4ca9e82bd1
Adds Bswap to the Cranelift IR. Implements the Bswap instruction in the x64 and aarch64 codegen backends. Cranelift users can now: ``` builder.ins().bswap(value) ``` to get a native byteswap instruction. * x64: implements the 32- and 64-bit bswap instruction, following the pattern set by similar unary instrutions (Neg and Not) - it only operates on a dst register, but is parameterized with both a src and dst which are expected to be the same register. As x64 bswap instruction is only for 32- or 64-bit registers, the 16-bit swap is implemented as a rotate left by 8. Updated x64 RexFlags type to support emitting for single-operand instructions like bswap * aarch64: Bswap gets emitted as aarch64 rev16, rev32, or rev64 instruction as appropriate. * s390x: Bswap was already supported in backend, just had to add a bit of plumbing * For completeness, added bswap to the interpreter as well. * added filetests and runtests for each ISA * added bswap to fuzzgen, thanks to afonso360 for the code there * 128-bit swaps are not yet implemented, that can be done later
59 lines
1.3 KiB
Plaintext
59 lines
1.3 KiB
Plaintext
test interpret
|
|
test run
|
|
target x86_64
|
|
target aarch64
|
|
target s390x
|
|
|
|
function %bswap_i16(i16) -> i16 {
|
|
block0(v0: i16):
|
|
v1 = bswap v0
|
|
return v1
|
|
}
|
|
; run: %bswap_i16(0) == 0
|
|
; run: %bswap_i16(1) == 0x0100
|
|
; run: %bswap_i16(0x1234) == 0x3412
|
|
; run: %bswap_i16(-2) == 0xFEFF
|
|
|
|
function %bswap_i32(i32) -> i32 {
|
|
block0(v0: i32):
|
|
v1 = bswap v0
|
|
return v1
|
|
}
|
|
; run: %bswap_i32(0) == 0
|
|
; run: %bswap_i32(1) == 0x01000000
|
|
; run: %bswap_i32(0x12345678) == 0x78563412
|
|
; run: %bswap_i32(-2) == 0xFEFFFFFF
|
|
|
|
function %bswap_i64(i64) -> i64 {
|
|
block0(v0: i64):
|
|
v1 = bswap v0
|
|
return v1
|
|
}
|
|
; run: %bswap_i64(0) == 0
|
|
; run: %bswap_i64(1) == 0x0100000000000000
|
|
; run: %bswap_i64(0x123456789ABCDEF0) == 0xF0DEBC9A78563412
|
|
; run: %bswap_i64(-2) == 0xFEFFFFFFFFFFFFFF
|
|
|
|
function %fuzzer_case_0() -> i8, i32, i64 {
|
|
block0:
|
|
v5 = iconst.i64 0x9903_5204_d05f_abab
|
|
v6 = bswap v5
|
|
v7 = iconst.i8 0
|
|
v8 = iconst.i32 0
|
|
return v7, v8, v6
|
|
}
|
|
|
|
; run: %fuzzer_case_0() == [0, 0, 0xabab_5fd0_0452_0399]
|
|
|
|
function %fuzzer_case_1(f32, f64, i32, i32, f64) -> i8, i32, i64 {
|
|
block0(v0: f32, v1: f64, v2: i32, v3: i32, v4: f64):
|
|
v5 = iconst.i64 0x9903_5204_d05f_abab
|
|
v6 = bswap v5
|
|
v7 = iconst.i8 0
|
|
v8 = iconst.i32 0
|
|
return v7, v8, v6
|
|
}
|
|
|
|
; run: %fuzzer_case_1(0.0, 0.0, 0, 0, 0.0) == [0, 0, 0xabab_5fd0_0452_0399]
|
|
|