diff mbox series

[v2,17/22] target/loongarch: Add floating point load/store instruction translation

Message ID 1626861198-6133-18-git-send-email-gaosong@loongson.cn (mailing list archive)
State New, archived
Headers show
Series Add LoongArch linux-user emulation support | expand

Commit Message

gaosong July 21, 2021, 9:53 a.m. UTC
This patch implement floating point load/store instruction translation.

This includes:
- FLD.{S/D}, FST.{S/D}
- FLDX.{S/D}, FSTX.{S/D}
- FLD{GT/LE}.{S/D}, FST{GT/LE}.{S/D}

Signed-off-by: Song Gao <gaosong@loongson.cn>
---
 target/loongarch/insns.decode |  24 ++++
 target/loongarch/trans.inc.c  | 257 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 281 insertions(+)

Comments

Richard Henderson July 23, 2021, 6:34 a.m. UTC | #1
On 7/20/21 11:53 PM, Song Gao wrote:
> +static bool trans_fldx_d(DisasContext *ctx, arg_fldx_d *a)
> +{
> +    TCGv t0;
> +    TCGv_i64 fp0;
> +    TCGv Rj = cpu_gpr[a->rj];
> +    TCGv Rk = cpu_gpr[a->rk];
> +
> +    t0 = tcg_temp_new();
> +    fp0 = tcg_temp_new_i64();
> +
> +    if (a->rj == 0 && a->rk == 0) {
> +        /* Nop */
> +        return true;
> +    }

This is not true.  This is simply a read from address 0 + 0 = 0.
Similarly for all of the other indexed memory operations.

And again, you should be using helpers to reduce the replication here.


r~
gaosong July 27, 2021, 8:07 a.m. UTC | #2
Hi, Richard.

On 07/23/2021 02:34 PM, Richard Henderson wrote:
> On 7/20/21 11:53 PM, Song Gao wrote:
>> +static bool trans_fldx_d(DisasContext *ctx, arg_fldx_d *a)
>> +{
>> +    TCGv t0;
>> +    TCGv_i64 fp0;
>> +    TCGv Rj = cpu_gpr[a->rj];
>> +    TCGv Rk = cpu_gpr[a->rk];
>> +
>> +    t0 = tcg_temp_new();
>> +    fp0 = tcg_temp_new_i64();
>> +
>> +    if (a->rj == 0 && a->rk == 0) {
>> +        /* Nop */
>> +        return true;
>> +    }
> 
> This is not true.  This is simply a read from address 0 + 0 = 0.
> Similarly for all of the other indexed memory operations.
> 
> And again, you should be using helpers to reduce the replication here.
> 
OK.
> 
> r~

Thanks
Song Gao.
diff mbox series

Patch

diff --git a/target/loongarch/insns.decode b/target/loongarch/insns.decode
index febf89a..ea776c2 100644
--- a/target/loongarch/insns.decode
+++ b/target/loongarch/insns.decode
@@ -72,6 +72,8 @@ 
 &fmt_fdcj           fd cj
 &fmt_cdrj           cd rj
 &fmt_rdcj           rd cj
+&fmt_fdrjrk         fd rj rk
+&fmt_fdrjsi12       fd rj si12
 
 #
 # Formats
@@ -106,6 +108,8 @@ 
 @fmt_fdcj            .... ........ ..... ..... .. ... .....   &fmt_fdcj           %fd %cj
 @fmt_cdrj            .... ........ ..... ..... ..... .. ...   &fmt_cdrj           %cd %rj
 @fmt_rdcj            .... ........ ..... ..... .. ... .....   &fmt_rdcj           %rd %cj
+@fmt_fdrjrk          .... ........ ..... ..... ..... .....    &fmt_fdrjrk         %fd %rj %rk
+@fmt_fdrjsi12        .... ...... ............ ..... .....     &fmt_fdrjsi12       %fd %rj %si12
 
