diff options
| -rw-r--r-- | arm9/asm/FX_mtx44.s | 362 | ||||
| -rw-r--r-- | arm9/lib/src/FX_cp.c | 34 | ||||
| -rw-r--r-- | arm9/lib/src/FX_mtx44.c | 172 | ||||
| -rw-r--r-- | include/fx.h | 50 |
4 files changed, 236 insertions, 382 deletions
diff --git a/arm9/asm/FX_mtx44.s b/arm9/asm/FX_mtx44.s deleted file mode 100644 index 0b042dee..00000000 --- a/arm9/asm/FX_mtx44.s +++ /dev/null @@ -1,362 +0,0 @@ - .include "asm/macros.inc" - .include "global.inc" - - .text - - arm_func_start MTX_Identity44_ -MTX_Identity44_: ; 0x020C49C4 - mov r2, #0x1000 - mov r3, #0x0 - stmia r0!, {r2-r3} - mov r1, #0x0 - stmia r0!, {r1,r3} - stmia r0!, {r1-r3} - stmia r0!, {r1,r3} - stmia r0!, {r1-r3} - stmia r0!, {r1,r3} - stmia r0!, {r1-r2} - bx lr - - arm_func_start MTX_Copy44To43_ -MTX_Copy44To43_: - ldmia r0!, {r2-r3,r12} - add r0, r0, #0x4 - stmia r1!, {r2-r3,r12} - ldmia r0!, {r2-r3,r12} - add r0, r0, #0x4 - stmia r1!, {r2-r3,r12} - ldmia r0!, {r2-r3,r12} - add r0, r0, #0x4 - stmia r1!, {r2-r3,r12} - ldmia r0!, {r2-r3,r12} - add r0, r0, #0x4 - stmia r1!, {r2-r3,r12} - bx lr - - thumb_func_start MTX_RotX44_ -MTX_RotX44_: ; 0x020C4A24 - str r2, [r0, #0x14] - str r2, [r0, #0x28] - str r1, [r0, #0x18] - neg r1, r1 - str r1, [r0, #0x24] - mov r1, #0x1 - mov r2, #0x0 - lsl r1, r1, #0xc - mov r3, #0x0 - stmia r0!, {r1-r3} - stmia r0!, {r2-r3} - add r0, #0x8 - stmia r0!, {r2-r3} - add r0, #0x8 - stmia r0!, {r2-r3} - stmia r0!, {r2-r3} - str r1, [r0, #0x0] - bx lr - - thumb_func_start MTX_RotY44_ -MTX_RotY44_: ; 0x020C4A48 - str r2, [r0, #0x0] - str r2, [r0, #0x28] - str r1, [r0, #0x20] - neg r1, r1 - str r1, [r0, #0x8] - mov r3, #0x1 - mov r1, #0x0 - lsl r3, r3, #0xc - mov r2, #0x0 - str r2, [r0, #0x4] - add r0, #0xc - stmia r0!, {r1-r3} - stmia r0!, {r1-r2} - str r2, [r0, #0x4] - add r0, #0xc - stmia r0!, {r1-r2} - stmia r0!, {r1-r3} - bx lr - - thumb_func_start MTX_RotZ44_ -MTX_RotZ44_: ; 0x020C4A6C - str r2, [r0, #0x0] - str r2, [r0, #0x14] - str r1, [r0, #0x4] - neg r1, r1 - str r1, [r0, #0x10] - mov r3, #0x1 - mov r1, #0x0 - lsl r3, r3, #0xc - mov r2, #0x0 - add r0, #0x8 - stmia r0!, {r1-r2} - add r0, #0x8 - stmia r0!, {r1-r2} - stmia r0!, {r1-r3} - stmia r0!, {r1-r2} - stmia r0!, {r1-r3} - bx lr - .balign 4 - - arm_func_start MTX_Concat44 -MTX_Concat44: ; 0x020C4A90 - stmdb sp!, {r4-r11,lr} - sub sp, sp, #0x44 - ldr r5, [r0, #0x4] - ldr r3, [r1, #0x10] - mov r12, r2 - smull r6, r4, r5, r3 - ldr r9, [r0, #0x0] - ldr r3, [r1, #0x0] - cmp r12, r1 - smlal r6, r4, r9, r3 - ldr r10, [r0, #0x8] - ldr r3, [r1, #0x20] - ldr