From: Conor McCarthy cmccarthy@codeweavers.com
The FXC optimiser sometimes converts a local array of input values into direct array addressing of the inputs, which can result in a dcl_indexrange instruction spanning input elements with different masks. --- tests/d3d12.c | 251 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 251 insertions(+)
diff --git a/tests/d3d12.c b/tests/d3d12.c index 1126d9749..b84c58543 100644 --- a/tests/d3d12.c +++ b/tests/d3d12.c @@ -37495,6 +37495,256 @@ static void test_get_resource_tiling(void) destroy_test_context(&context); }
+static void test_hull_shader_punned_array(void) +{ + static const float white[] = {1.0f, 1.0f, 1.0f, 1.0f}; + D3D12_GRAPHICS_PIPELINE_STATE_DESC pso_desc; + ID3D12GraphicsCommandList *command_list; + struct test_context_desc desc; + struct test_context context; + ID3D12CommandQueue *queue; + struct vec4 tess_factors; + HRESULT hr; + + static const DWORD hs_code[] = + { +#if 0 + float4 tess_factor; + + struct data + { + float3 f0 : FOO0; + float4 f1 : FOO1; + float3 f2 : FOO2; + float4 position : SV_Position; + }; + + struct patch_constant_data + { + float edges[3] : SV_TessFactor; + float inside : SV_InsideTessFactor; + float4 f : FOO; + }; + + void patch_constant(InputPatch<data, 3> input, out patch_constant_data output) + { + output.edges[0] = tess_factor.x; + output.edges[1] = tess_factor.y; + output.edges[2] = tess_factor.z; + output.inside = tess_factor.w; + /* Compiles into punned array access to f0-f3 using dcl_indexrange. */ + float f[3] = {input[0].f0.x, input[0].f1.x, input[0].f2.x}; + output.f = f[tess_factor.x]; + } + + [domain("tri")] + [outputcontrolpoints(3)] + [partitioning("integer")] + [outputtopology("triangle_cw")] + [patchconstantfunc("patch_constant")] + data hs_main(InputPatch<data, 3> input, uint i : SV_OutputControlPointID) + { + data result = input[i]; + /* Read a value with more components than the first element in dcl_indexrange. Without + * special handling, this would fail because the dcl_indexrange instruction uses only + * the mask from element 0. */ + result.f2 = input[0].f1.yzw; + return result; + } + + [domain("tri")] + void ds_main(patch_constant_data input, + float3 tess_coord : SV_DomainLocation, + const OutputPatch<data, 3> patch, + out data output) + { + output.position = tess_coord.x * patch[0].position + + tess_coord.y * patch[1].position + + tess_coord.z * patch[2].position; + output.f0.x = tess_coord.x * patch[0].f0.x + tess_coord.y * patch[1].f0.x + tess_coord.z * patch[2].f0.x; + output.f0.y = tess_coord.x * patch[0].f0.y + tess_coord.y * patch[1].f0.y + tess_coord.z * patch[2].f0.y; + output.f0.z = tess_coord.x * patch[0].f0.z + tess_coord.y * patch[1].f0.z + tess_coord.z * patch[2].f0.z; + output.f1 = 0.0; + output.f2 = 0.0; + } + + void vs_main(uint id : SV_VertexID, out data output) + { + float2 coords = float2((id << 1) & 2, id & 2); + output.position = float4(coords * float2(2, -2) + float2(-1, 1), 0, 1); + output.f0 = float3(0.0, 1.0, 0.0); + output.f1 = float4(2.0, 3.0, 4.0, 5.0); + output.f2 = float3(6.0, 7.0, 8.0); + } + + float4 ps_main(data input) : sv_target + { + return float4(input.f0, 1.0); + } +#endif + 0x43425844, 0x6d775869, 0x25139e4c, 0x407bfb1e, 0xe239367e, 