mirror of
https://github.com/cemu-project/cemu_graphic_packs.git
synced 2024-12-27 18:31:50 +01:00
8699939dfc
Switch over to Xalphenos version since his version now has a dynamically sized "oldest frame" (there's not really a good name for what it does) thing which was one of the main things in my version. Once FPS++ progress is halted, I'll clean up the comments again to something similar what I had in my version, which I feel is more understandable for people that want to see what it does and maybe improve it. If testing is correct, the previous version also had stability drops or something in comparison with this version. If anything, this update only pushes the arrow time stamina drain fix.
266 lines
12 KiB
Plaintext
266 lines
12 KiB
Plaintext
[BotwFPSV208]
|
|
moduleMatches = 0x6267BFD0
|
|
|
|
#rodata constants
|
|
_float.5 = 0x100005E0
|
|
_float1 = 0x10000670
|
|
_float30 = 0x101E7964
|
|
_convSub = 0x10000BB0
|
|
_float32 = 0x1021FCEC
|
|
_arrowsDiv = 0x1001CCAC
|
|
_arrowsDer = 0x1001CB18
|
|
|
|
#TestCave
|
|
codeCaveSize = 0x12C
|
|
|
|
_fpsCalc = 0x00000010
|
|
0x00000000 = .float 2 ; Don't edit me!
|
|
_lowlimit = 0x00000000
|
|
0x00000004 = .float 62156250
|
|
_busSpeed = 0x00000004
|
|
_averageFPS = 0x00000008
|
|
_speedDiv = 0x0000000C
|
|
# HOW TO CHANGE AMOUNT OF FRAMES TO AVERAGE
|
|
0x00000128 = .float 32 #This float can be anything. To change the amount of frames averaged change this float...
|
|
_bufferSize = 0x00000128 #...and change the "0x84" on line 74 to this number times 4 plus 4 converted to hex.
|
|
#Example using 8 frames. 8 x 4 = 34. 34 + 4 = 38. In hex 0x26
|
|
#So line 74 would change from "cmpwi r12, 0x0C" to "cmpwi r12, 0x26"
|
|
|
|
|
|
0x00000010 = stw r0, 0x78(r30) #orig instruction we are replacing ;ticks between frame are currently in r12.
|
|
0x00000014 = xoris r12, r12, 0x8000 #flip the sign bit of int ticks for floating point conversion
|
|
0x00000018 = stw r12, 0xD4(r30) #store sign flipped ticks in memory as lower half of double
|
|
0x0000001C = lis r12, 0x4330 #create upper half of ticks double
|
|
0x00000020 = stw r12, 0xD0(r30) #store it in upper half of memory
|
|
0x00000024 = lfd f10, 0xD0(r30) #Load full double ticks into f10
|
|
0x00000028 = lis r12, _convSub@ha #load number to subtract from tick double...
|
|
0x0000002C = lfd f12, _convSub@l(r12) #...to create tick float into f12
|
|
0x00000030 = fsub f10, f10, f12 #Do the subtraction
|
|
0x00000034 = frsp f10, f10 #round to single precision and tick float is in f10
|
|
0x00000038 = lis r12, _float1@ha #Load float of 1...
|
|
0x0000003C = lfs f12, _float1@l(r12) #...into f12
|
|
0x00000040 = fdivs f10, f12, f10 #divide 1 by ticks
|
|
0x00000044 = lis r12, _busSpeed@ha #load wii u bus speed...