r8, [r0, #0xc] - smlal r6, r4, r10, r3 - ldr r3, [r1, #0x30] - addeq r2, sp, #0x0 - smlal r6, r4, r8, r3 - mov r3, r6, lsr #0xc - orr r3, r3, r4, lsl #0x14 - str r3, [r2, #0x0] - ldr r3, [r1, #0x14] - ldr r4, [r1, #0x4] - smull r7, r6, r5, r3 - smlal r7, r6, r9, r4 - ldr r3, [r1, #0x24] - ldr r4, [r1, #0x34] - smlal r7, r6, r10, r3 - smlal r7, r6, r8, r4 - mov r3, r7, lsr #0xc - orr r3, r3, r6, lsl #0x14 - str r3, [r2, #0x4] - ldr r3, [r1, #0x1c] - ldr r4, [r1, #0xc] - smull r7, r6, r5, r3 - smlal r7, r6, r9, r4 - ldr r3, [r1, #0x2c] - ldr r4, [r1, #0x3c] - smlal r7, r6, r10, r3 - smlal r7, r6, r8, r4 - mov r3, r7, lsr #0xc - orr r3, r3, r6, lsl #0x14 - str r3, [r2, #0xc] - ldr r6, [r1, #0x18] - ldr r7, [r1, #0x8] - smull r4, r3, r5, r6 - smlal r4, r3, r9, r7 - ldr r9, [r1, #0x28] - ldr r5, [r1, #0x38] - smlal r4, r3, r10, r9 - smlal r4, r3, r8, r5 - mov r4, r4, lsr #0xc - orr r4, r4, r3, lsl #0x14 - str r4, [r2, #0x8] - ldr r8, [r0, #0x14] - ldr r10, [r0, #0x10] - smull r4, r3, r8, r6 - smlal r4, r3, r10, r7 - ldr r7, [r0, #0x18] - ldr r6, [r0, #0x1c] - smlal r4, r3, r7, r9 - smlal r4, r3, r6, r5 - mov r4, r4, lsr #0xc - orr r4, r4, r3, lsl #0x14 - str r4, [r2, #0x18] - ldr r3, [r1, #0x14] - ldr r4, [r1, #0x4] - smull r11, r3, r8, r3 - smlal r11, r3, r10, r4 - ldr r5, [r1, #0x24] - ldr r9, [r1, #0x34] - smlal r11, r3, r7, r5 - smlal r11, r3, r6, r9 - mov r4, r11, lsr #0xc - orr r4, r4, r3, lsl #0x14 - str r4, [r2, #0x14] - ldr r3, [r1, #0x1c] - ldr r4, [r1, #0xc] - smull r11, r3, r8, r3 - smlal r11, r3, r10, r4 - ldr r5, [r1, #0x2c] - ldr r9, [r1, #0x3c] - smlal r11, r3, r7, r5 - smlal r11, r3, r6, r9 - mov r4, r11, lsr #0xc - orr r4, r4, r3, lsl #0x14 - str r4, [r2, #0x1c] - ldr r9, [r1, #0x10] - ldr r11, [r1, #0x0] - smull r4, r3, r8, r9 - smlal r4, r3, r10, r11 - ldr r5, [r1, #0x20] - ldr r8, [r1, #0x30] - smlal r4, r3, r7, r5 - smlal r4, r3, r6, r8 - mov r4, r4, lsr #0xc - orr r4, r4, r3, lsl #0x14 - str r4, [r2, #0x10] - ldr r6, [r0, #0x24] - ldr r7, [r0, #0x20] - smull r4, r3, r6, r9 - smlal r4, r3, r7, r11 - ldr r10, [r0, #0x28] - add lr, sp, #0x0 - smlal r4, r3, r10, r5 - ldr r5, [r0, #0x2c] - cmp r2, lr - smlal r4, r3, r5, r8 - mov r4, r4, lsr #0xc - orr r4, r4, r3, lsl #0x14 - str r4, [r2, #0x20] - ldr r3, [r1, #0x14] - ldr r4, [r1, #0x4] - smull r11, r3, r6, r3 - smlal r11, r3, r7, r4 - ldr r8, [r1, #0x24] - ldr r9, [r1, #0x34] - smlal r11, r3, r10, r8 - smlal r11, r3, r5, r9 - mov r4, r11, lsr #0xc - orr r4, r4, r3, lsl #0x14 - str r4, [r2, #0x24] - ldr r3, [r1, #0x1c] - ldr r4, [r1, #0xc] - smull