!!VP1.0
#
# score.vp -- three symbol blosum62 matching on a gpu
# seth hardy (shardy@aculei.net)
# 
# so technically i'm under NDA not to release this, but then again, i never
# got paid for it either. not that it's worth anything anymore, but it just
# might have been when i wrote it. oh well, such is life.
#
# this is a nvidia asm program for vertex shaders, written by hand, back from
# the day when the Cg spec had just been released and the compiler didn't work
# at all.
#
# the purpose of this program is to do three-symbol pattern matching for
# amino acids using the BLOSUM62 matrix. the matrix is loaded in via your
# opengl program, the xyz coordinates and rgb colors of the vertex to be shaded 
# correspond to the two strings. the output vertex is shaded red with an
# intensity equal to the match value.
#
# and for anyone who is interested, here's the definition of the blosum62
# matrix:
#
# const float blosum62[] = {
#  4, -1, -2, -2,  0, -1, -1,  0, -2, -1, -1, -1, -1, -2, -1,  1,  0, -3, -2, 0,
#  5,  0, -2, -3,  1,  0, -2,  0, -3, -2,  2, -1, -3, -2, -1, -1, -3, -2, -3,
#  6,  1, -3,  0,  0,  0,  1, -3, -3,  0, -2, -3, -2,  1,  0, -4, -2, -3,
#  6, -3,  0,  2, -1, -1, -3, -4, -1, -3, -3, -1,  0, -1, -4, -3, -3,
#  9, -3, -4, -3, -3, -1, -1, -3, -1, -2, -3, -1, -1, -2, -2, -1,
#  5,  2, -2,  0, -3, -2,  1,  0, -3, -1,  0, -1, -2, -1, -2,
#  5, -2,  0, -3, -3,  1, -2, -3, -1,  0, -1, -3, -2, -2,
#  6, -2, -4, -4, -2, -3, -3, -2,  0, -2, -2, -3, -3,
#  8, -3, -3, -1, -2, -1, -2, -1, -2, -2,  2, -3,
#  4,  2, -3,  1,  0, -3, -2, -1, -3, -1,  3,
#  4, -2,  2,  0, -3, -2, -1, -2, -1,  1,
#  5, -2, -3, -1,  0, -1, -3, -2, -2,
#  5,  0, -2, -1, -1, -1, -1,  1,
#  6, -4, -2, -2,  1,  3, -1,
#  7, -1, -1, -4, -3, -2,
#  4,  1, -3, -2, -2,
#  5, -2, -2,  0,
# 11,  2, -3,
#  7, -1,
#  4};
#
mov r0.x, c[48].x; 
add r1.x, c[48].z, -v[0].x; 
add r1.y, c[48].w, -v[0].x; 
mul r1.x, r1.x, r1.y; 
rcp r1.y, c[49].x; 
mad r1.x, r1.x, r1.y, v[1].x; 
add r1.x, r1.x, -v[0].x; 
add r0,y, c[48].y, -r1.x; 
exp r2, r1.x; 
add r2, r1.x, -r2.y; 
add r3, r1.x, -r2.x; 
add r4, r3.x, -c[49].y; 
slt r5, r1.x, c[48].x; 
mul r6, r5.x, r3.x; 
add r3, r3.x, -r6.x; 
mad r3.x, r5.x, r4.x, r2.x; 
add r4, r2.x, r1.z; 
mul r6, r5.x, r2.x; 
add r2, r2.x, -r6.x; 
mad r3.y, r5.x, r4.x, r2.x; 
mul r3.y, r3.y, c[49].w; 
add r3.z, r0.x, c[r3.x].w; 
sge r0.x, r3.y, c[49].z, r3.z; 
mov r3.y, r3.w; 
add r3.w, r3.z, -c[49].y; 
mad r0.x, r0.x, r3.w, r0.x; 
add r3.z, r0.x, c[r3.x].z; 
