// Enter your kernel in this window
kernel void hello_brook_check(int a<>,int b<>, out int output<>
//first index - key dword, second index - thread
{
output = a-b;
}
result is:
; -------- Disassembly --------------------
00 TEX: ADDR(48) CNT(2) VALID_PIX
0 SAMPLE R1.x___, R0.xyxx, t1, s0 UNNORM(XYZW)
1 SAMPLE R0.x___, R0.xyxx, t0, s0 UNNORM(XYZW)
01 ALU: ADDR(32) CNT(3)
2 y: MOV R1.y, 0.0f
z: SUB_INT ____, 0.0f, R1.x
3 x: ADD_INT R1.x, R0.x, PV2.z
02 EXP_DONE: PIX0, R1.xyyy
END_OF_PROGRAM
why it does 2 opperations here? Target is 4870.
-----------------------------
output = a-b-c-d-e;
; -------- Disassembly --------------------
00 TEX: ADDR(48) CNT(5) VALID_PIX
0 SAMPLE R1.x___, R0.xyxx, t1, s0 UNNORM(XYZW)
1 SAMPLE R4.x___, R0.xyxx, t0, s0 UNNORM(XYZW)
2 SAMPLE R2.x___, R0.xyxx, t2, s0 UNNORM(XYZW)
3 SAMPLE R3.x___, R0.xyxx, t3, s0 UNNORM(XYZW)
4 SAMPLE R0.x___, R0.xyxx, t4, s0 UNNORM(XYZW)
01 ALU: ADDR(32) CNT(9)
5 x: SUB_INT ____, 0.0f, R1.x
y: SUB_INT T0.y, 0.0f, R3.x VEC_021
z: SUB_INT T0.z, 0.0f, R2.x VEC_102
w: MOV R1.w, 0.0f
6 x: SUB_INT ____, 0.0f, R0.x
w: ADD_INT ____, R4.x, PV5.x
7 y: ADD_INT ____, PV6.w, T0.z
z: ADD_INT ____, PV6.x, T0.y
8 x: ADD_INT R1.x, PV7.y, PV7.z
02 EXP_DONE: PIX0, R1.xwww
END_OF_PROGRAM
here we see 8 instead of 4 :-S