r11, r3, r6, r3 - smlal r11, r3, r7, r4 - ldr r8, [r1, #0x2c] - ldr r9, [r1, #0x3c] - smlal r11, r3, r10, r8 - smlal r11, r3, r5, r9 - mov r4, r11, lsr #0xc - orr r4, r4, r3, lsl #0x14 - str r4, [r2, #0x2c] - ldr r9, [r1, #0x18] - ldr r8, [r1, #0x8] - smull r4, r3, r6, r9 - smlal r4, r3, r7, r8 - ldr r7, [r1, #0x28] - ldr r6, [r1, #0x38] - smlal r4, r3, r10, r7 - smlal r4, r3, r5, r6 - mov r4, r4, lsr #0xc - orr r4, r4, r3, lsl #0x14 - str r4, [r2, #0x28] - ldr r5, [r0, #0x34] - ldr r4, [r0, #0x30] - smull r10, r9, r5, r9 - ldr r3, [r0, #0x38] - smlal r10, r9, r4, r8 - smlal r10, r9, r3, r7 - ldr r0, [r0, #0x3c] - addne sp, sp, #0x44 - smlal r10, r9, r0, r6 - mov r6, r10, lsr #0xc - orr r6, r6, r9, lsl #0x14 - str r6, [r2, #0x38] - ldr r6, [r1, #0x14] - ldr r7, [r1, #0x4] - smull r10, r6, r5, r6 - smlal r10, r6, r4, r7 - ldr r8, [r1, #0x24] - ldr r9, [r1, #0x34] - smlal r10, r6, r3, r8 - smlal r10, r6, r0, r9 - mov r7, r10, lsr #0xc - orr r7, r7, r6, lsl #0x14 - str r7, [r2, #0x34] - ldr r6, [r1, #0x10] - ldr r7, [r1, #0x0] - smull r10, r6, r5, r6 - smlal r10, r6, r4, r7 - ldr r8, [r1, #0x20] - ldr r9, [r1, #0x30] - smlal r10, r6, r3, r8 - smlal r10, r6, r0, r9 - mov r7, r10, lsr #0xc - orr r7, r7, r6, lsl #0x14 - str r7, [r2, #0x30] - ldr r8, [r1, #0x3c] - ldr r7, [r1, #0x2c] - ldr r6, [r1, #0xc] - ldr r1, [r1, #0x1c] - smull r9, r1, r5, r1 - smlal r9, r1, r4, r6 - smlal r9, r1, r3, r7 - smlal r9, r1, r0, r8 - mov r0, r9, lsr #0xc - orr r0, r0, r1, lsl #0x14 - str r0, [r2, #0x3c] - ldmneia sp!, {r4-r11,lr} - bxne lr - ldmia lr!, {r0-r3} - stmia r12!, {r0-r3} - ldmia lr!, {r0-r3} - stmia r12!, {r0-r3} - ldmia lr!, {r0-r3} - stmia r12!, {r0-r3} - ldmia lr, {r0-r3} - stmia r12, {r0-r3} - add sp, sp, #0x44 - ldmia sp!, {r4-r11,lr} - bx lr - - arm_func_start MTX_TransApply44 -MTX_TransApply44: ; 0x020C4DB4 - stmdb sp!, {r4-r7,lr} - sub sp, sp, #0x4 - mov r7, r0 - mov r6, r1 - mov r5, r2 - mov r4, r3 - cmp r7, r6 - beq _020C4DD8 - bl MI_Copy48B -_020C4DD8: - ldr r0, [r7, #0x10] - ldr r1, [r7, #0x0] - smull r3, r2, r4, r0 - smlal r3, r2, r5, r1 - ldr r0, [sp, #0x18] - ldr r1, [r7, #0x20] - ldr r12, [r7, #0x30] - smlal r3, r2, r0, r1 - mov r1, r3, lsr #0xc - orr r1, r1, r2, lsl #0x14 - add r1, r12, r1 - str r1, [r6, #0x30] - ldr r1, [r7, #0x14] - ldr r2, [r7, #0x4] - smull r12, r3, r4, r1 - smlal r12, r3, r5, r2 - ldr r1, [r7, #0x24] - ldr r2, [r7, #0x34] - smlal r12, r3, r0, r1 - mov r1, r12, lsr #0xc - orr r1, r1, r3, lsl #0x14 - add r1, r2, r1 - str r1, [r6, #0x34] - ldr r1, [r7, #0x18] - ldr