Builds/RandomWOW
1
0
Fork 0
mirror of https://codeberg.org/wownero/RandomWOW synced 2026-03-05 14:17:33 -05:00
Code Issues Packages Projects Releases Wiki Activity

Interpreter with bytecode

Browse Source 
Fixed some undefined behavior with signed types
Fixed different results on big endian systems
Removed unused code files
Restored FNEG_R instructions
Updated documentation
This commit is contained in:
tevador
2019-02-09 15:45:26 +01:00
parent a586751f6b
commit 32d827d0a6
41 changed files with 1517 additions and 3621 deletions
Download Patch File Download Diff File Expand all files Collapse all files

281
src/program.inc
View File

@@ -1,17 +1,14 @@
; FMUL_R e0, a2
mulpd xmm4, xmm10
; IADD_RC r2, r5, -1621224194
; IADD_RC r2, r5, 2673743102
lea r10, [r10+r13-1621224194]
; ISTORE L2[r2], r7
mov eax, r10d
and eax, 262136
mov qword ptr [rsi+rax], r15
; FSUB_M f2, L1[r2]
mov eax, r10d
and eax, 16376
cvtdq2pd xmm12, qword ptr [rsi+rax]
subpd xmm2, xmm12
; IMUL_9C r6, -1003503212
; FNEG_R f2
xorps xmm2, xmm15
; IMUL_9C r6, 3291464084
lea r14, [r14+r14*8-1003503212]
; FSUB_R f1, a0
subpd xmm1, xmm8
@@ -19,11 +16,8 @@
mov eax, r11d
and eax, 262136
xor r13, qword ptr [rsi+rax]
; FSUB_M f2, L1[r4]
mov eax, r12d
and eax, 16376
cvtdq2pd xmm12, qword ptr [rsi+rax]
subpd xmm2, xmm12
; FNEG_R f2
xorps xmm2, xmm15
; FSUB_R f3, a0
subpd xmm3, xmm8
; ISDIV_C r0, 1400272688
@@ -38,35 +32,37 @@
mov eax, r15d
and eax, 16376
imul r11, qword ptr [rsi+rax]
; IROL_R r2, r3
mov ecx, r11d
rol r10, cl
; ISWAP_R r2, r3
xchg r10, r11
; IMULH_R r6, r0
mov rax, r14
mul r8
mov r14, rdx
; FMUL_R e0, a2
mulpd xmm4, xmm10
; IADD_RC r3, r4, -52260428
; IADD_RC r3, r4, 4242706868
lea r11, [r11+r12-52260428]
; IADD_R r7, -1138617760
; IADD_R r7, 3156349536
add r15, -1138617760
; IXOR_M r2, L1[r6]
mov eax, r14d
and eax, 16376
xor r10, qword ptr [rsi+rax]
; FSUB_R f2, a1
subpd xmm2, xmm9
; FSUB_M f2, L1[r5]
mov eax, r13d
and eax, 16376
cvtdq2pd xmm12, qword ptr [rsi+rax]
subpd xmm2, xmm12
; IXOR_R r7, r1
xor r15, r9
; COND_R r2, lt(r7, -41618808)
; COND_R r2, lt(r7, 4253348488)
xor ecx, ecx
cmp r15d, -41618808
setl cl
add r10, rcx
; FMUL_R e3, a0
mulpd xmm7, xmm8
; COND_R r4, sg(r1, -961190365)
; COND_R r4, sg(r1, 3333776931)
xor ecx, ecx
cmp r9d, -961190365