 #
 # Fixed point arithmetic operation instruction
@@ -424,3 +428,23 @@  movfr2cf         0000 00010001 01001 10100 ..... 00 ...   @fmt_cdfj
 movcf2fr         0000 00010001 01001 10101 00 ... .....   @fmt_fdcj
 movgr2cf         0000 00010001 01001 10110 ..... 00 ...   @fmt_cdrj
 movcf2gr         0000 00010001 01001 10111 00 ... .....   @fmt_rdcj
+
+#
+# Floating point load/store instruction
+#
+fld_s            0010 101100 ............ ..... .....     @fmt_fdrjsi12
+fst_s            0010 101101 ............ ..... .....     @fmt_fdrjsi12
+fld_d            0010 101110 ............ ..... .....     @fmt_fdrjsi12
+fst_d            0010 101111 ............ ..... .....     @fmt_fdrjsi12
+fldx_s           0011 10000011 00000 ..... ..... .....    @fmt_fdrjrk
+fldx_d           0011 10000011 01000 ..... ..... .....    @fmt_fdrjrk
+fstx_s           0011 10000011 10000 ..... ..... .....    @fmt_fdrjrk
+fstx_d           0011 10000011 11000 ..... ..... .....    @fmt_fdrjrk
+fldgt_s          0011 10000111 01000 ..... ..... .....    @fmt_fdrjrk
+fldgt_d          0011 10000111 01001 ..... ..... .....    @fmt_fdrjrk
+fldle_s          0011 10000111 01010 ..... ..... .....    @fmt_fdrjrk
+fldle_d          0011 10000111 01011 ..... ..... .....    @fmt_fdrjrk
+fstgt_s          0011 10000111 01100 ..... ..... .....    @fmt_fdrjrk
+fstgt_d          0011 10000111 01101 ..... ..... .....    @fmt_fdrjrk
+fstle_s          0011 10000111 01110 ..... ..... .....    @fmt_fdrjrk
+fstle_d          0011 10000111 01111 ..... ..... .....    @fmt_fdrjrk
diff --git a/target/loongarch/trans.inc.c b/target/loongarch/trans.inc.c
index 56677f8..8adfdd3 100644
--- a/target/loongarch/trans.inc.c
+++ b/target/loongarch/trans.inc.c
@@ -5028,3 +5028,260 @@  static bool trans_movcf2gr(DisasContext *ctx, arg_movcf2gr *a)
 
