate-a64.c | 77 ++++++++++++++++++++++++++++++++++++++++++++++

>  1 file changed, 77 insertions(+)


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



r~
diff mbox series

Patch

diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index 2dd958c0e7..5392f83794 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -9794,6 +9794,82 @@  static void disas_simd_three_reg_same(DisasContext *s, uint32_t insn)
     }
 }
 
+/*
+ * Advanced SIMD three same (ARMv8.2 FP16 variants)
+ *
+ *  31  30  29  28       24 23  22 21 20  16 15 14 13    11 10  9    5 4    0
+ * +---+---+---+-----------+---------+------+-----+--------+---+------+------+
+ * | 0 | Q | U | 0 1 1 1 0 | a | 1 0 |  Rm  | 0 0 | opcode | 1 |  Rn  |  Rd  |
+ * +---+---+---+-----------+---------+------+-----+--------+---+------+------+
+ *
+ * This includes FMULX, FCMEQ (register), FRECPS, FRSQRTS, FCMGE
+ * (register), FACGE, FABD, FCMGT (register) and FACGT.
+ *
+ */
+static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn)
+{
+    int opcode, fpopcode;
+    int is_q, u, a, rm, rn, rd;
+    int datasize, elements;
+    int pass;
+    TCGv_ptr fpst;
+
+    if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) {
+        unallocated_encoding(s);
+        return;
+    }
+
+    if (!fp_access_check(s)) {
+        return;
+    }
+
+    /* For these floating point ops, the U, a and opcode bits
+     * together indicate the operation.
+     */
+    opcode = extract32(insn, 11, 3);
+    u = extract32(insn, 29, 1);
+    a = extract32(insn, 23, 1);
+    is_q = extract32(insn, 30, 1);
+    rm = extract32(insn, 16, 5);
+    rn = extract32(insn, 5, 5);
+    rd = extract32(insn, 0, 5);
+
+    fpopcode = opcode | (a << 3) |  (u << 4);
+    datasize = is_q ? 128 : 64;
+    elements = datasize / 16;
+
+    fpst = get_fpstatus_ptr(true);
+
+    for (pass = 0; pass < elements; pass++) {
+        TCGv_i32 tcg_op1 = tcg_temp_new_i32();
+        TCGv_i32 tcg_op2 = tcg_temp_new_i32();
+        TCGv_i32 tcg_res = tcg_temp_new_i32();
+
+        read_vec_element_i32(s, tcg_op1, rn, pass, MO_16);
+        read_vec_element_i32(s, tcg_op2, rm, pass, MO_16);
+
+        switch (fpopcode) {
+        default:
+            fprintf(stderr, "%s: insn %#04x, fpop %#2x @ %#" PRIx64 "\n",
+                    __func__, insn, fpopcode, s->pc);
+            g_assert_not_reached();
+        }
+
+        write_vec_element_i32(s, tcg_res, rd, pass, MO_16);
+        tcg_temp_free_i32(tcg_res);
+        tcg_temp_free_i32(tcg_op1);
+        tcg_temp_free_i32(tcg_op2);
+    }
+
+    tcg_temp_free_ptr(fpst);
+
+    if (!is_q) {
+        /* non-quad vector op */
+        clear_vec_high(s, rd);
+    }
+
+}
+
 static void handle_2misc_widening(DisasContext *s, int opcode, bool is_q,
                                   int size, int rn, int rd)
 {
@@ -11199,6 +11275,7 @@  static const AArch64DecodeTable data_proc_simd[] = {
     { 0x4e280800, 0xff3e0c00, disas_crypto_aes },
     { 0x5e000000, 0xff208c00, disas_crypto_three_reg_sha },
     { 0x5e280800, 0xff3e0c00, disas_crypto_two_reg_sha },
+    { 0x0e400400, 0x9f60c400, disas_simd_three_reg_same_fp16 },
     { 0x00000000, 0x00000000, NULL }
 };