sge r0.x, r3.y, c[49].x, r3.z; 
mov r3.y, r3.w; 
add r3.w, r3.z, -c[49].y; 
mad r0.x, r0.x, r3.w, r0.x; 
add r3.z, r0.x, c[r3.x].x; 
sge r0.x, r3.y, c[49].y, r3.z; 
mov r3.y, r3.w; 
add r3.w, r3.z, -c[49].y; 
mad r0.x, r0.x, r3.w, r0.x; 
add r3.z, r0.x, c[r3.x].y; 
sge r0.x, r3.y, c[48].x, r3.z; 
mov r3.y, r3.w; 
add r3.w, r3.z, -c[49].y; 
mad r0.x, r0.x, r3.w, r0.x; 
add r1.x, c[48].z, -v[0].y; 
add r1.y, c[48].w, -v[0].y; 
mul r1.x, r1.x, r1.y; 
rcp r1.y, c[49].x; 
mad r1.x, r1.x, r1.y, v[1].y; 
add r1.x, r1.x, -v[0].y; 
add r0,y, c[48].y, -r1.x; 
exp r2, r1.x; 
add r2, r1.x, -r2.y; 
add r3, r1.x, -r2.x; 
add r4, r3.x, -c[49].y; 
slt r5, r1.x, c[48].x; 
mul r6, r5.x, r3.x; 
add r3, r3.x, -r6.x; 
mad r3.x, r5.x, r4.x, r2.x; 
add r4, r2.x, r1.z; 
mul r6, r5.x, r2.x; 
add r2, r2.x, -r6.x; 
mad r3.y, r5.x, r4.x, r2.x; 
mul r3.y, r3.y, c[49].w; 
add r3.z, r0.x, c[r3.x].w; 
sge r0.x, r3.y, c[49].z, r3.z; 
mov r3.y, r3.w; 
add r3.w, r3.z, -c[49].y; 
mad r0.x, r0.x, r3.w, r0.x; 
add r3.z, r0.x, c[r3.x].z; 
sge r0.x, r3.y, c[49].x, r3.z; 
mov r3.y, r3.w; 
add r3.w, r3.z, -c[49].y; 
mad r0.x, r0.x, r3.w, r0.x; 
add r3.z, r0.x, c[r3.x].x; 
sge r0.x, r3.y, c[49].y, r3.z; 
mov r3.y, r3.w; 
add r3.w, r3.z, -c[49].y; 
mad r0.x, r0.x, r3.w, r0.x; 
add r3.z, r0.x, c[r3.x].y; 
sge r0.x, r3.y, c[48].x, r3.z; 
mov r3.y, r3.w; 
add r3.w, r3.z, -c[49].y; 
mad r0.x, r0.x, r3.w, r0.x; 
add r1.x, c[48].z, -v[0].z; 
add r1.y, c[48].w, -v[0].z; 
mul r1.x, r1.x, r1.y; 
rcp r1.y, c[49].x; 
mad r1.x, r1.x, r1.y, v[1].z; 
add r1.x, r1.x, -v[0].z; 
add r0,y, c[48].y, -r1.x; 
exp r2, r1.x; 
add r2, r1.x, -r2.y; 
add r3, r1.x, -r2.x; 
add r4, r3.x, -c[49].y; 
slt r5, r1.x, c[48].x; 
mul r6, r5.x, r3.x; 
add r3, r3.x, -r6.x; 
mad r3.x, r5.x, r4.x, r2.x; 
add r4, r2.x, r1.z; 
mul r6, r5.x, r2.x; 
add r2, r2.x, -r6.x; 
mad r3.y, r5.x, r4.x, r2.x; 
mul r3.y, r3.y, c[49].w; 
add r3.z, r0.x, c[r3.x].w; 
sge r0.x, r3.y, c[49].z, r3.z; 
mov r3.y, r3.w; 
add r3.w, r3.z, -c[49].y; 
mad r0.x, r0.x, r3.w, r0.x; 
add r3.z, r0.x, c[r3.x].z; 
sge r0.x, r3.y, c[49].x, r3.z; 
mov r3.y, r3.w; 
add r3.w, r3.z, -c[49].y; 
mad r0.x, r0.x, r3.w, r0.x; 
add r3.z, r0.x, c[r3.x].x; 
sge r0.x, r3.y, c[49].y, r3.z; 
mov r3.y, r3.w; 
add r3.w, r3.z, -c[49].y; 
mad r0.x, r0.x, r3.w, r0.x; 
add r3.z, r0.x, c[r3.x].y; 
sge r0.x, r3.y, c[48].x, r3.z; 
mov r3.y, r3.w; 
add r3.w, r3.z, -c[49].y; 
mad r0.x, r0.x, r3.w, r0.x; 
mov o[pos], v0; 
mov o[col0].x, r0.x; 
mov o[col0].yzw, c[48].x; 
END