sets cl
@@ -122,19 +118,21 @@
addpd xmm1, xmm8
; FMUL_R e3, a2
mulpd xmm7, xmm10
; FADD_R f0, a1
addpd xmm0, xmm9
; FADD_M f0, L2[r5]
mov eax, r13d
and eax, 262136
cvtdq2pd xmm12, qword ptr [rsi+rax]
addpd xmm0, xmm12
; IMUL_R r5, r6
imul r13, r14
; IADD_RC r1, r2, -1263285243
; IADD_RC r1, r2, 3031682053
lea r9, [r9+r10-1263285243]
; ISUB_M r4, L1[r6]
mov eax, r14d
and eax, 16376
sub r12, qword ptr [rsi+rax]
; IROL_R r7, r2
mov ecx, r10d
rol r15, cl
; FSWAP_R e3
shufpd xmm7, xmm7, 1
; IMUL_R r0, r7
imul r8, r15
; IXOR_R r1, r6
@@ -156,9 +154,8 @@
andps xmm12, xmm14
divpd xmm6, xmm12
maxpd xmm6, xmm13
; IROL_R r2, r0
mov ecx, r8d
rol r10, cl
; ISWAP_R r2, r0
xchg r10, r8
; IADD_R r7, r5
add r15, r13
; FDIV_M e0, L1[r4]
@@ -210,8 +207,11 @@
mov eax, r8d
and eax, 16376
mov qword ptr [rsi+rax], r15
; FSUB_R f0, a1
subpd xmm0, xmm9
; FSUB_M f0, L2[r1]
mov eax, r9d
and eax, 262136
cvtdq2pd xmm12, qword ptr [rsi+rax]
subpd xmm0, xmm12
; FADD_R f3, a1
addpd xmm3, xmm9
; IXOR_R r5, r4
@@ -220,8 +220,8 @@
mov eax, r15d
and eax, 262136
mov qword ptr [rsi+rax], r10
; ISWAP_R r6, r7
xchg r14, r15
; FSWAP_R e2
shufpd xmm6, xmm6, 1
; FADD_R f3, a2
addpd xmm3, xmm10
; ISMULH_R r5, r0
@@ -232,7 +232,7 @@
mov eax, r12d
and eax, 16376
add r8, qword ptr [rsi+rax]
; COND_R r7, ge(r6, -1972898485)
; COND_R r7, ge(r6, 2322068811)
xor ecx, ecx
cmp r14d, -1972898485
setge cl
@@ -242,9 +242,9 @@
; IROR_R r7, r6
mov ecx, r14d
ror r15, cl
; IADD_RC r2, r4, -117457973
; IADD_RC r2, r4, 4177509323
lea r10, [r10+r12-117457973]
; IMUL_R r0, -1500893068
; IMUL_R r0, 2794074228
imul r8, -1500893068
; IADD_R r2, r3
add r10, r11
@@ -265,19 +265,19 @@
lea r14, [r14+r14+540663146]
; IROR_R r5, 58
ror r13, 58
; FSWAP_R f2
shufpd xmm2, xmm2, 1
; FSWAP_R f2
shufpd xmm2, xmm2, 1
; FADD_R f2, a1
addpd xmm2, xmm9
; FADD_R f2, a2
addpd xmm2, xmm10
; FMUL_R e1, a2
mulpd xmm5, xmm10
; ISWAP_R r5, r6
xchg r13, r14
; FSWAP_R e1
shufpd xmm5, xmm5, 1
; IADD_R r5, r3
add r13, r11
; IADD_R r7, -1780268176
; IADD_R r7, 2514699120
add r15, -1780268176
; IADD_RC r7, r0, -1497756854
; IADD_RC r7, r0, 2797210442
lea r15, [r15+r8-1497756854]
; ISTORE L2[r0], r7
mov eax, r8d
@@ -287,8 +287,11 @@
mov rax, r10
imul r12
mov r10, rdx
; FSUB_R f0, a2
subpd xmm0, xmm10
; FSUB_M f0, L1[r2]
