[Qemu-devel] [PATCH v2 14/17] target-ppc: improve lxvw4x implementation

[Nikunj A Dadhania <nikunj@linux.vnet.ibm.com>]

Load 8byte at a time and manipulate.

Signed-off-by: Nikunj A Dadhania <nikunj@linux.vnet.ibm.com>
---
 target-ppc/helper.h                 |  1 +
 target-ppc/mem_helper.c             |  5 +++++
 target-ppc/translate/vsx-impl.inc.c | 34 ++++++++++++++++++++--------------
 3 files changed, 26 insertions(+), 14 deletions(-)

diff --git a/target-ppc/helper.h b/target-ppc/helper.h
index 695a2db..ce214f7 100644
--- a/target-ppc/helper.h
+++ b/target-ppc/helper.h
@@ -288,6 +288,7 @@ DEF_HELPER_2(mtvscr, void, env, avr)
 DEF_HELPER_3(lvebx, void, env, avr, tl)
 DEF_HELPER_3(lvehx, void, env, avr, tl)
 DEF_HELPER_3(lvewx, void, env, avr, tl)
+DEF_HELPER_1(bswap32x2, i64, i64)
 DEF_HELPER_3(stvebx, void, env, avr, tl)
 DEF_HELPER_3(stvehx, void, env, avr, tl)
 DEF_HELPER_3(stvewx, void, env, avr, tl)
diff --git a/target-ppc/mem_helper.c b/target-ppc/mem_helper.c
index bf6c44a..070dff6 100644
--- a/target-ppc/mem_helper.c
+++ b/target-ppc/mem_helper.c
@@ -354,6 +354,11 @@ STVE(stvewx, cpu_stl_data_ra, bswap32, u32)
 #undef I
 #undef LVE
 
+uint64_t helper_bswap32x2(uint64_t x)
+{
+    return deposit64((x >> 32), 32, 32, (x));
+}
+
 #undef HI_IDX
 #undef LO_IDX
 
diff --git a/target-ppc/translate/vsx-impl.inc.c b/target-ppc/translate/vsx-impl.inc.c
index eee6052..e3374df 100644
--- a/target-ppc/translate/vsx-impl.inc.c
+++ b/target-ppc/translate/vsx-impl.inc.c
@@ -75,7 +75,7 @@ static void gen_lxvdsx(DisasContext *ctx)
 static void gen_lxvw4x(DisasContext *ctx)
 {
     TCGv EA;
-    TCGv_i64 tmp;
+    TCGv_i64 t0, t1;
     TCGv_i64 xth = cpu_vsrh(xT(ctx->opcode));
     TCGv_i64 xtl = cpu_vsrl(xT(ctx->opcode));
     if (unlikely(!ctx->vsx_enabled)) {
@@ -84,22 +84,28 @@ static void gen_lxvw4x(DisasContext *ctx)
     }
     gen_set_access_type(ctx, ACCESS_INT);
     EA = tcg_temp_new();
-    tmp = tcg_temp_new_i64();
 
     gen_addr_reg_index(ctx, EA);
-    gen_qemu_ld32u_i64(ctx, tmp, EA);
-    tcg_gen_addi_tl(EA, EA, 4);
-    gen_qemu_ld32u_i64(ctx, xth, EA);
-    tcg_gen_deposit_i64(xth, xth, tmp, 32, 32);
-
-    tcg_gen_addi_tl(EA, EA, 4);
-    gen_qemu_ld32u_i64(ctx, tmp, EA);
-    tcg_gen_addi_tl(EA, EA, 4);
-    gen_qemu_ld32u_i64(ctx, xtl, EA);
-    tcg_gen_deposit_i64(xtl, xtl, tmp, 32, 32);
-
+    if (ctx->le_mode) {
+        t0 = tcg_temp_new_i64();
+        t1 = tcg_temp_new_i64();
+        tcg_gen_qemu_ld_i64(t0, EA, ctx->mem_idx, MO_LEQ);
+        tcg_gen_shri_i64(t1, t0, 32);
+        tcg_gen_deposit_i64(xth, t1, t0, 32, 32);
+        tcg_gen_addi_tl(EA, EA, 8);
+        tcg_gen_qemu_ld_i64(t0, EA, ctx->mem_idx, MO_LEQ);
+        tcg_gen_shri_i64(t1, t0, 32);
+        tcg_gen_deposit_i64(xtl, t1, t0, 32, 32);
+        tcg_temp_free_i64(t0);
+        tcg_temp_free_i64(t1);
+    } else {
+        tcg_gen_qemu_ld_i64(xth, EA, ctx->mem_idx, MO_LEQ);
+        gen_helper_bswap32x2(xth, xth);
+        tcg_gen_addi_tl(EA, EA, 8);
+        tcg_gen_qemu_ld_i64(xtl, EA, ctx->mem_idx, MO_LEQ);
+        gen_helper_bswap32x2(xtl, xtl);
+    }
     tcg_temp_free(EA);
-    tcg_temp_free_i64(tmp);
 }
 
 #define VSX_STORE_SCALAR(name, operation)                     \
-- 
2.7.4