35     VLDMIA      r2,{s0-s15}         // The entire p2 matrix is put in the [S0-S15] registers  in MTX44AddAsm()
38     VADD.F32    s0,s16,s0  in MTX44AddAsm()
63     VSTMIA      r0,{s0-s15}         // Store result  in MTX44AddAsm()
73     VLDMIA      r1,{s0-s15}     // All p are put in the [S0-S15] registers  in MTX44CopyAsm()
74     VSTMIA      r0,{s0-s15}     // All pOut are put in the [S0-S15] registers  in MTX44CopyAsm()
87     VMUL.F32    s0,s24,s16  in MTX44MultAsm()
113     VMLA.F32    s0,s24,s20  in MTX44MultAsm()
139     VMLA.F32    s0,s24,s16  in MTX44MultAsm()
163     VMLA.F32    s0,s24,s20  in MTX44MultAsm()
186     VSTMIA      r0,{s0-s15}         // Store result  in MTX44MultAsm()
198     VMUL.F32    s1,s1,s0  in MTX44MultAsm()
199     VMUL.F32    s2,s2,s0  in MTX44MultAsm()
200     VMUL.F32    s3,s3,s0  in MTX44MultAsm()
202     VMUL.F32    s4,s4,s0  in MTX44MultAsm()
203     VMUL.F32    s5,s5,s0  in MTX44MultAsm()
204     VMUL.F32    s6,s6,s0  in MTX44MultAsm()
205     VMUL.F32    s7,s7,s0  in MTX44MultAsm()
207     VMUL.F32    s8,s8,s0  in MTX44MultAsm()
208     VMUL.F32    s9,s9,s0  in MTX44MultAsm()
209     VMUL.F32    s10,s10,s0  in MTX44MultAsm()
210     VMUL.F32    s11,s11,s0  in MTX44MultAsm()
212     VMUL.F32    s12,s12,s0  in MTX44MultAsm()
213     VMUL.F32    s13,s13,s0  in MTX44MultAsm()
214     VMUL.F32    s14,s14,s0  in MTX44MultAsm()
215     VMUL.F32    s15,s15,s0  in MTX44MultAsm()
217     VMUL.F32    s0,s16,s0  in MTX44MultAsm()
219     VSTMIA      r0,{s0-s15}         // Store result  in MTX44MultAsm()
226     VLDMIA      r1,{s0-s11}        // Matrix p is put into the [S0-S11] registers  in MTX44MultScaleAsm()
229     VMUL.F32    s0,s0,s12  in MTX44MultScaleAsm()
241     VSTMIA      r0,{s0-s11}         // Store result  in MTX44MultScaleAsm()
248     VLDMIA      r2,{s0-s11}        // Matrix p is put into the [S0-S11] registers  in MTX44MultScaleAsm()
251     VMUL.F32    s0,s0,s12  in MTX44MultScaleAsm()
266     VSTMIA      r0,{s0-s11}         // Store result  in MTX44MultScaleAsm()
273     VLDMIA      r2,{s0-s11}         // The entire pM matrix is put in the [S0-S11] registers  in MTX44MultTranslateAsm()
280     VSTMIA      r0,{s0-s11}         // Store result  in MTX44MultTranslateAsm()
287     VLDMIA      r1!,{s0-s11}        // Matrix pM is put into the [S0-S11] registers  in MTX44MultTranslateAsm()
290     VMLA.F32    s3,s0,s12  in MTX44MultTranslateAsm()
304     VSTMIA      r0,{s0-s15}         // Store result  in MTX44MultTranslateAsm()
312     VLDR.F32    s0,[r1,#0*16+0*4]  in MTX44TransposeAsm()
329     VSTMIA      r0,{s0-s15}         // Store result  in MTX44TransposeAsm()
338     VLDMIA      r1,{s0-s15}         // The entire pM matrix is put in the [S0-S15] registers  in VEC3TransformAsm()
341     VMLA.F32    s3,s0,s16  in VEC3TransformAsm()