mov eax, r10d
and eax, 16376
cvtdq2pd xmm12, qword ptr [rsi+rax]
subpd xmm0, xmm12
; ISMULH_R r2, r3
mov rax, r10
imul r11
@@ -301,8 +304,11 @@
addpd xmm2, xmm8
; FMUL_R e0, a2
mulpd xmm4, xmm10
; FADD_R f2, a3
addpd xmm2, xmm11
; FADD_M f2, L1[r3]
mov eax, r11d
and eax, 16376
cvtdq2pd xmm12, qword ptr [rsi+rax]
addpd xmm2, xmm12
; IMUL_R r1, r2
imul r9, r10
; IMUL_M r7, L1[r5]
@@ -313,11 +319,8 @@
imul r11, r10
; IXOR_R r1, r0
xor r9, r8
; FSUB_M f0, L1[r5]
mov eax, r13d
and eax, 16376
cvtdq2pd xmm12, qword ptr [rsi+rax]
subpd xmm0, xmm12
; FNEG_R f0
xorps xmm0, xmm15
; IADD_RC r4, r4, 1456841848
lea r12, [r12+r12+1456841848]
; IXOR_R r3, r2
@@ -327,19 +330,16 @@
cmp r12d, 1678513610
seto cl
add r8, rcx
; ISMULH_R r4, -1620573087
mov rax, -1620573087
; ISMULH_R r4, r4
mov rax, r12
imul r12
add r12, rdx
mov r12, rdx
; IMUL_R r4, r1
imul r12, r9
; FSWAP_R e1
shufpd xmm5, xmm5, 1
; FADD_M f2, L1[r0]
mov eax, r8d
and eax, 16376
cvtdq2pd xmm12, qword ptr [rsi+rax]
addpd xmm2, xmm12
; FADD_R f1, a2
addpd xmm1, xmm10
; FSUB_R f2, a0
subpd xmm2, xmm8
; FMUL_R e1, a2
mulpd xmm5, xmm10
; FSUB_R f0, a3
@@ -362,29 +362,35 @@
sub r12, qword ptr [rsi+rax]
; FADD_R f2, a2
addpd xmm2, xmm10
; FSUB_R f3, a0
subpd xmm3, xmm8
; FSUB_M f3, L2[r4]
mov eax, r12d
and eax, 262136
cvtdq2pd xmm12, qword ptr [rsi+rax]
subpd xmm3, xmm12
; IXOR_R r7, r2
xor r15, r10
; IXOR_R r0, r5
xor r8, r13
; FSWAP_R f1
shufpd xmm1, xmm1, 1
; FADD_R f1, a2
addpd xmm1, xmm10
; FMUL_R e3, a2
mulpd xmm7, xmm10
; ISWAP_R r7, r1
xchg r15, r9
; ISWAP_R r1, r4
xchg r9, r12
; COND_R r2, ge(r2, -226330940)
; FSWAP_R e3
shufpd xmm7, xmm7, 1
; FSWAP_R f1
shufpd xmm1, xmm1, 1
; COND_R r2, ge(r2, 4068636356)
xor ecx, ecx
cmp r10d, -226330940
setge cl
add r10, rcx
; FMUL_R e2, a3
mulpd xmm6, xmm11
; FSUB_R f2, a1
subpd xmm2, xmm9
; FSUB_M f2, L2[r1]
mov eax, r9d
and eax, 262136
cvtdq2pd xmm12, qword ptr [rsi+rax]
subpd xmm2, xmm12
; FADD_R f1, a0
addpd xmm1, xmm8
; ISUB_R r7, r5
@@ -395,12 +401,11 @@
sub r8, qword ptr [rsi+rax]
; FSUB_R f3, a1
subpd xmm3, xmm9
; IROL_R r3, r5
mov ecx, r13d
rol r11, cl
; ISWAP_R r3, r5
xchg r11, r13
; IADD_RC r5, r2, 795784298
lea r13, [r13+r10+795784298]
; IADD_RC r0, r4, -2050178553
; IADD_RC r0, r4, 2244788743
lea r8, [r8+r12-2050178553]