0x00000001, 0x00000660, 0x00000004, + 0x00000030, 0x000000b0, 0x00000130, 0x000001e0, 0x4e475349, 0x00000078, 0x00000004, 0x00000008, + 0x00000068, 0x00000000, 0x00000000, 0x00000003, 0x00000000, 0x00000707, 0x00000068, 0x00000001, + 0x00000000, 0x00000003, 0x00000001, 0x00000f0f, 0x00000068, 0x00000002, 0x00000000, 0x00000003, + 0x00000002, 0x00000107, 0x0000006c, 0x00000000, 0x00000001, 0x00000003, 0x00000003, 0x00000f0f, + 0x004f4f46, 0x505f5653, 0x7469736f, 0x006e6f69, 0x4e47534f, 0x00000078, 0x00000004, 0x00000008, + 0x00000068, 0x00000000, 0x00000000, 0x00000003, 0x00000000, 0x00000807, 0x00000068, 0x00000001, + 0x00000000, 0x00000003, 0x00000001, 0x0000000f, 0x00000068, 0x00000002, 0x00000000, 0x00000003, + 0x00000002, 0x00000807, 0x0000006c, 0x00000000, 0x00000001, 0x00000003, 0x00000003, 0x0000000f, + 0x004f4f46, 0x505f5653, 0x7469736f, 0x006e6f69, 0x47534350, 0x000000a8, 0x00000005, 0x00000008, + 0x00000080, 0x00000000, 0x0000000d, 0x00000003, 0x00000000, 0x00000e01, 0x00000080, 0x00000001, + 0x0000000d, 0x00000003, 0x00000001, 0x00000e01, 0x00000080, 0x00000002, 0x0000000d, 0x00000003, + 0x00000002, 0x00000e01, 0x0000008e, 0x00000000, 0x0000000e, 0x00000003, 0x00000003, 0x00000e01, + 0x000000a2, 0x00000000, 0x00000000, 0x00000003, 0x00000004, 0x0000000f, 0x545f5653, 0x46737365, + 0x6f746361, 0x56530072, 0x736e495f, 0x54656469, 0x46737365, 0x6f746361, 0x4f460072, 0xabab004f, + 0x58454853, 0x00000478, 0x00030050, 0x0000011e, 0x01000071, 0x01001893, 0x01001894, 0x01001095, + 0x01000896, 0x01001897, 0x0100086a, 0x04000059, 0x00208e46, 0x00000000, 0x00000001, 0x01000072, + 0x0200005f, 0x00016000, 0x0400005f, 0x00201072, 0x00000003, 0x00000000, 0x0400005f, 0x002010f2, + 0x00000003, 0x00000001, 0x0400005f, 0x002010f2, 0x00000003, 0x00000003, 0x03000065, 0x00102072, + 0x00000000, 0x03000065, 0x001020f2, 0x00000001, 0x03000065, 0x00102072, 0x00000002, 0x03000065, + 0x001020f2, 0x00000003, 0x02000068, 0x00000001, 0x04000036, 0x00100012, 0x00000000, 0x00016001, + 0x07000036, 0x00102072, 0x00000000, 0x00a01246, 0x0010000a, 0x00000000, 0x00000000, 0x07000036, + 0x001020f2, 0x00000001, 0x00a01e46, 0x0010000a, 0x00000000, 0x00000001, 0x07000036, 0x001020f2, + 0x00000003, 0x00a01e46, 0x0010000a, 0x00000000, 0x00000003, 0x06000036, 0x00102072, 0x00000002, + 0x00201796, 0x00000000, 0x00000001, 0x0100003e, 0x01000073, 0x04000067, 0x00102012, 0x00000000, + 0x00000011, 0x06000036, 0x00102012, 0x00000000, 0x0020800a, 0x00000000, 0x00000000, 0x0100003e, + 0x01000073, 0x04000067, 0x00102012, 0x00000001, 0x00000012, 0x06000036, 0x00102012, 0x00000001, + 0x0020801a, 0x00000000, 0x00000000, 0x0100003e, 0x01000073, 0x04000067, 0x00102012, 0x00000002, + 0x00000013, 0x06000036, 0x00102012, 0x00000002, 0x0020802a, 0x00000000, 0x00000000, 0x0100003e, + 0x01000073, 0x04000067, 0x00102012, 0x00000003, 0x00000014, 0x06000036, 0x00102012, 0x00000003, + 0x0020803a, 0x00000000, 0x00000000, 0x0100003e, 0x01000073, 0x0400005f, 0x00219012, 0x00000003, + 0x00000000, 0x0400005f, 0x00219012, 0x00000003, 0x00000001, 0x0400005f, 0x00219012, 0x00000003, + 0x00000002, 0x0400005f, 0x00219012, 0x00000003, 0x00000003, 0x03000065, 0x00102012, 0x00000004, + 0x02000068, 0x00000001, 0x0500005b, 0x00219012, 0x00000003, 0x00000000, 