r2, [r7, #0x8] - smull r12, r3, r4, r1 - smlal r12, r3, r5, r2 - ldr r1, [r7, #0x28] - ldr r2, [r7, #0x38] - smlal r12, r3, r0, r1 - mov r1, r12, lsr #0xc - orr r1, r1, r3, lsl #0x14 - add r1, r2, r1 - str r1, [r6, #0x38] - ldr r1, [r7, #0x1c] - ldr r2, [r7, #0xc] - smull r12, r3, r4, r1 - smlal r12, r3, r5, r2 - ldr r1, [r7, #0x2c] - ldr r2, [r7, #0x3c] - smlal r12, r3, r0, r1 - mov r0, r12, lsr #0xc - orr r0, r0, r3, lsl #0x14 - add r0, r2, r0 - str r0, [r6, #0x3c] - add sp, sp, #0x4 - ldmia sp!, {r4-r7,lr} - bx lr diff --git a/arm9/lib/src/FX_cp.c b/arm9/lib/src/FX_cp.c index a8da0a8f..a2d8307b 100644 --- a/arm9/lib/src/FX_cp.c +++ b/arm9/lib/src/FX_cp.c @@ -1,11 +1,7 @@ #include "global.h" #include "main.h" #include "fx.h" - -s32 FX_GetDivResult(); -s32 FX_GetSqrtResult(); -void FX_DivAsync(s32 numerator, s32 denominator); -void FX_InvAsync(s32 x); + s32 FX_Div(s32 numerator, s32 denominator){ FX_DivAsync(numerator, denominator); @@ -57,18 +53,18 @@ void FX_DivAsync(s32 numerator, s32 denominator){ SETREG64(HW_REG_DIV_DENOM, (u32)denominator); } - s32 FX_DivS32(s32 numerator, s32 denominator){ - SETREG16(HW_REG_DIVCNT, 0x0); - SETREG32(HW_REG_DIV_NUMER, (u32)numerator); //32bit write for some reason - SETREG64(HW_REG_DIV_DENOM, (u32)denominator); - while (READREG16(HW_REG_DIVCNT) & 0x8000); - return READREG32(HW_REG_DIV_RESULT); - } +s32 FX_DivS32(s32 numerator, s32 denominator){ + SETREG16(HW_REG_DIVCNT, 0x0); + SETREG32(HW_REG_DIV_NUMER, (u32)numerator); //32bit write for some reason + SETREG64(HW_REG_DIV_DENOM, (u32)denominator); + while (READREG16(HW_REG_DIVCNT) & 0x8000); + return READREG32(HW_REG_DIV_RESULT); +} - s32 FX_ModS32(s32 num, s32 mod){ - SETREG16(HW_REG_DIVCNT, 0x0); - SETREG32(HW_REG_DIV_NUMER, (u32)num); //32bit write for some reason - SETREG64(HW_REG_DIV_DENOM, (u32)mod); - while (READREG16(HW_REG_DIVCNT) & 0x8000); - return READREG32(HW_REG_DIVREM_RESULT); - } +s32 FX_ModS32(s32 num, s32 mod){ + SETREG16(HW_REG_DIVCNT, 0x0); + SETREG32(HW_REG_DIV_NUMER, (u32)num); //32bit write for some reason + SETREG64(HW_REG_DIV_DENOM, (u32)mod); + while (READREG16(HW_REG_DIVCNT) & 0x8000); + return READREG32(HW_REG_DIVREM_RESULT); +} diff --git a/arm9/lib/src/FX_mtx44.c b/arm9/lib/src/FX_mtx44.c new file mode 100644 index 00000000..3c91b4df --- /dev/null +++ b/arm9/lib/src/FX_mtx44.c @@ -0,0 +1,172 @@ +#include "global.h" +#include "main.h" +#include "fx.h" + +void MI_Copy48B(void *src, void *dst); + + +void MTX_TransApply44(struct Mtx44 *mtx, struct Mtx44 *dst, s32 x, s32 y, s32 z){ + if(mtx != dst) + MI_Copy48B(mtx, dst); + dst->_[12] = mtx->_[12] + (s32)(((s64)x * mtx->_[0] + (s64)y * mtx->_[4] + (s64)z * mtx->_[8] ) >> FX32_INT_SHIFT); + dst->_[13] = mtx->_[13] + (s32)(((s64)x * mtx->_[1] + (s64)y * mtx->_[5] + (s64)z * mtx->_[9] ) >> FX32_INT_SHIFT); + dst->_[14] = mtx->_[14] + (s32)(((s64)x * mtx->_[2] + (s64)y * mtx->_[6] + (s64)z * mtx->_[10]) >> FX32_INT_SHIFT); + dst->_[15] = mtx->_[15] + (s32)(((s64)x * mtx->_[3] + (s64)y * mtx->_[7] + (s64)z * mtx->_[11]) >> FX32_INT_SHIFT); +} + +void MTX_Concat44(struct Mtx44 *a, struct Mtx44 *b, struct Mtx44 *c){ + struct Mtx44 temp; + struct Mtx44 *dst; + s32 a0, a1, a2, a3; + s32 b0, b1, b2, b3; + + if (c == b) + dst = &temp; + else + dst = c; + + a0 = a->_[0]; + a1 = a->_[1]; + a2 = a->_[2]; + a3 = a->_[3]; + dst->_[0] = (((s64)a0 * b->_[0] + (s64)a1 * b->_[4] + (s64)a2 * b->_[8] + (s64)a3 * b->_[12]) >> FX32_INT_SHIFT); + dst->_[1] = (((s64)a0 * b->_[1] + (s64)a1 * b->_[5] + (s64)a2 * b->_[9] + (s64)a3 * b->_[13]) >> FX32_INT_SHIFT); + dst->_[3] = (((s64)a0 * b->_[3] + (s64)a1 * b->_[7] + (s64)a2 * b->_[11] + (s64)a3 * b->_[15]) >> FX32_INT_SHIFT); + b0 = b->_[2]; + b1 = b->_[6]; + b2 = b->_[10]; + b3 = b->_[14]; + dst->_[2] = (((s64)a0 * b0 + (s64)a1 * b1 + (s64)a2 * b2 + (s64)a3 * b3) >> FX32_INT_SHIFT); + a0 = a->_[4]; + a1 = a->_[5]; + a2 = a->_[6]; + a3 = a->_[7]; + dst->_[6] = (((s64)a0 * b0 + (s64)a1 * b1 + (s64)a2 * b2 + (s64)a3 * b3) >> FX32_INT_SHIFT); + dst->_[5] = (((s64)a0 * b->_[1] + (s64)a1 * b->_[5] + (s64)a2 * b->_[9] + (s64)a3 * b->_[13]) >> FX32_INT_SHIFT); + dst->_[7] = (((s64)a0 * b->_[3] + (s64)a1 * b->_[7] + (s64)a2 * b->_[11] + (s64)a3 * b->_[15]) >> FX32_INT_SHIFT); + b0 = b->_[0]; + b1 = b->_[4]; + b2 = b->_[8]; + b3 = b->_[12]; + dst->_[4] = (((s64)a0 * b0 + (s64)a1 * b1 + (s64)a2 * b2 + (s64)a3 * b3) >> FX32_INT_SHIFT); + a0 = a->_[8]; + a1 = a->_[9]; + a2 = a->_[10]; + a3 = a->_[11]; + dst->_[8] = (((s64)a0 * b0 + (s64)a1 * b1 + (s64)a2 * b2 + (s64)a3 * b3) >> FX32_INT_SHIFT); + dst->_[9] = (((s64)a0 * b->_[1] + (s64)a1 * b->_[5] + (s64)a2 * b->_[9] + (s64)a3 * b->_[13]) >> FX32_INT_SHIFT); + dst->_[11] = (((s64)a0 * b->_[3] + (s64)a1 * b->_[7] + (s64)a2 * b->_[11] + (s64)a3 * b->_[15]) >> FX32_INT_SHIFT); + b0 = b->_[2]; + b1 = b->_[6]; + b2 = b->_[10]; + b3 = b->_[14]; + dst->_[10] = (((s64)a0 * b0 + (s64)a1 * b1 + (s64)a2 * b2 + (s64)a3 * b3) >> FX32_INT_SHIFT); + a0 = a->_[12]; + a1 = a->_[13]; + a2 = a->_[14]; + a3 = a->_[15]; + dst->_[14] = (((s64)a0 * b0 + (s64)a1 * b1 + (s64)a2 * b2 + (s64)a3 * b3) >> FX32_INT_SHIFT); + dst->_[13] = (((s64)a0 * b->_[1] + (s64)a1 * b->_[5] + (s64)a2 * b->_[9] + (s64)a3 * b->_[13]) >> FX32_INT_SHIFT); + dst->_[12] = (((s64)a0 * b->_[0] + (s64)a1 * b->_[4] + (s64)a2 * b->_[8] + (s64)a3 * b->_[12]) >> FX32_INT_SHIFT); + dst->_[15] = (((s64)a0 * b->_[3] + (s64)a1 * b->_[7] + (s64)a2 * b->_[11] + (s64)a3 * b->_[15]) >> FX32_INT_SHIFT); + if (dst == &temp) + *c = temp; +} + +asm void MTX_Identity44_(struct Mtx44 *dst){ + mov r2, #0x1000 + mov r3, #0x0 + stmia r0!, {r2-r3} + mov r1, #0x0 + stmia r0!, {r1,r3} + stmia r0!, {r1-r3} + stmia r0!, {r1,r3} + stmia r0!, {r1-r3} + stmia r0!, {r1,r3} + stmia r0!, {r1-r2} + bx lr +} + +asm void MTX_Copy44To43_(struct Mtx44 *src, struct Mtx43 *dst){ + ldmia r0!, {r2-r3,r12} + add r0, r0, #0x4 + stmia r1!, {r2-r3,r12} + ldmia r0!, {r2-r3,r12} + add r0, r0, #0x4 + stmia r1!, {r2-r3,r12} + ldmia r0!, {r2-r3,r12} + add r0, r0, #0x4 + stmia r1!, {r2-r3,r12} + ldmia r0!, {r2-r3,r12} + add r0, r0, #0x4 + stmia r1!, {r2-r3,r12} + bx lr +} + +#pragma thumb on +asm void MTX_RotX44_(struct Mtx44 *mtx, s32 sinphi, s32 cosphi){ + str r2, [r0, #0x14] + str r2, [r0, #0x28] + str r1, [r0, #0x18] + neg r1, r1 + str r1, [r0, #0x24] + mov r1, #0x1 + mov r2, #0x0 + lsl r1, r1, #0xc + mov r3, #0x0 + stmia r0!, {r1-r3} + stmia r0!, {r2-r3} + add r0, #0x8 + stmia r0!, {r2-r3} + add r0, #0x8 + stmia r0!, {r2-r3} + stmia r0!, {r2-r3} + str r1, [r0, #0x0] + bx lr +} +#pragma thumb off + +#pragma thumb on +asm void MTX_RotY44_(struct Mtx44 *mtx, s32 sinphi, s32 cosphi){ + str r2, [r0, #0x0] + str r2, [r0, #0x28] + str r1, [r0, #0x20] + neg r1, r1 + str r1, [r0, #0x8] + mov r3, #0x1 + mov r1, #0x0 + lsl r3, r3, #0xc + mov r2, #0x0 + str r2, [r0, #0x4] + add r0, #0xc + stmia r0!, {r1-r3} + stmia r0!, {r1-r2} + str r2, [r0, #0x4] + add r0, #0xc + stmia r0!, {r1-r2} + stmia r0!, {r1-r3} + bx lr +} +#pragma thumb off + +#pragma thumb on +asm void MTX_RotZ44_(struct Mtx44 *mtx, s32 sinphi, s32 cosphi){ + str r2, [r0, #0x0] + str r2, [r0, #0x14] + str r1, [r0, #0x4] + neg r1, r1 + str r1, [r0, #0x10] + mov r3, #0x1 + mov r1, #0x0 + lsl r3, r3, #0xc + mov r2, #0x0 + add r0, #0x8 + stmia r0!, {r1-r2} + add r0, #0x8 + stmia r0!, {r1-r2} + stmia r0!, {r1-r3} + stmia r0!, {r1-r2} + stmia r0!, {r1-r3} + bx lr +} +#pragma thumb off diff --git a/include/fx.h b/include/fx.h index 22ef3d3a..1e9eb291 100644 --- a/include/fx.h +++ b/include/fx.h @@ -1,6 +1,11 @@ #ifndef GUARD_FX_H #define GUARD_FX_H +#define FX16_INT_MASK 0xF000 +#define FX16_INT_ABS_MASK 0x7000 +#define FX16_FRAC_MASK 