; IMUL_9C r5, 1062534001
lea r13, [r13+r13*8+1062534001]
@@ -436,16 +441,15 @@
mov rax, r12
imul r10
mov r12, rdx
; IROL_R r3, r0
mov ecx, r8d
rol r11, cl
; ISWAP_R r3, r0
xchg r11, r8
; IXOR_R r2, r0
xor r10, r8
; IXOR_M r0, L2[r1]
mov eax, r9d
and eax, 262136
xor r8, qword ptr [rsi+rax]
; ISDIV_C r7, -935446980
; ISDIV_C r7, 3359520316
mov rax, 7859804860668271393
imul r15
xor eax, eax
@@ -458,11 +462,8 @@
mov eax, r10d
and eax, 16376
imul r14, qword ptr [rsi+rax]
; FSUB_M f3, L1[r6]
mov eax, r14d
and eax, 16376
cvtdq2pd xmm12, qword ptr [rsi+rax]
subpd xmm3, xmm12
; FNEG_R f3
xorps xmm3, xmm15
; IADD_RC r4, r2, 1704868083
lea r12, [r12+r10+1704868083]
; FADD_R f2, a0
@@ -471,8 +472,11 @@
mov eax, r8d
and eax, 16376
mov qword ptr [rsi+rax], r8
; FADD_R f0, a3
addpd xmm0, xmm11
; FADD_M f0, L1[r7]
mov eax, r15d
and eax, 16376
cvtdq2pd xmm12, qword ptr [rsi+rax]
addpd xmm0, xmm12
; FMUL_R e0, a3
mulpd xmm4, xmm11
; FSUB_R f3, a2
@@ -481,8 +485,8 @@
lea r15, [r15+r15+1302457878]
; ISUB_R r1, 1330165941
sub r9, 1330165941
; FSUB_R f1, a3
subpd xmm1, xmm11
; FNEG_R f1
xorps xmm1, xmm15
; IROR_R r0, r4
mov ecx, r12d
ror r8, cl
@@ -491,7 +495,7 @@
; IROR_R r5, r6
mov ecx, r14d
ror r13, cl
; COND_R r0, ab(r1, -310933871)
; COND_R r0, ab(r1, 3984033425)
xor ecx, ecx
cmp r9d, -310933871
seta cl
@@ -516,22 +520,22 @@
andps xmm12, xmm14
divpd xmm5, xmm12
maxpd xmm5, xmm13
; IROL_R r1, 5
rol r9, 5
; IADD_R r7, -1421188024
; FSWAP_R f1
shufpd xmm1, xmm1, 1
; IADD_R r7, 2873779272
add r15, -1421188024
; FSUB_R f3, a2
subpd xmm3, xmm10
; FSUB_M f3, L2[r2]
mov eax, r10d
and eax, 262136
cvtdq2pd xmm12, qword ptr [rsi+rax]
subpd xmm3, xmm12
; FSUB_R f2, a3
subpd xmm2, xmm11
; FADD_M f3, L1[r1]
mov eax, r9d
and eax, 16376
cvtdq2pd xmm12, qword ptr [rsi+rax]
addpd xmm3, xmm12
; FSUB_R f3, a1
subpd xmm3, xmm9
; FMUL_R e1, a3
mulpd xmm5, xmm11
; IADD_RC r2, r4, -317832028
; IADD_RC r2, r4, 3977135268
lea r10, [r10+r12-317832028]
; IMUL_M r4, L1[r5]
mov eax, r13d
@@ -575,12 +579,11 @@
sub r12, r9
; ISUB_R r3, r0
sub r11, r8
; IROL_R r7, r5
mov ecx, r13d
rol r15, cl
; ISWAP_R r7, r5
xchg r15, r13
; IMUL_R r2, r6
imul r10, r14
; COND_R r2, ge(r2, -1892157506)
; COND_R r2, ge(r2, 2402809790)
xor ecx, ecx
cmp r10d, -1892157506
setge cl
@@ -596,7 +599,7 @@
