T0b1/wasmtime
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Infer REX prefixes for SIMD load_extend

Browse Source
This commit is contained in:
Andrew Brown
2020-04-01 09:57:14 -07:00
parent 9336884db5
commit dc874a5b3b
4 changed files with 40 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
cranelift/codegen/meta/src/isa/x86/encodings.rs
View File

@@ -1945,15 +1945,8 @@ fn define_simd(
for recipe in &[rec_fld, rec_fldDisp8, rec_fldDisp32] {
let inst = *inst;
let template = recipe.opcodes(*opcodes);
e.enc32_maybe_isap(inst.clone().bind(I32), template.clone(), isap);
// REX-less encoding must come after REX encoding so we don't use it by
// default. Otherwise reg-alloc would never use r8 and up.
e.enc64_maybe_isap(inst.clone().bind(I32), template.clone().rex(), isap);
e.enc64_maybe_isap(inst.clone().bind(I32), template.clone(), isap);
// Similar to above; TODO some of this duplication can be cleaned up by infer_rex()
// tracked in https://github.com/bytecodealliance/cranelift/issues/1090
e.enc64_maybe_isap(inst.clone().bind(I64), template.clone().rex(), isap);
e.enc64_maybe_isap(inst.bind(I64), template, isap);
e.enc_both_inferred_maybe_isap(inst.clone().bind(I32), template.clone(), isap);
e.enc64_maybe_isap(inst.bind(I64), template.infer_rex(), isap);
}
}

6
cranelift/codegen/meta/src/isa/x86/recipes.rs
View File

@@ -2087,7 +2087,7 @@ pub(crate) fn define<'shared>(
);
// XX /r float load with 8-bit offset.
recipes.add_template_recipe(
recipes.add_template_inferred(
EncodingRecipeBuilder::new("fldDisp8", &formats.load, 2)
.operands_in(vec![gpr])
.operands_out(vec![fpr])
@@ -2110,6 +2110,7 @@ pub(crate) fn define<'shared>(
sink.put1(offset as u8);
"#,
),
"size_plus_maybe_sib_for_inreg_0_plus_rex_prefix_for_inreg0_outreg0",
);
let has_big_offset =
@@ -2142,7 +2143,7 @@ pub(crate) fn define<'shared>(
);
// XX /r float load with 32-bit offset.
recipes.add_template_recipe(
recipes.add_template_inferred(
EncodingRecipeBuilder::new("fldDisp32", &formats.load, 5)
.operands_in(vec![gpr])
.operands_out(vec![fpr])
@@ -2165,6 +2166,7 @@ pub(crate) fn define<'shared>(
sink.put4(offset as u32);
"#,
),
"size_plus_maybe_sib_for_inreg_0_plus_rex_prefix_for_inreg0_outreg0",
);
}

16
cranelift/codegen/src/isa/x86/enc_tables.rs
View File

@@ -156,6 +156,22 @@ fn size_plus_maybe_sib_or_offset_for_inreg_0_plus_rex_prefix_for_inreg0_outreg0(
+ if needs_rex { 1 } else { 0 }
}
/// Calculates the size while inferring if the first input register (inreg0) and first output
/// register (outreg0) require a dynamic REX and if the first input register (inreg0) requires a
/// SIB.
fn size_plus_maybe_sib_for_inreg_0_plus_rex_prefix_for_inreg0_outreg0(
sizing: &RecipeSizing,
enc: Encoding,
inst: Inst,
divert: &RegDiversions,
func: &Function,
) -> u8 {
let needs_rex = (EncodingBits::from(enc.bits()).rex_w() != 0)
|| test_input(0, inst, divert, func, is_extended_reg)
|| test_result(0, inst, divert, func, is_extended_reg);
size_plus_maybe_sib_for_inreg_0(sizing, enc, inst, divert, func) + if needs_rex { 1 } else { 0 }
}
/// Infers whether a dynamic REX prefix will be emitted, for use with one input reg.
///
/// A REX prefix is known to be emitted if either: