Patchwork [10/13] Add xxmrgh/xxmrgl

login
register
mail settings
Submitter Tom Musta
Date Oct. 4, 2013, 1:23 p.m.
Message ID <524EC167.1010902@gmail.com>
Download mbox | patch
Permalink /patch/280626/
State New
Headers show

Comments

Tom Musta - Oct. 4, 2013, 1:23 p.m.
This patch adds the VSX Merge High Word and VSX Merge Low Word
instructions.

Signed-off-by: Tom Musta <tommusta@gmail.com>
---
  target-ppc/translate.c |   44 ++++++++++++++++++++++++++++++++++++++++++++
  1 files changed, 44 insertions(+), 0 deletions(-)


@@ -9798,6 +9840,8 @@ VSX_LOGICAL(xxlandc, 0x8, 0x11, PPC2_VSX),
  VSX_LOGICAL(xxlor, 0x8, 0x12, PPC2_VSX),
  VSX_LOGICAL(xxlxor, 0x8, 0x13, PPC2_VSX),
  VSX_LOGICAL(xxlnor, 0x8, 0x14, PPC2_VSX),
+GEN_XX3FORM(xxmrghw, 0x08, 0x02, PPC2_VSX),
+GEN_XX3FORM(xxmrglw, 0x08, 0x06, PPC2_VSX),

  GEN_XX3FORM_DM(xxpermdi, 0x08, 0x01),
Richard Henderson - Oct. 9, 2013, 8:09 p.m.
On 10/04/2013 06:23 AM, Tom Musta wrote:
> +        tcg_gen_andi_i64(a0, a0, 0xFFFFFFFF00000000ul);     \
> +        tcg_gen_shli_i64(a1, a1, 32);                       \
> +        tcg_gen_shri_i64(b0, b0, 32);                       \
> +        tcg_gen_andi_i64(b0, b0, 0x00000000FFFFFFFFul);     \
> +        tcg_gen_andi_i64(b1, b1, 0x00000000FFFFFFFFul);     \
> +        tcg_gen_or_i64(a0, a0, b0);                         \
> +        tcg_gen_or_i64(a1, a1, b1);                         \
> +        tcg_gen_mov_i64(cpu_vsrh(xT(ctx->opcode)), a0);     \
> +        tcg_gen_mov_i64(cpu_vsrl(xT(ctx->opcode)), a1);     \

Two deposit operations.


r~
Tom Musta - Oct. 10, 2013, 12:16 p.m.
On 10/9/2013 3:09 PM, Richard Henderson wrote:
> On 10/04/2013 06:23 AM, Tom Musta wrote:
>> +        tcg_gen_andi_i64(a0, a0, 0xFFFFFFFF00000000ul);     \
>> +        tcg_gen_shli_i64(a1, a1, 32);                       \
>> +        tcg_gen_shri_i64(b0, b0, 32);                       \
>> +        tcg_gen_andi_i64(b0, b0, 0x00000000FFFFFFFFul);     \
>> +        tcg_gen_andi_i64(b1, b1, 0x00000000FFFFFFFFul);     \
>> +        tcg_gen_or_i64(a0, a0, b0);                         \
>> +        tcg_gen_or_i64(a1, a1, b1);                         \
>> +        tcg_gen_mov_i64(cpu_vsrh(xT(ctx->opcode)), a0);     \
>> +        tcg_gen_mov_i64(cpu_vsrl(xT(ctx->opcode)), a1);     \
> Two deposit operations.
>
>
> r~
Richard:  Thanks for the comments. I will rework this to use deposit 
(and also lxvw4x and xxspltw).

Patch

diff --git a/target-ppc/translate.c b/target-ppc/translate.c
index f1ce4fe..bd62c62 100644
--- a/target-ppc/translate.c
+++ b/target-ppc/translate.c
@@ -7286,6 +7286,48 @@  VSX_LOGICAL(xxlor, tcg_gen_or_tl)
  VSX_LOGICAL(xxlxor, tcg_gen_xor_tl)
  VSX_LOGICAL(xxlnor, tcg_gen_nor_tl)

+#define VSX_XXMRG(name, high)                               \
+static void glue(gen_, name)(DisasContext * ctx)            \
+    {                                                       \
+        TCGv_i64 a0, a1, b0, b1;                            \
+        if (unlikely(!ctx->vsx_enabled)) {                  \
+            gen_exception(ctx, POWERPC_EXCP_VSXU);          \
+            return;                                         \
+        }                                                   \
+        a0 = tcg_temp_new();                                \
+        a1 = tcg_temp_new();                                \
+        b0 = tcg_temp_new();                                \
+        b1 = tcg_temp_new();                                \
+        if (high) {                                         \
+            tcg_gen_mov_i64(a0, cpu_vsrh(xA(ctx->opcode))); \
+            tcg_gen_mov_i64(a1, cpu_vsrh(xA(ctx->opcode))); \
+            tcg_gen_mov_i64(b0, cpu_vsrh(xB(ctx->opcode))); \
+            tcg_gen_mov_i64(b1, cpu_vsrh(xB(ctx->opcode))); \
+        } else {                                            \
+            tcg_gen_mov_i64(a0, cpu_vsrl(xA(ctx->opcode))); \
+            tcg_gen_mov_i64(a1, cpu_vsrl(xA(ctx->opcode))); \
+            tcg_gen_mov_i64(b0, cpu_vsrl(xB(ctx->opcode))); \
+            tcg_gen_mov_i64(b1, cpu_vsrl(xB(ctx->opcode))); \
+        }                                                   \
+        tcg_gen_andi_i64(a0, a0, 0xFFFFFFFF00000000ul);     \
+        tcg_gen_shli_i64(a1, a1, 32);                       \
+        tcg_gen_shri_i64(b0, b0, 32);                       \
+        tcg_gen_andi_i64(b0, b0, 0x00000000FFFFFFFFul);     \
+        tcg_gen_andi_i64(b1, b1, 0x00000000FFFFFFFFul);     \
+        tcg_gen_or_i64(a0, a0, b0);                         \
+        tcg_gen_or_i64(a1, a1, b1);                         \
+        tcg_gen_mov_i64(cpu_vsrh(xT(ctx->opcode)), a0);     \
+        tcg_gen_mov_i64(cpu_vsrl(xT(ctx->opcode)), a1);     \
+        tcg_temp_free(a0);                                  \
+        tcg_temp_free(a1);                                  \
+        tcg_temp_free(b0);                                  \
+        tcg_temp_free(b1);                                  \
+    }
+
+VSX_XXMRG(xxmrghw, 1)
+VSX_XXMRG(xxmrglw, 0)
+
+
  /***                           SPE 
extension                               ***/
  /* Register moves */