将《底特律：变人》从 PlayStation® 4 移植到 PC – 第二部分

// the descriptor set, an array of 13 resources (textures)
[[vk::binding(0)]] RWTexture2D imgDst[13] :register(u0);

// the threadgroup has 128 lanes so there are in total either 4 or 2 subgroups
// (of size 32 or respectively of size 64)
[numthreads(64,2,1)]

void main(uint3 LocalThreadId : SV_GroupThreadID)
{
    // the index that will be used to access an element in the descriptor set
    uint index = 0;

    // load instruction for the texture at index 0
    float4 value = imgDst[index].Load(LocalThreadId.xy);

    // store instruction for the texture at index 1
    imgDst[index + 1][LocalThreadId.xy] = value;
}

s_inst_prefetch  0x3
s_getpc_b64   s[0:1]
s_mov_b32  s0, s2

// here we load the descriptor for the texture we want to access:
// the descriptor of texture[0] is loaded to scalar registers s[4:11]
// the descriptors are always stored in scalar registers
// and thus, are uniform across all lanes
s_load_dwordx8  s[4:11], s[0:1], 0x0
s_waitcnt     lgkmcnt(0)

// we load from descriptor stored at s[4:11] -> points to texture[0]
image_load v[2:5], v[0:1], s[4:11] dmask:0xf dim:SQ_RSRC_IMG_2D
v_nop

// we load the descriptor of texture[1] into s[0:7]
s_load_dwordx8  s[0:7], s[0:1], 0x20
s_waitcnt     vmcnt(0)  lgkmcnt(0)

// we write into texture[1]
image_store   v[2:5], v[0:1], s[0:7] dmask:0xf dim:SQ_RSRC_IMG_2D unorm glc
s_endpgm

[[vk::binding(0)]] RWTexture2D imgDst[13] :register(u0);
[numthreads(64,2,1)]

void main(uint3 LocalThreadId : SV_GroupThreadID)
{
    uint index = LocalThreadId.y;
    float4 value = imgDst[index].Load(LocalThreadId.xy);
    imgDst[index + 1][LocalThreadId.xy] = value;
}

s_inst_prefetch  0x3
s_getpc_b64   s[0:1]

// only load the value of gl_LocalInvocationID.y of the first active lane
// as index is considered a uniform value, it must be equal across all lanes
// store it in a scalar register
v_readfirstlane_b32  s0, v1
s_mov_b32  s3, s1
s_lshl_b32 s0, s0, 5

// load the texture descriptor from texture[gl_LocalInvocationID.y-from-first-lane]
s_load_dwordx8  s[4:11], s[2:3], s0
s_add_u32  s0, s0, 32
s_waitcnt     lgkmcnt(0)
image_load v[2:5], v[0:1], s[4:11] dmask:0xf dim:SQ_RSRC_IMG_2D
v_nop
s_load_dwordx8  s[0:7], s[2:3], s0
s_waitcnt     vmcnt(0)  lgkmcnt(0)
image_store   v[2:5], v[0:1], s[0:7] dmask:0xf dim:SQ_RSRC_IMG_2D unorm glc
s_endpgm

[numthreads(16,8,1)]

[[vk::binding(0)]] RWTexture2D imgDst[13] :register(u0);
[numthreads(16,8,1)]

void main(uint3 LocalThreadId : SV_GroupThreadID)
{
    uint index = LocalThreadId.y;
    float4 value = imgDst[NonUniformResourceIndex(index)].Load(LocalThreadId.xy);
    imgDst[NonUniformResourceIndex(index + 1)][LocalThreadId.xy] = value;
}

s_inst_prefetch  0x3
s_getpc_b64   s[0:1]
s_mov_b32  s0, s2
v_lshlrev_b32_e32  v2, 5, v1
s_mov_b32  s2, exec_lo
s_mov_b32  s3, exec_lo
s_nop      0
s_nop      0

_L2:
    // we still have readfirstlane here, the descriptor is loaded in
    // scalar registers. We can’t pick different descriptors
    // in parallel, but must pick them one by one
    v_readfirstlane_b32  s4, v2

    // check if we picked the right descriptor for the lane
    // if yes, load from the texture at the picked descriptor
    v_cmp_eq_u32_e32  vcc_lo, s4, v2
    s_and_saveexec_b32  s5, vcc_lo

    // if not right descriptor, skip imageLoad
    s_cbranch_execz  _L0

BBF0_0:
    s_load_dwordx8  s[8:15], s[0:1], s4
    s_waitcnt     vmcnt(0)  lgkmcnt(0)
    s_waitcnt_depctr  0xffe3
    image_load v[3:6], v[0:1], s[8:15] dmask:0xf dim:SQ_RSRC_IMG_2D
    s_andn2_b32   s3, s3, exec_lo

    // if we picked right descriptor for the lane,
    // jump to the imageStore part
    s_cbranch_scc0  _L1

_L0:
    // if it was the wrong descriptor, jump back to the beginning
    // and pick the descriptor of the first remaining active lane
    // loop goes on until no active lanes are remaining for the
    // imageLoad instruction
    v_nop
    s_mov_b32     exec_lo, s5
    s_and_b32     exec_lo, exec_lo, s3
    s_branch      _L2

_L1:
    v_nop
    s_mov_b32     exec_lo, s2
    v_add_nc_u32_e32  v2, 32, v2
    s_mov_b32  s2, exec_lo
    s_nop      0
    s_nop      0
    s_nop      0
    s_nop      0

_L5:
    // do again a ‘waterfall’ loop as before, but now for the descriptors
    // used for the imageStore instruction
    v_readfirstlane_b32  s3, v2
    v_cmp_eq_u32_e32  vcc_lo, s3, v2
    s_and_saveexec_b32  s4, vcc_lo
    s_cbranch_execz  _L3

BBF0_1:
    s_load_dwordx8  s[8:15], s[0:1], s3
    s_waitcnt     vmcnt(0)  lgkmcnt(0)
    s_waitcnt_depctr  0xffe3
    image_store   v[3:6], v[0:1], s[8:15] dmask:0xf dim:SQ_RSRC_IMG_2D unorm glc
    s_andn2_b32   s2, s2, exec_lo
    s_cbranch_scc0  _L4

_L3:
    v_nop
    s_mov_b32     exec_lo, s4
    s_and_b32     exec_lo, exec_lo, s2
    s_branch      _L5

_L4:
    s_endpgm

struct VERTEX
{
    [[vk::location(0)]] float2 vTexcoord : TEXCOORD;
    [[vk::location(1)]] uint inIndex : INDEX;
};

[[vk::binding(1)]] Texture2D imgDst[13] :register(t0);
[[vk::binding(1)]] SamplerState srcSampler :register(s0);

[[vk::location(0)]] float4 main(VERTEX input) : SV_Target
{
    return imgDst[NonUniformResourceIndex(input.inIndex)].Sample(srcSampler, input.vTexcoord);
}