     return true;
 }
+
+/* Floating point load/store instruction translation */
+static bool trans_fld_s(DisasContext *ctx, arg_fld_s *a)
+{
+    TCGv t0;
+    TCGv_i32 fp0;
+
+    t0 = tcg_temp_new();
+    fp0 = tcg_temp_new_i32();
+
+    check_fpu_enabled(ctx);
+    gen_base_offset_addr(t0, a->rj, a->si12);
+    tcg_gen_qemu_ld_i32(fp0, t0, ctx->mem_idx, MO_TESL |
+                        ctx->default_tcg_memop_mask);
+    gen_store_fpr32(fp0, a->fd);
+
+    tcg_temp_free(t0);
+    tcg_temp_free_i32(fp0);
+
+
+    return true;
+}
+
+static bool trans_fst_s(DisasContext *ctx, arg_fst_s *a)
+{
+    TCGv t0;
+    TCGv_i32 fp0;
+
+    t0 = tcg_temp_new();
+    fp0 = tcg_temp_new_i32();
+
+    check_fpu_enabled(ctx);
+    gen_base_offset_addr(t0, a->rj, a->si12);
+    gen_load_fpr32(fp0, a->fd);
+    tcg_gen_qemu_st_i32(fp0, t0, ctx->mem_idx, MO_TEUL |
+                        ctx->default_tcg_memop_mask);
+
+    tcg_temp_free(t0);
+    tcg_temp_free_i32(fp0);
+
+    return true;
+}
+
+static bool trans_fld_d(DisasContext *ctx, arg_fld_d *a)
+{
+    TCGv t0;
+    TCGv_i64 fp0;
+
+    t0 = tcg_temp_new();
+    fp0 = tcg_temp_new_i64();
+
+    check_fpu_enabled(ctx);
+    gen_base_offset_addr(t0, a->rj, a->si12);
+    tcg_gen_qemu_ld_i64(fp0, t0, ctx->mem_idx, MO_TEQ |
+                        ctx->default_tcg_memop_mask);
+    gen_store_fpr64(fp0, a->fd);
+
+    tcg_temp_free(t0);
+    tcg_temp_free_i64(fp0);
+
+    return true;
+}
+
+static bool trans_fst_d(DisasContext *ctx, arg_fst_d *a)
+{
+    TCGv t0;
+    TCGv_i64 fp0;
+
+    t0 = tcg_temp_new();
+    fp0 = tcg_temp_new_i64();
+
+    check_fpu_enabled(ctx);
+    gen_base_offset_addr(t0, a->rj, a->si12);
+    gen_load_fpr64(fp0, a->fd);
+    tcg_gen_qemu_st_i64(fp0, t0, ctx->mem_idx, MO_TEQ |
+                        ctx->default_tcg_memop_mask);
+
+    tcg_temp_free(t0);
+    tcg_temp_free_i64(fp0);
+
+    return true;
+}
+
+static bool trans_fldx_s(DisasContext *ctx, arg_fldx_s *a)
+{
+    TCGv t0;
+    TCGv_i32 fp0;
+    TCGv Rj = cpu_gpr[a->rj];
+    TCGv Rk = cpu_gpr[a->rk];
+
+    t0 = tcg_temp_new();
+    fp0 = tcg_temp_new_i32();
+
+    if (a->rj == 0 && a->rk == 0) {
+        /* Nop */
+        return true;
+    }
+
+    tcg_gen_add_tl(t0, Rj, Rk);
+    tcg_gen_qemu_ld_tl(t0, t0, ctx->mem_idx, MO_TESL);
+    tcg_gen_trunc_tl_i32(fp0, t0);
+    gen_store_fpr32(fp0, a->fd);
+
+    tcg_temp_free(t0);
+    tcg_temp_free_i32(fp0);
+
+    return true;
+}
+
+static bool trans_fldx_d(DisasContext *ctx, arg_fldx_d *a)
+{
+    TCGv t0;
+    TCGv_i64 fp0;
+    TCGv Rj = cpu_gpr[a->rj];
+    TCGv Rk = cpu_gpr[a->rk];
+
+    t0 = tcg_temp_new();
+    fp0 = tcg_temp_new_i64();
+
+    if (a->rj == 0 && a->rk == 0) {
+        /* Nop */
+        return true;
+    }
+
+    tcg_gen_add_tl(t0, Rj, Rk);
+    tcg_gen_qemu_ld_i64(fp0, t0, ctx->mem_idx, MO_TEQ);
+    gen_store_fpr64(fp0, a->fd);
+
+    tcg_temp_free(t0);
+    tcg_temp_free_i64(fp0);
+
+    return true;
+}
+
+static bool trans_fstx_s(DisasContext *ctx, arg_fstx_s *a)
+{
+    TCGv t0;
+    TCGv_i32 fp0;
+    TCGv Rj = cpu_gpr[a->rj];
+    TCGv Rk = cpu_gpr[a->rk];
+
+    t0 = tcg_temp_new();
+    fp0 = tcg_temp_new_i32();
+
+    if (a->rj == 0 && a->rk == 0) {
+        /* Nop */
+        return true;
+    }
+
+    tcg_gen_add_tl(t0, Rj, Rk);
+    gen_load_fpr32(fp0, a->fd);
+    tcg_gen_qemu_st_i32(fp0, t0, ctx->mem_idx, MO_TEUL);
+
+    tcg_temp_free(t0);
+    tcg_temp_free_i32(fp0);
+
+    return true;
+}
+
+static bool trans_fstx_d(DisasContext *ctx, arg_fstx_d *a)
+{
+    TCGv t0;
+    TCGv_i64 fp0;
+    TCGv Rj = cpu_gpr[a->rj];
+    TCGv Rk = cpu_gpr[a->rk];
+
+    t0 = tcg_temp_new();
+    fp0 = tcg_temp_new_i64();
+
+    if (a->rj == 0 && a->rk == 0) {
+        /* Nop */
+        return true;
+    }
+
+    tcg_gen_add_tl(t0, Rj, Rk);
+    gen_load_fpr64(fp0, a->fd);
+    tcg_gen_qemu_st_i64(fp0, t0, ctx->mem_idx, MO_TEQ);
+
+    tcg_temp_free_i64(fp0);
+    tcg_temp_free(t0);
+
+    return true;
+}
+
+
+#define DECL_ARG2(name)  \
+    arg_ ## name arg = { \
+        .fd = a->fd,     \
+        .rj = a->rj,     \
+        .rk = a->rk,     \
+    };
+
+static bool trans_fldgt_s(DisasContext *ctx, arg_fldgt_s *a)
+{
+    ASRTGT;
+    DECL_ARG2(fldx_s)
+    trans_fldx_s(ctx, &arg);
+    return true;
+}
+
+static bool trans_fldgt_d(DisasContext *ctx, arg_fldgt_d *a)
+{
+    ASRTGT;
+    DECL_ARG2(fldx_d);
+    trans_fldx_d(ctx, &arg);
+    return true;
+}
+
+static bool trans_fldle_s(DisasContext *ctx, arg_fldle_s *a)
+{
+    ASRTLE;
+    DECL_ARG2(fldx_s);
+    trans_fldx_s(ctx, &arg);
+    return true;
+}
+
+static bool trans_fldle_d(DisasContext *ctx, arg_fldle_d *a)
+{
+    ASRTLE;
+    DECL_ARG2(fldx_d);
+    trans_fldx_d(ctx, &arg);
+    return true;
+}
+
+static bool trans_fstgt_s(DisasContext *ctx, arg_fstgt_s *a)
+{
+    ASRTGT;
+    DECL_ARG2(fstx_s);
+    trans_fstx_s(ctx, &arg);
+    return true;
+}
+
+static bool trans_fstgt_d(DisasContext *ctx, arg_fstgt_d *a)
+{
+    ASRTGT;
+    DECL_ARG2(fstx_d);
+    trans_fstx_d(ctx, &arg);
+    return true;
+}
+
+static bool trans_fstle_s(DisasContext *ctx, arg_fstle_s *a)
+{
+    ASRTLE;
+    DECL_ARG2(fstx_s);
+    trans_fstx_s(ctx, &arg);
+    return true;
+}
+
+static bool trans_fstle_d(DisasContext *ctx, arg_fstle_d *a)
+{
+    ASRTLE;
+    DECL_ARG2(fstx_d);
+    trans_fstx_d(ctx, &arg);
+    return true;
+}
+
+#undef DECL_ARG2