|
|
0x00000048 = lfs f12, _busSpeed@l(r12) #...into f12
|
|
0x0000004C = fmuls f10, f12, f10 #multiply bus speed to have current fps in f10. (1/ticks)*bus speed
|
|
|
|
0x00000050 = mr r3, r30 #Make a copy of r30 so we can screw around with it
|
|
0x00000054 = addi r3, r3, 0xE0 #Add offset to available memory space
|
|
0x00000058 = stw r3, 0xD8(r30) #Save our virgin memory address so we can retrieve it later
|
|
0x0000005C = lwz r12, 0xDC(r30) #load counter into r12
|
|
0x00000060 = add r3, r3, r12 #add our counter to the offset for our memory location
|
|
0x00000064 = stfsu f10, 0x04(r3) #store current fps to memory location +4 and update efective address into r3
|
|
0x00000068 = lfs f7, 0xE0(r30) #Load fpsSum into f7
|
|
0x0000006C = fadds f10, f10, f7 #Add currentFPS to fpsSum
|
|
0x00000070 = addi r12, r12, 0x04 #Incriment counter by 4
|
|
0x00000074 = cmpwi r12, 0x84 #Compare counter with 0x80(32 address from base memory location)
|
|
0x00000078 = bne .+0x0C #If we write our last current fps then
|
|
0x0000007C = lis r12, 0 #Zero our counter
|
|
0x00000080 = lwz r3, 0xD8(r30) #and reload our virgin memory offset
|
|
0x00000084 = stw r12, 0xDC(r30) #Store counter r12 to memory location
|
|
0x00000088 = lfs f7, 0x04(r3) #load oldest fps into f7
|
|
0x0000008C = fsubs f10, f10, f7 #Subtract oldest fps from fpsSum
|
|
0x00000090 = stfs f10, 0xE0(r30) #store fpsSum back into it's memory address.
|
|
0x00000094 = lis r12, _bufferSize@ha #load 32 as a float ...
|
|
0x00000098 = lfs f7, _bufferSize@l(r12) #...into f7
|
|
0x0000009C = fdivs f10, f10, f7 #divide fps sum by 32, the number of saved fps values, to get average fps over 32 frames
|
|
0x000000A0 = lis r12, _averageFPS@ha #Store averaged fps...
|
|
0x000000A4 = stfs f10, _averageFPS@l(r12) #... into _averageFPS variable.
|
|
|
|
0x000000A8 = lis r12, _float30@ha #Setting up speed diviser. 30/current fps = game speed. ex 30/60 = .5 game speed
|
|
0x000000AC = lfs f12, _float30@l(r12) #load float 30 into f12
|
|
0x000000B0 = fdivs f7, f12, f10 #do the division f10 is our current fps(now averaged)
|
|
0x000000B4 = lis r12, _lowlimit@ha #set up a low limit to not set game speed below. here: 10/30 = 3
|
|
0x000000B8 = lfs f12, _lowlimit@l(r12) #Set 3 as the low limit into f12
|
|
0x000000BC = lis r12, _speedDiv@ha #prepare to store game speed into _speedDiv but wait.
|
|
0x000000C0 = fcmpu cr0, f7, f12 #compare Compare lowlimit with current working game speed
|
|
0x000000C4 = bge .+0x08 #If game speed is not being set below 10 fps...
