> On Jun 14, 2019, at 12:42 AM, Peter Zijlstra <peterz@xxxxxxxxxxxxx> wrote:
>
> On Thu, Jun 13, 2019 at 06:52:24PM +0000, Song Liu wrote:
>>> On Jun 13, 2019, at 6:21 AM, Josh Poimboeuf <jpoimboe@xxxxxxxxxx> wrote:
>
>>> @@ -403,11 +403,11 @@ static void emit_mov_imm64(u8 **pprog, u32 dst_reg,
>>> * For emitting plain u32, where sign bit must not be
>>> * propagated LLVM tends to load imm64 over mov32
>>> * directly, so save couple of bytes by just doing
>>> - * 'mov %eax, imm32' instead.
>>> + * 'mov imm32, %eax' instead.
>>> */
>>> emit_mov_imm32(&prog, false, dst_reg, imm32_lo);
>>> } else {
>>> - /* movabsq %rax, imm64 */
>>> + /* movabs imm64, %rax */
>>
>> ^^^^^ Should this be moveabsq?
>>
>>> EMIT2(add_1mod(0x48, dst_reg), add_1reg(0xB8, dst_reg));
>>> EMIT(imm32_lo, 4);
>>> EMIT(imm32_hi, 4);
>
> Song, can you please trim replies; I only found what you said because of
> Josh's reply.
Sorry for the problem. I will trim in the future.
Song