0x00000004, 0x0600001c, + 0x00100012, 0x00000000, 0x0020800a, 0x00000000, 0x00000000, 0x07000036, 0x00102012, 0x00000004, + 0x0421900a, 0x00000000, 0x0010000a, 0x00000000, 0x0100003e, 0x01000073, 0x0400005f, 0x00219012, + 0x00000003, 0x00000000, 0x0400005f, 0x00219012, 0x00000003, 0x00000001, 0x0400005f, 0x00219012, + 0x00000003, 0x00000002, 0x0400005f, 0x00219012, 0x00000003, 0x00000003, 0x03000065, 0x00102022, + 0x00000004, 0x02000068, 0x00000001, 0x0500005b, 0x00219012, 0x00000003, 0x00000000, 0x00000004, + 0x0600001c, 0x00100012, 0x00000000, 0x0020800a, 0x00000000, 0x00000000, 0x07000036, 0x00102022, + 0x00000004, 0x0421900a, 0x00000000, 0x0010000a, 0x00000000, 0x0100003e, 0x01000073, 0x0400005f, + 0x00219012, 0x00000003, 0x00000000, 0x0400005f, 0x00219012, 0x00000003, 0x00000001, 0x0400005f, + 0x00219012, 0x00000003, 0x00000002, 0x0400005f, 0x00219012, 0x00000003, 0x00000003, 0x03000065, + 0x00102042, 0x00000004, 0x02000068, 0x00000001, 0x0500005b, 0x00219012, 0x00000003, 0x00000000, + 0x00000004, 0x0600001c, 0x00100012, 0x00000000, 0x0020800a, 0x00000000, 0x00000000, 0x07000036, + 0x00102042, 0x00000004, 0x0421900a, 0x00000000, 0x0010000a, 0x00000000, 0x0100003e, 0x01000073, + 0x0400005f, 0x00219012, 0x00000003, 0x00000000, 0x0400005f, 0x00219012, 0x00000003, 0x00000001, + 0x0400005f, 0x00219012, 0x00000003, 0x00000002, 0x0400005f, 0x00219012, 0x00000003, 0x00000003, + 0x03000065, 0x00102082, 0x00000004, 0x02000068, 0x00000001, 0x0500005b, 0x00219012, 0x00000003, + 0x00000000, 0x00000004, 0x0600001c, 0x00100012, 0x00000000, 0x0020800a, 0x00000000, 0x00000000, + 0x07000036, 0x00102082, 0x00000004, 0x0421900a, 0x00000000, 0x0010000a, 0x00000000, 0x0100003e, + }; + static const D3D12_SHADER_BYTECODE hs = {hs_code, sizeof(hs_code)}; + static const DWORD ds_code[] = + { + 0x43425844, 0x9c50437f, 0xe21aebbd, 0x29bff97d, 0xa7808efa, 0x00000001, 0x0000036c, 0x00000004, + 0x00000030, 0x000000b0, 0x00000160, 0x000001e0, 0x4e475349, 0x00000078, 0x00000004, 0x00000008, + 0x00000068, 0x00000000, 0x00000000, 0x00000003, 0x00000000, 0x00000707, 0x00000068, 0x00000001, + 0x00000000, 0x00000003, 0x00000001, 0x0000000f, 0x00000068, 0x00000002, 0x00000000, 0x00000003, + 0x00000002, 0x00000007, 0x0000006c, 0x00000000, 0x00000001, 0x00000003, 0x00000003, 0x00000f0f, + 0x004f4f46, 0x505f5653, 0x7469736f, 0x006e6f69, 0x47534350, 0x000000a8, 0x00000005, 0x00000008, + 0x00000080, 0x00000000, 0x0000000d, 0x00000003, 0x00000000, 0x00000001, 0x00000080, 0x00000001, + 0x0000000d, 0x00000003, 0x00000001, 0x00000001, 0x00000080, 0x00000002, 0x0000000d, 0x00000003, + 0x00000002, 0x00000001, 0x0000008e, 0x00000000, 0x0000000e, 0x00000003, 0x00000003, 0x00000001, + 0x000000a2, 0x00000000, 0x00000000, 0x00000003, 0x00000004, 0x0000000f, 0x545f5653, 0x46737365, + 0x6f746361, 0x56530072, 0x736e495f, 0x54656469, 0x46737365, 0x6f746361, 0x4f460072, 0xabab004f, + 0x4e47534f, 0x00000078, 0x00000004, 0x00000008, 0x00000068, 0x00000000, 0x00000000, 0x00000003, + 0x00000000, 0x00000807, 0x00000068, 0x00000001, 0x00000000, 0x00000003, 0x00000001, 0x0000000f, + 0x00000068, 0x00000002, 0x00000000, 0x00000003, 0x00000002, 0x00000807, 0x0000006c, 0x00000000, + 0x00000001, 0x00000003, 0x00000003, 0x0000000f, 0x004f4f46, 0x505f5653, 