blob: cc39c776747bcaf5cc9c287bbb17dc4553a273d9 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
|
//TEST_CATEGORY(wave, compute)
//DISABLE_TEST:COMPARE_COMPUTE_EX:-cpu -compute -shaderobj
//DISABLE_TEST:COMPARE_COMPUTE_EX:-slang -compute -shaderobj
//TEST:COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -profile cs_6_0 -shaderobj -render-feature hardware-device
//TEST(vulkan):COMPARE_COMPUTE_EX:-vk -compute -shaderobj -render-feature hardware-device
//TEST:COMPARE_COMPUTE_EX:-cuda -compute -render-features cuda_sm_7_0 -shaderobj
//TEST_INPUT:ubuffer(data=[0 0 0 0 0 0 0 0], stride=4):out,name outputBuffer
RWStructuredBuffer<int> outputBuffer;
[numthreads(8, 1, 1)]
void computeMain(uint3 dispatchThreadID : SV_DispatchThreadID)
{
const int idx = int(dispatchThreadID.x);
int2 v0 = int2(idx + 1, idx + 2);
float2 v1 = float2(idx + 2, idx + 3);
// NOTE! dxc only supports bit ops on uint and associated types NOT int
uint2 uv0 = v0;
int2 r0 = WaveActiveSum(v0);
float2 r1 = WaveActiveSum(v1);
int2 r2 = WaveActiveBitXor(uv0);
int2 r3 = WaveActiveBitOr(uv0);
int2 r4 = WaveActiveBitAnd(uv0);
int2 r = r0 + int2(r1) + r2 + r3 + r4;
outputBuffer[idx] = r.x + r.y;
}
|