|
|
0x000000C8 = b .+0x08 #then skip the next line
|
|
0x000000CC = fmr f7, f12 #else overrite working current speed with low limit as new working current speed
|
|
0x000000D0 = stfs f7, _speedDiv@l(r12) #store working current speed into _speedDiv
|
|
|
|
0x000000D4 = lis r12, _float30@ha #An attempt to port arrow fix to fps++
|
|
0x000000D8 = lfs f12, _float30@l(r12) #load float30 into f12
|
|
0x000000DC = fmuls f10, f7, f12 #arrowsDiv = 30 * speedDiv
|
|
0x000000E0 = lis r12, _arrowsDiv@ha
|
|
0x000000E4 = stfs f10, _arrowsDiv@l(r12) #store the results
|
|
0x000000E8 = lis r12, _float.5@ha #load float of .5 into f12
|
|
0x000000EC = lfs f12, _float.5@l(r12)
|
|
0x000000F0 = fdivs f10, f12, f7 #arrowsDer = .5 / speedDiv
|
|
0x000000F4 = lis r12, _arrowsDer@ha
|
|
0x000000F8 = stfs f10, _arrowsDer@l(r12) #store the results
|
|
0x000000FC = blr #return
|
|
|
|
_fenceNeg1 = 0x00000100
|
|
0x00000100 = add r6, r12, r0 #orig instruction we are replacing
|
|
0x00000104 = cmpwi r6, 500 #check if less than 500 (full sync on those first frames to prevent milk water)
|
|
0x00000108 = blt .+0x08 #skip subtract if less than
|
|
0x0000010C = subi r6, r6, 1 #do the subtract
|
|
0x00000110 = blr #return
|
|
|
|
|
|
_arrowTimeDrain = 0x00000114
|
|
0x00000114 = lfs f1, 0xFC(r11)
|
|
0x00000118 = lis r12, _speedDiv@ha
|
|
0x0000011C = lfs f0, _speedDiv@l(r12)
|
|
0x00000120 = fmuls f1, f1, f0
|
|
0x00000124 = blr
|
|
|
|
#codeChanges
|
|
0x031FA97C = bla _fpsCalc
|
|
0x03793328 = nop
|
|
0x03793334 = nop
|
|
0x03793378 = lis r29, _speedDiv@ha
|
|
0x03793380 = lfs f0, _speedDiv@L(r29)
|
|
0x0379338C = nop
|
|
0x03415C1C = lis r12, _speedDiv@ha
|
|
0x03415C24 = lfs f0, _speedDiv@l(r12)
|
|
0x03415C2C = nop
|
|
0x02D90D2C = lis r10, _averageFPS@ha
|
|
0x02D90D30 = lfs f11, _averageFPS@l(r10)
|
|
0x02D90D88 = lis r10, _averageFPS@ha
|
|
0x02D90D8C = lfs f11, _averageFPS@l(r10)
|
|
0x02D5F760 = bla _arrowTimeDrain
|
|
|
|
|
|
#break all forms of frame limiting
|
|
0x031FAAFC = bla _fenceNeg1 ;Best fence (make sure GPU is never more than 1 frame ahead)
|
|
;0x031FAAE8 = li r0, 1 ;Better fence (make sure GPU is never more than 1 second? ahead)
|
|
;0x031FAB00 = nop ; skip fence (no waiting on GPU)
|
|
0x031FACD0 = nop ; disable vsync
|
|
0x031FACF4 = nop ; disable vsync loop
|
|
|
|
|
|
|
|
[BotwFPSv176V192]
|
|
moduleMatches = 0xFD091F9F, 0xD472D8A5
|
|
|
|
# rodata constants
|
|
_float.5 = 0x100005E0
|
|
_float1 = 0x10000670
|
|
_float30 = 0x101E78F4
|
|
_float32 = 0x1025D1A8
|
|
_convSub = 0x10000BB0
|
|
_arrowsDiv = 0x1001CCAC
|
|
_arrowsDer = 0x1001CB18
|
|
|
|
|
|
#TestCave
|
|
codeCaveSize = 0x12C
|
|
|
|
_fpsCalc = 0x00000010
|
|
0x00000000 = .float 2 ; Don't edit me!
|
|
_lowlimit = 0x00000000
|
|
0x00000004 = .float 62156250
|
|
_busSpeed = 0x00000004
|
|
_averageFPS = 0x00000008
|
|
_speedDiv = 0x0000000C
|
|
|
|
# HOW TO CHANGE AMOUNT OF FRAMES TO AVERAGE
|
|
0x00000128 = .float 32 #This float can be anything. To change the amount of frames averaged change this float...
|
|
_bufferSize = 0x00000128 #...and change the "0x84" on line 74 to this number times 4 plus 4 converted to hex.
|
|
#Example using 8 frames. 8 x 4 = 34. 34 + 4 = 38. In hex 0x26
|
|
#So line 74 would change from "cmpwi r12, 0x0C" to "cmpwi r12, 0x26"
|
|
|
|
|
|
0x00000010 = stw r0, 0x78(r30) #orig instruction we are replacing ;ticks between frame are currently in r12.