0x7469736f, 0x006e6f69, + 0x58454853, 0x00000184, 0x00040050, 0x00000061, 0x01001893, 0x01001095, 0x0100086a, 0x0200005f, + 0x0001c072, 0x0400005f, 0x00219072, 0x00000003, 0x00000000, 0x0400005f, 0x002190f2, 0x00000003, + 0x00000003, 0x03000065, 0x00102072, 0x00000000, 0x03000065, 0x001020f2, 0x00000001, 0x03000065, + 0x00102072, 0x00000002, 0x04000067, 0x001020f2, 0x00000003, 0x00000001, 0x02000068, 0x00000001, + 0x07000038, 0x00100072, 0x00000000, 0x0001c556, 0x00219246, 0x00000001, 0x00000000, 0x09000032, + 0x00100072, 0x00000000, 0x0001c006, 0x00219246, 0x00000000, 0x00000000, 0x00100246, 0x00000000, + 0x09000032, 0x00102072, 0x00000000, 0x0001caa6, 0x00219246, 0x00000002, 0x00000000, 0x00100246, + 0x00000000, 0x08000036, 0x001020f2, 0x00000001, 0x00004002, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x08000036, 0x00102072, 0x00000002, 0x00004002, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x07000038, 0x001000f2, 0x00000000, 0x0001c556, 0x00219e46, 0x00000001, 0x00000003, + 0x09000032, 0x001000f2, 0x00000000, 0x0001c006, 0x00219e46, 0x00000000, 0x00000003, 0x00100e46, + 0x00000000, 0x09000032, 0x001020f2, 0x00000003, 0x0001caa6, 0x00219e46, 0x00000002, 0x00000003, + 0x00100e46, 0x00000000, 0x0100003e, + }; + static const D3D12_SHADER_BYTECODE ds = {ds_code, sizeof(ds_code)}; + static const DWORD vs_code[] = + { + 0x43425844, 0xa781de9a, 0xd9cd6837, 0xd70ee110, 0xba5ecac2, 0x00000001, 0x0000025c, 0x00000003, + 0x0000002c, 0x00000060, 0x000000e0, 0x4e475349, 0x0000002c, 0x00000001, 0x00000008, 0x00000020, + 0x00000000, 0x00000006, 0x00000001, 0x00000000, 0x00000101, 0x565f5653, 0x65747265, 0x00444978, + 0x4e47534f, 0x00000078, 0x00000004, 0x00000008, 0x00000068, 0x00000000, 0x00000000, 0x00000003, + 0x00000000, 0x00000807, 0x00000068, 0x00000001, 0x00000000, 0x00000003, 0x00000001, 0x0000000f, + 0x00000068, 0x00000002, 0x00000000, 0x00000003, 0x00000002, 0x00000807, 0x0000006c, 0x00000000, + 0x00000001, 0x00000003, 0x00000003, 0x0000000f, 0x004f4f46, 0x505f5653, 0x7469736f, 0x006e6f69, + 0x58454853, 0x00000174, 0x00010050, 0x0000005d, 0x0100086a, 0x04000060, 0x00101012, 0x00000000, + 0x00000006, 0x03000065, 0x00102072, 0x00000000, 0x03000065, 0x001020f2, 0x00000001, 0x03000065, + 0x00102072, 0x00000002, 0x04000067, 0x001020f2, 0x00000003, 0x00000001, 0x02000068, 0x00000001, + 0x08000036, 0x00102072, 0x00000000, 0x00004002, 0x00000000, 0x3f800000, 0x00000000, 0x00000000, + 0x08000036, 0x001020f2, 0x00000001, 0x00004002, 0x40000000, 0x40400000, 0x40800000, 0x40a00000, + 0x08000036, 0x00102072, 0x00000002, 0x00004002, 0x40c00000, 0x40e00000, 0x41000000, 0x00000000, + 0x0b00008c, 0x00100012, 0x00000000, 0x00004001, 0x00000001, 0x00004001, 0x00000001, 0x0010100a, + 0x00000000, 0x00004001, 0x00000000, 0x07000001, 0x00100042, 0x00000000, 0x0010100a, 0x00000000, + 0x00004001, 0x00000002, 0x05000056, 0x00100032, 0x00000000, 0x00100086, 0x00000000, 0x0f000032, + 0x00102032, 0x00000003, 0x00100046, 0x00000000, 0x00004002, 0x40000000, 0xc0000000, 0x00000000, + 0x00000000, 0x00004002, 0xbf800000, 0x3f800000, 0x00000000, 0x00000000, 0x08000036, 0x001020c2, + 0x00000003, 0x00004002, 0x00000000, 0x00000000, 0x00000000, 0x3f800000, 0x0100003e, + }; + static const D3D12_SHADER_BYTECODE vs = {vs_code, sizeof(vs_code)}; + static const DWORD ps_code[] = + { + 0x43425844, 0x586f8b9c, 0x6ca70cc8, 0x2aa24884, 0xae111d8c, 0x00000001, 0x00000138, 0x00000003, + 0x0000002c, 0x000000ac, 0x000000e0, 0x4e475349, 0x00000078, 0x00000004, 0x00000008, 0x00000068, + 0x00000000, 0x00000000, 0x00000003, 0x00000000, 0x00000707, 0x00000068, 0x00000001, 0x00000000, + 0x00000003, 0x00000001, 0x0000000f, 0x00000068, 0x00000002, 0x00000000, 0x00000003, 0x00000002, + 0x00000007, 0x0000006c, 0x00000000, 0x00000001, 0x00000003, 0x00000003, 0x0000000f, 0x004f4f46, + 0x505f5653, 0x7469736f, 0x006e6f69, 0x4e47534f, 0x0000002c, 0x00000001, 0x00000008, 0x00000020, + 0x00000000, 0x00000000, 0x00000003, 0x00000000, 0x0000000f, 0x745f7673, 0x65677261, 0xabab0074, + 0x58454853, 0x00000050, 0x00000050, 0x00000014, 0x0100086a, 0x03001062, 0x00101072, 0x00000000, + 0x03000065, 0x001020f2, 0x00000000, 0x05000036, 0x00102072, 0x00000000, 0x00101246, 0x00000000, + 0x05000036, 0x00102082, 0x00000000, 0x00004001, 0x3f800000, 0x0100003e, + }; + static const D3D12_SHADER_BYTECODE ps = {ps_code, sizeof(ps_code)}; + + memset(&desc, 0, sizeof(desc)); + desc.no_root_signature = true; + if (!init_test_context(&context, &desc)) + return; + command_list = context.list; + queue = context.queue; + + context.root_signature = create_32bit_constants_root_signature(context.device, + 0, 4, D3D12_SHADER_VISIBILITY_HULL); + + init_pipeline_state_desc(&pso_desc, context.root_signature, + context.render_target_desc.Format, &vs, &ps, NULL); + pso_desc.HS = hs; + pso_desc.DS = ds; + pso_desc.PrimitiveTopologyType = D3D12_PRIMITIVE_TOPOLOGY_TYPE_PATCH; + hr = ID3D12Device_CreateGraphicsPipelineState(context.device, &pso_desc, + &IID_ID3D12PipelineState, (void **)&context.pipeline_state); + ok(hr == S_OK, "Failed to create state, hr %#x.\n", hr); + + ID3D12GraphicsCommandList_ClearRenderTargetView(command_list, context.rtv, white, 0, NULL); + + ID3D12GraphicsCommandList_OMSetRenderTargets(command_list, 1, &context.rtv, false, NULL); + ID3D12GraphicsCommandList_SetGraphicsRootSignature(command_list, context.root_signature); + ID3D12GraphicsCommandList_SetPipelineState(command_list, context.pipeline_state); + ID3D12GraphicsCommandList_IASetPrimitiveTopology(command_list, D3D_PRIMITIVE_TOPOLOGY_3_CONTROL_POINT_PATCHLIST); + ID3D12GraphicsCommandList_RSSetViewports(command_list, 1, &context.viewport); + ID3D12GraphicsCommandList_RSSetScissorRects(command_list, 1, &context.scissor_rect); + tess_factors.x = tess_factors.y = tess_factors.z = tess_factors.w = 1.0f; + ID3D12GraphicsCommandList_SetGraphicsRoot32BitConstants(command_list, 0, 4, &tess_factors.x, 0); + ID3D12GraphicsCommandList_DrawInstanced(command_list, 3, 1, 0, 0); + + transition_resource_state(command_list, context.render_target, + D3D12_RESOURCE_STATE_RENDER_TARGET, D3D12_RESOURCE_STATE_COPY_SOURCE); + + todo + check_sub_resource_uint(context.render_target, 0, queue, command_list, 0xff00ff00, 0); + + destroy_test_context(&context); +} + START_TEST(d3d12) { parse_args(argc, argv); @@ -37676,4 +37926,5 @@ START_TEST(d3d12) run_test(test_readback_map_stability); run_test(test_vs_ps_relative_addressing); run_test(test_get_resource_tiling); + run_test(test_hull_shader_punned_array); }