0x0FFF +#define FX16_INT_SHIFT 0xC + #define FX32_INT_MASK 0xFFFFF000 #define FX32_INT_ABS_MASK 0x7FFFF000 #define FX32_FRAC_MASK 0x00000FFF @@ -20,6 +25,10 @@ #define FX_INT_ABS(TYPE, x) (((x) & TYPE ## _INT_ABS_MASK) >> TYPE ## _INT_SHIFT) #define FX_FRAC(TYPE, x) ((x) & TYPE ## _FRAC_MASK) +#define FX16_INT(x) FX_INT(FX16, x) +#define FX16_INT_ABS(x) FX_INT_ABS(FX16, x) +#define FX16_FRAC(x) FX_FRAC(FX16, x) + #define FX32_INT(x) FX_INT(FX32, x) #define FX32_INT_ABS(x) FX_INT_ABS(FX32, x) #define FX32_FRAC(x) FX_FRAC(FX32, x) @@ -33,7 +42,6 @@ #define FX64C_FRAC(x) FX_FRAC(FX64C, x) - #define HW_REG_DIVCNT 0x04000280 #define HW_REG_DIV_NUMER 0x04000290 #define HW_REG_DIV_DENOM 0x04000298 @@ -65,6 +73,26 @@ struct Vecx16 s16 z; }; +struct Mtx44 +{ + s32 _[16]; +}; + +struct Mtx43 +{ + s32 _[12]; +}; + +struct Mtx33 +{ + s32 _[9]; +}; + +struct Mtx22 +{ + s32 _[4]; +}; + //FX void FX_Init(); s32 FX_Modf(s32 x, s32 *iptr); @@ -78,6 +106,13 @@ void VEC_Add(struct Vecx32 *x, struct Vecx32 *y, struct Vecx32 *dst); void VEC_Subtract(struct Vecx32 *x, struct Vecx32 *y, struct Vecx32 *dst); void VEC_Fx16Add(struct Vecx16 *x, struct Vecx16 *y, struct Vecx16 *dst); s32 VEC_DotProduct(struct Vecx32 *x, struct Vecx32 *y); +s32 VEC_Fx16DotProduct(struct Vecx16 *a, struct Vecx16 *b); +void VEC_CrossProduct(struct Vecx32 *a, struct Vecx32 *b, struct Vecx32 *dst); +void VEC_Fx16CrossProduct(struct Vecx16 *a, struct Vecx16 *b, struct Vecx16 *dst); +s32 VEC_Mag(struct Vecx32 *a); +void VEC_Normalize(struct Vecx32 *a, struct Vecx32 *dst); +void VEC_Fx16Normalize(struct Vecx16 *a, struct Vecx16 *dst); +void VEC_MultAdd(s32 factor, struct Vecx32 *a, struct Vecx32 *b, struct Vecx32 *dst); //CP s32 FX_Div(s32 numerator, s32 denominator); @@ -91,4 +126,17 @@ void FX_DivAsync(s32 numerator, s32 denominator); s32 FX_DivS32(s32 numerator, s32 denominator); s32 FX_ModS32(s32 num, s32 mod); +//Mtx +//The functions ending in underscores seem to be in assembly originally +//at least I see no way to recreate the stmia copies and some of them are actually in thumb +//Mtx44 +void MTX_TransApply44(struct Mtx44 *mtx, struct Mtx44 *dst, s32 x, s32 y, s32 z); +void MTX_Concat44(struct Mtx44 *a, struct Mtx44 *b, struct Mtx44 *c); +void MTX_Identity44_(struct Mtx44 *dst); +void MTX_Copy44To43_(struct Mtx44 *src, struct Mtx43 *dst); +void MTX_RotX44_(struct Mtx44 *mtx, s32 sinphi, s32 cosphi); +void MTX_RotY44_(struct Mtx44 *mtx, s32 sinphi, s32 cosphi); +void MTX_RotZ44_(struct Mtx44 *mtx, s32 sinphi, s32 cosphi); + + #endif //GUARD_FX_H |