|
|
0x00000014 = xoris r12, r12, 0x8000 #flip the sign bit of int ticks for floating point conversion
|
|
0x00000018 = stw r12, 0xD4(r30) #store sign flipped ticks in memory as lower half of double
|
|
0x0000001C = lis r12, 0x4330 #create upper half of ticks double
|
|
0x00000020 = stw r12, 0xD0(r30) #store it in upper half of memory
|
|
0x00000024 = lfd f10, 0xD0(r30) #Load full double ticks into f10
|
|
0x00000028 = lis r12, _convSub@ha #load number to subtract from tick double...
|
|
0x0000002C = lfd f12, _convSub@l(r12) #...to create tick float into f12
|
|
0x00000030 = fsub f10, f10, f12 #Do the subtraction
|
|
0x00000034 = frsp f10, f10 #round to single precision and tick float is in f10
|
|
0x00000038 = lis r12, _float1@ha #Load float of 1...
|
|
0x0000003C = lfs f12, _float1@l(r12) #...into f12
|
|
0x00000040 = fdivs f10, f12, f10 #divide 1 by ticks
|
|
0x00000044 = lis r12, _busSpeed@ha #load wii u bus speed...
|
|
0x00000048 = lfs f12, _busSpeed@l(r12) #...into f12
|
|
0x0000004C = fmuls f10, f12, f10 #multiply bus speed to have current fps in f10. (1/ticks)*bus speed
|
|
|
|
0x00000050 = mr r3, r30 #Make a copy of r30 so we can screw around with it
|
|
0x00000054 = addi r3, r3, 0xE0 #Add offset to available memory space
|
|
0x00000058 = stw r3, 0xD8(r30) #Save our virgin memory address so we can retrieve it later
|
|
0x0000005C = lwz r12, 0xDC(r30) #load counter into r12
|
|
0x00000060 = add r3, r3, r12 #add our counter to the offset for our memory location
|
|
0x00000064 = stfsu f10, 0x04(r3) #store current fps to memory location +4 and update efective address into r3
|
|
0x00000068 = lfs f7, 0xE0(r30) #Load fpsSum into f7
|
|
0x0000006C = fadds f10, f10, f7 #Add currentFPS to fpsSum
|
|
0x00000070 = addi r12, r12, 0x04 #Incriment counter by 4
|
|
0x00000074 = cmpwi r12, 0x84 #Compare counter with 0x84(32 address from base memory location)
|
|
0x00000078 = bne .+0x0C #If we write our last current fps then
|
|
0x0000007C = lis r12, 0 #Zero our counter
|
|
0x00000080 = lwz r3, 0xD8(r30) #and reload our virgin memory offset
|
|
0x00000084 = stw r12, 0xDC(r30) #Store counter r12 to memory location
|
|
0x00000088 = lfs f7, 0x04(r3) #load oldest fps into f7
|
|
0x0000008C = fsubs f10, f10, f7 #Subtract oldest fps from fpsSum
|
|
0x00000090 = stfs f10, 0xE0(r30) #store fpsSum back into it's memory address.
|
|
0x00000094 = lis r12, _float32@ha #load 32 as a float ...
|
|
0x00000098 = lfs f7, _float32@l(r12) #...into f7
|
|
0x0000009C = fdivs f10, f10, f7 #divide fps sum by 32, the number of saved fps values, to get average fps over 32 frames
|
|
0x000000A0 = lis r12, _averageFPS@ha #Store averaged fps...
|
|
0x000000A4 = stfs f10, _averageFPS@l(r12) #... into _averageFPS variable.