add r9, rdx
; FADD_R f0, a1
addpd xmm0, xmm9
; IADD_RC r5, r7, -477591118
; IADD_RC r5, r7, 3817376178
lea r13, [r13+r15-477591118]
; FSUB_R f0, a3
subpd xmm0, xmm11
@@ -610,9 +613,12 @@
add r8, r12
; FSUB_R f3, a1
subpd xmm3, xmm9
; FSUB_R f2, a0
subpd xmm2, xmm8
; ISDIV_C r2, -396711688
; FSUB_M f2, L1[r4]
mov eax, r12d
and eax, 16376
cvtdq2pd xmm12, qword ptr [rsi+rax]
subpd xmm2, xmm12
; ISDIV_C r2, 3898255608
mov rax, 5964731804029407733
imul r10
xor eax, eax
@@ -621,16 +627,19 @@
sets al
add rdx, rax
add r10, rdx
; FSUB_R f2, a2
subpd xmm2, xmm10
; FNEG_R f2
xorps xmm2, xmm15
; FSUB_R f3, a2
subpd xmm3, xmm10
; FADD_R f1, a3
addpd xmm1, xmm11
; IMUL_R r3, r2
imul r11, r10
; FADD_R f0, a3
addpd xmm0, xmm11
; FADD_M f0, L1[r3]
mov eax, r11d
and eax, 16376
cvtdq2pd xmm12, qword ptr [rsi+rax]
addpd xmm0, xmm12
; ISMULH_R r5, r2
mov rax, r13
imul r10
@@ -639,28 +648,30 @@
mov rax, r14
mul r10
mov r14, rdx
; FADD_R f3, a3
addpd xmm3, xmm11
; FADD_M f3, L1[r3]
mov eax, r11d
and eax, 16376
cvtdq2pd xmm12, qword ptr [rsi+rax]
addpd xmm3, xmm12
; IMUL_R r6, r7
imul r14, r15
; FSUB_R f0, a0
subpd xmm0, xmm8
; FSUB_R f2, a0
subpd xmm2, xmm8
; FNEG_R f2
xorps xmm2, xmm15
; ISUB_R r6, r4
sub r14, r12
; FSWAP_R f1
shufpd xmm1, xmm1, 1
; FADD_R f1, a1
addpd xmm1, xmm9
; IXOR_R r0, r5
xor r8, r13
; FADD_R f2, a1
addpd xmm2, xmm9
; IROL_R r7, r5
mov ecx, r13d
rol r15, cl
; ISWAP_R r7, r5
xchg r15, r13
; FMUL_R e3, a2
mulpd xmm7, xmm10
; IADD_RC r3, r6, -1317630728
; IADD_RC r3, r6, 2977336568
lea r11, [r11+r14-1317630728]
; IMUL_R r2, r3
imul r10, r11
@@ -668,11 +679,8 @@
lea r9, [r9+r12+894105694]
; IMUL_9C r7, 504293473
lea r15, [r15+r15*8+504293473]
; FADD_M f1, L2[r0]
mov eax, r8d
and eax, 262136
cvtdq2pd xmm12, qword ptr [rsi+rax]
addpd xmm1, xmm12
; FSUB_R f1, a0
subpd xmm1, xmm8
; IMUL_R r7, r1
imul r15, r9
; IXOR_R r2, r4
@@ -713,19 +721,16 @@
mov eax, r9d
and eax, 16376
mov qword ptr [rsi+rax], r13
; FSUB_M f0, L1[r1]
mov eax, r9d
and eax, 16376
cvtdq2pd xmm12, qword ptr [rsi+rax]
subpd xmm0, xmm12
; FNEG_R f0
xorps xmm0, xmm15
; FSQRT_R e2
sqrtpd xmm6, xmm6
; FMUL_R e0, a3
mulpd xmm4, xmm11
; FMUL_R e3, a2
mulpd xmm7, xmm10
; IROL_R r5, r2
; IROR_R r5, r2
mov ecx, r10d
rol r13, cl
ror r13, cl
; IADD_R r0, r4
add r8, r12