target-mips: simplify LWL/LDL mask generation

The LWL/LDL instructions mask the GPR with a mask depending on the
address alignement. It is currently computed by doing:

    mask = 0x7fffffffffffffffull >> (t1 ^ 63)

It's simpler to generate it by doing:

    mask = ~(-1 << t1)

It uses one TCG instruction less, and it avoids a 32/64-bit constant
loading which can take a few instructions on RISC hosts.

Cc: Leon Alrae <[email protected]>
Signed-off-by: Aurelien Jarno <[email protected]>
Reviewed-by: Richard Henderson <[email protected]>
Reviewed-by: Leon Alrae <[email protected]>
Signed-off-by: Leon Alrae <[email protected]>

diff --git a/target-mips/translate.c b/target-mips/translate.c
index 22ef84df9eab0f549cbd01d4d6371e985c7db503..98cf72de7490a1bbfef389518d4705e06854612b 100644 (file)
--- a/target-mips/translate.c
+++ b/target-mips/translate.c
@@ -2153,11 +2153,10 @@ static void gen_ld(DisasContext *ctx, uint32_t opc,
         tcg_gen_andi_tl(t0, t0, ~7);
         tcg_gen_qemu_ld_tl(t0, t0, ctx->mem_idx, MO_TEQ);
         tcg_gen_shl_tl(t0, t0, t1);
-        tcg_gen_xori_tl(t1, t1, 63);
-        t2 = tcg_const_tl(0x7fffffffffffffffull);
-        tcg_gen_shr_tl(t2, t2, t1);
+        t2 = tcg_const_tl(-1);
+        tcg_gen_shl_tl(t2, t2, t1);
         gen_load_gpr(t1, rt);
-        tcg_gen_and_tl(t1, t1, t2);
+        tcg_gen_andc_tl(t1, t1, t2);
         tcg_temp_free(t2);
         tcg_gen_or_tl(t0, t0, t1);
         tcg_temp_free(t1);
@@ -2246,11 +2245,10 @@ static void gen_ld(DisasContext *ctx, uint32_t opc,
         tcg_gen_andi_tl(t0, t0, ~3);
         tcg_gen_qemu_ld_tl(t0, t0, ctx->mem_idx, MO_TEUL);
         tcg_gen_shl_tl(t0, t0, t1);
-        tcg_gen_xori_tl(t1, t1, 31);
-        t2 = tcg_const_tl(0x7fffffffull);
-        tcg_gen_shr_tl(t2, t2, t1);
+        t2 = tcg_const_tl(-1);
+        tcg_gen_shl_tl(t2, t2, t1);
         gen_load_gpr(t1, rt);
-        tcg_gen_and_tl(t1, t1, t2);
+        tcg_gen_andc_tl(t1, t1, t2);
         tcg_temp_free(t2);
         tcg_gen_or_tl(t0, t0, t1);
         tcg_temp_free(t1);