diff options
| author | Nikunj A Dadhania | 2016-09-28 20:41:57 +0200 |
|---|---|---|
| committer | David Gibson | 2016-10-05 02:05:28 +0200 |
| commit | 1c0744190ca69732da13d49f6cb48e648dff9a40 (patch) | |
| tree | 4a24b06cc4e1e7f2f72d27b3a1a0f4c66cff34c2 | |
| parent | target-ppc: improve stxvw4x implementation (diff) | |
| download | qemu-1c0744190ca69732da13d49f6cb48e648dff9a40.tar.gz qemu-1c0744190ca69732da13d49f6cb48e648dff9a40.tar.xz qemu-1c0744190ca69732da13d49f6cb48e648dff9a40.zip | |
target-ppc: add lxvh8x instruction
lxvh8x: Load VSX Vector Halfword*8
Big-Endian Storage
+-------+-------+-------+-------+-------+-------+-------+-------+
| 00 01 | 10 11 | 20 21 | 30 31 | 40 41 | 50 51 | 60 61 | 70 71 |
+-------+-------+-------+-------+-------+-------+-------+-------+
Little-Endian Storage
+-------+-------+-------+-------+-------+-------+-------+-------+
| 01 00 | 11 10 | 21 20 | 31 30 | 41 40 | 51 50 | 61 60 | 71 70 |
+-------+-------+-------+-------+-------+-------+-------+-------+
Vector load results in (16-bit elements):
+------+------+------+------+------+------+------+------+
| 0001 | 1011 | 2021 | 3031 | 4041 | 5051 | 6061 | 7071 |
+------+------+------+------+------+------+------+------+
Signed-off-by: Nikunj A Dadhania <nikunj@linux.vnet.ibm.com>
Reviewed-by: Richard Henderson <rth@twiddle.net>
[dwg: Tweak to commit description]
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
| -rw-r--r-- | target-ppc/translate/vsx-impl.inc.c | 49 | ||||
| -rw-r--r-- | target-ppc/translate/vsx-ops.inc.c | 1 |
2 files changed, 50 insertions, 0 deletions
diff --git a/target-ppc/translate/vsx-impl.inc.c b/target-ppc/translate/vsx-impl.inc.c index a7e35d06e9..1376be8ddf 100644 --- a/target-ppc/translate/vsx-impl.inc.c +++ b/target-ppc/translate/vsx-impl.inc.c @@ -106,6 +106,55 @@ static void gen_lxvw4x(DisasContext *ctx) tcg_temp_free(EA); } +static void gen_bswap16x8(TCGv_i64 outh, TCGv_i64 outl, + TCGv_i64 inh, TCGv_i64 inl) +{ + TCGv_i64 mask = tcg_const_i64(0x00FF00FF00FF00FF); + TCGv_i64 t0 = tcg_temp_new_i64(); + TCGv_i64 t1 = tcg_temp_new_i64(); + + /* outh = ((inh & mask) << 8) | ((inh >> 8) & mask) */ + tcg_gen_and_i64(t0, inh, mask); + tcg_gen_shli_i64(t0, t0, 8); + tcg_gen_shri_i64(t1, inh, 8); + tcg_gen_and_i64(t1, t1, mask); + tcg_gen_or_i64(outh, t0, t1); + + /* outl = ((inl & mask) << 8) | ((inl >> 8) & mask) */ + tcg_gen_and_i64(t0, inl, mask); + tcg_gen_shli_i64(t0, t0, 8); + tcg_gen_shri_i64(t1, inl, 8); + tcg_gen_and_i64(t1, t1, mask); + tcg_gen_or_i64(outl, t0, t1); + + tcg_temp_free_i64(t0); + tcg_temp_free_i64(t1); + tcg_temp_free_i64(mask); +} + +static void gen_lxvh8x(DisasContext *ctx) +{ + TCGv EA; + TCGv_i64 xth = cpu_vsrh(xT(ctx->opcode)); + TCGv_i64 xtl = cpu_vsrl(xT(ctx->opcode)); + + if (unlikely(!ctx->vsx_enabled)) { + gen_exception(ctx, POWERPC_EXCP_VSXU); + return; + } + gen_set_access_type(ctx, ACCESS_INT); + + EA = tcg_temp_new(); + gen_addr_reg_index(ctx, EA); + tcg_gen_qemu_ld_i64(xth, EA, ctx->mem_idx, MO_BEQ); + tcg_gen_addi_tl(EA, EA, 8); + tcg_gen_qemu_ld_i64(xtl, EA, ctx->mem_idx, MO_BEQ); + if (ctx->le_mode) { + gen_bswap16x8(xth, xtl, xth, xtl); + } + tcg_temp_free(EA); +} + #define VSX_STORE_SCALAR(name, operation) \ static void gen_##name(DisasContext *ctx) \ { \ diff --git a/target-ppc/translate/vsx-ops.inc.c b/target-ppc/translate/vsx-ops.inc.c index 1287973636..322fd5bb2f 100644 --- a/target-ppc/translate/vsx-ops.inc.c +++ b/target-ppc/translate/vsx-ops.inc.c @@ -7,6 +7,7 @@ GEN_HANDLER_E(lxsspx, 0x1F, 0x0C, 0x10, 0, PPC_NONE, PPC2_VSX207), GEN_HANDLER_E(lxvd2x, 0x1F, 0x0C, 0x1A, 0, PPC_NONE, PPC2_VSX), GEN_HANDLER_E(lxvdsx, 0x1F, 0x0C, 0x0A, 0, PPC_NONE, PPC2_VSX), GEN_HANDLER_E(lxvw4x, 0x1F, 0x0C, 0x18, 0, PPC_NONE, PPC2_VSX), +GEN_HANDLER_E(lxvh8x, 0x1F, 0x0C, 0x19, 0, PPC_NONE, PPC2_ISA300), GEN_HANDLER_E(stxsdx, 0x1F, 0xC, 0x16, 0, PPC_NONE, PPC2_VSX), GEN_HANDLER_E(stxsibx, 0x1F, 0xD, 0x1C, 0, PPC_NONE, PPC2_ISA300), |