|
|
|
|
0x000000A8 = lis r12, _float30@ha #Setting up speed diviser. 30/current fps = game speed. ex 30/60 = .5 game speed
|
|
0x000000AC = lfs f12, _float30@l(r12) #load float 30 into f12
|
|
0x000000B0 = fdivs f7, f12, f10 #do the division f10 is our current fps(now averaged)
|
|
0x000000B4 = lis r12, _lowlimit@ha #set up a low limit to not set game speed below. here: 10/30 = 3
|
|
0x000000B8 = lfs f12, _lowlimit@l(r12) #Set 3 as the low limit into f12
|
|
0x000000BC = lis r12, _speedDiv@ha #prepare to store game speed into _speedDiv but wait.
|
|
0x000000C0 = fcmpu cr0, f7, f12 #compare Compare lowlimit with current working game speed
|
|
0x000000C4 = bge .+0x08 #If game speed is not being set below 10 fps...
|
|
0x000000C8 = b .+0x08 #then skip the next line
|
|
0x000000CC = fmr f7, f12 #else overrite working current speed with low limit as new working current speed
|
|
0x000000D0 = stfs f7, _speedDiv@l(r12) #store working current speed into _speedDiv
|
|
|
|
0x000000D4 = lis r12, _float30@ha #An attempt to port arrow fix to fps++
|
|
0x000000D8 = lfs f12, _float30@l(r12) #load float30 into f12
|
|
0x000000DC = fmuls f10, f7, f12 #arrowsDiv = 30 * speedDiv
|
|
0x000000E0 = lis r12, _arrowsDiv@ha
|
|
0x000000E4 = stfs f10, _arrowsDiv@l(r12) #store the results
|
|
0x000000E8 = lis r12, _float.5@ha #load float of .5 into f12
|
|
0x000000EC = lfs f12, _float.5@l(r12)
|
|
0x000000F0 = fdivs f10, f12, f7 #arrowsDer = .5 / speedDiv
|
|
0x000000F4 = lis r12, _arrowsDer@ha
|
|
0x000000F8 = stfs f10, _arrowsDer@l(r12) #store the results
|
|
0x000000FC = blr #return
|
|
|
|
_fenceNeg1 = 0x00000100
|
|
0x00000100 = add r6, r12, r0 #orig instruction we are replacing
|
|
0x00000104 = cmpwi r6, 500 #check if less than 500 (full sync on those first frames to prevent milk water)
|
|
0x00000108 = blt .+0x08 #skip subtract if less than
|
|
0x0000010C = subi r6, r6, 1 #do the subtract
|
|
0x00000110 = blr #return
|
|
|
|
|
|
_arrowTimeDrain = 0x00000114
|
|
0x00000114 = lfs f1, 0xFC(r11)
|
|
0x00000118 = lis r12, _speedDiv@ha
|
|
0x0000011C = lfs f0, _speedDiv@l(r12)
|
|
0x00000120 = fmuls f1, f1, f0
|
|
0x00000124 = blr
|
|
|
|
#codeChanges
|
|
0x031F9E80 = bla _fpsCalc
|
|
0x03792620 = nop
|
|
0x0379262C = nop
|
|
0x03792670 = lis r29, _speedDiv@ha
|
|
0x03792678 = lfs f0, _speedDiv@l(r29)
|
|
0x03792684 = nop
|
|
0x03414EF8 = lis r12, _speedDiv@ha
|
|
0x03414F00 = lfs f0, _speedDiv@l(r12)
|
|
0x03414F08 = nop
|
|
0x02D90790 = lis r10, _averageFPS@ha
|
|
0x02D90794 = lfs f11, _averageFPS@l(r10)
|
|
0x02D907EC = lis r10, _averageFPS@ha
|
|
0x02D907F0 = lfs f11, _averageFPS@l(r10)
|
|
0x02D5F200 = bla _arrowTimeDrain
|
|
|
|
# Break all forms of frame limiting
|
|
0x031FA000 = bla _fenceNeg1
|
|
;0x031F9FEC = li r0, 1
|
|
;0x031FA004 = nop
|
|
0x031FA1D4 = nop
|
|
0x031FA1F8 = nop |