small perf tweaks

clearing reg_rrr and reg_mmm more efficiently is an extremely small win,
but a win

read_imm_signed generally should inline well and runs afoul of some
heuristic. inlining gets about 8% improved throughput on the
(unrealistic) in-repo benchmark

it would be great to be able to avoid bounds checks somehow; it looks
like they alone are another ~10% of decode time. i'm not sure how to
pull that off while retaining the generic iterator parameter. might just
not be possible.

2 files changed, 7 insertions, 3 deletions

diff --git a/CHANGELOG b/CHANGELOG
index 1325597..c608941 100644
--- a/CHANGELOG
+++ b/CHANGELOG
@@ -3,6 +3,8 @@
   - AMD-only `monitorx`, `mwaitx`, `clzero`, and `rdpru` are now supported
   - `swapgs` is invalid in non-64-bit modes
   - `rdpkru` and `wrpkru` were incorrectly decoded when modrm bits were not `11`
+* small performance tweaks. read_imm_signed is now inline(always) and some
+  pre-decode initialization is a bit better-packed
 
 ## 0.1.4
 * [long mode only]: fix decoding of rex-prefixed modrm+sib operands selecting index 0b100 and base 0b101
diff --git a/src/long_mode/mod.rs b/src/long_mode/mod.rs
index f15e2a1..f9be9ab 100644
--- a/src/long_mode/mod.rs
+++ b/src/long_mode/mod.rs
@@ -5835,8 +5835,10 @@ fn read_instr<T: Iterator<Item=u8>>(decoder: &InstDecoder, mut bytes_iter: T, in
 //    use core::intrinsics::unlikely;
     let mut prefixes = Prefixes::new(0);
 
-    instruction.modrm_mmm.bank = RegisterBank::Q;
-    instruction.sib_index.bank = RegisterBank::Q;
+    // ever so slightly faster than just setting .bank: this allows the two assignments to merge
+    // into one `mov 0, dword [instruction + modrm_mmm_offset]`
+    instruction.modrm_mmm = RegSpec::rax();
+    instruction.sib_index = RegSpec::rax();
 
     fn escapes_are_prefixes_actually(prefixes: &mut Prefixes, opc_map: &mut Option<OpcodeMap>) {
         match opc_map {
@@ -8881,7 +8883,7 @@ fn read_imm_ivq<T: Iterator<Item=u8>>(bytes: &mut T, width: u8, length: &mut u8)
     }
 }
 
-#[inline]
+#[inline(always)]
 fn read_imm_signed<T: Iterator<Item=u8>>(bytes: &mut T, num_width: u8, length: &mut u8) -> Result<i64, DecodeError> {
     if num_width == 1 {
         *length += 1;