INCLUDELIB ntoskrnl

CONST SEGMENT
    __real@bff0000000000000 DQ 0bff0000000000000r ; -1.0
CONST ENDS

_TEXT SEGMENT
PUBLIC GetTiming

GetTiming PROC
     sub rsp, 70h
     movups [rsp+30h], xmm0
     movups [rsp+40h], xmm1
     movups [rsp+50h], xmm2
     push r10
     push r9
     push r8

    ; Load frequency into r10
    mov r10, rcx

    ; Check if frequency is zero
    test rcx, rcx
    jne SHORT not_zero
    movsd xmm0, QWORD PTR __real@bff0000000000000
    ret

not_zero:
    ; Get high-precision time using RDTSC
    rdtsc
    shl rdx, 32
    or rax, rdx

    ; Compute time_s and time_fract
    xor edx, edx
    div r10
    mov r9, rdx             ; Store time_fract in r9
    mov r8, rax             ; Store time_s in r8

    ; Perform intermediate calculations
    mov rax, -8633038790181359431 
    imul r8
    add rdx, r8
    sar rdx, 24
    mov rcx, rdx
    shr rcx, 63
    add rdx, rcx
    imul rax, rdx, 31536000
    sub r8, rax



    ; Perform the floating-point operation
    xorps xmm0, xmm0
    cvtsi2sd xmm0, r8
    xorps xmm2, xmm2
    cvtsi2sd xmm2, r9
    xorps xmm1, xmm1
    cvtsi2sd xmm1, r10
    divsd xmm2, xmm1
    addsd xmm0, xmm2

    pop r8
    pop r9
    pop r10
    movups xmm0, [rsp+30h]
    movups xmm1, [rsp+40h]
    movups xmm2, [rsp+50h]
    add rsp, 70h


cleanup:
    ret
GetTiming ENDP

_TEXT ENDS

END    

If the code is a call target then the pushfd will re-align the stack, so it will work fine.

But if the code is used inline then this will crash due to the stack being unaligned. You can fix that by changing movaps to movups.. Then it will work in all situations.

If the code is a call target then the pushfd will re-align the stack, so it will work fine.

revolution wrote:

If the code is a call target then the pushfd will re-align the stack, so it will work fine.

It's not pushfd, it's pushfq.