Skip to content

VERY experimental Nintendo Switch 2 emulator

C++

[vulkan] Implementation for VK_EXT_shader_quad_control (#4168)

CamilleLaVey50cb8fd1c94e
diff --git a/src/shader_recompiler/backend/glasm/emit_glasm_instructions.h b/src/shader_recompiler/backend/glasm/emit_glasm_instructions.h
index 6572db86dc..6f522ab5c2 100644
--- a/src/shader_recompiler/backend/glasm/emit_glasm_instructions.h
+++ b/src/shader_recompiler/backend/glasm/emit_glasm_instructions.h
@@ -1,4 +1,4 @@
-// SPDX-FileCopyrightText: Copyright 2025 Eden Emulator Project
+// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
// SPDX-License-Identifier: GPL-3.0-or-later
// SPDX-FileCopyrightText: Copyright 2021 yuzu Emulator Project
@@ -665,6 +665,8 @@ void EmitShuffleDown(EmitContext& ctx, IR::Inst& inst, ScalarU32 value, ScalarU3
const IR::Value& clamp, const IR::Value& segmentation_mask);
void EmitShuffleButterfly(EmitContext& ctx, IR::Inst& inst, ScalarU32 value, ScalarU32 index,
const IR::Value& clamp, const IR::Value& segmentation_mask);
+void EmitQuadBroadcast(EmitContext& ctx, IR::Inst& inst, ScalarU32 value, ScalarU32 lane);
+void EmitQuadSwap(EmitContext& ctx, IR::Inst& inst, ScalarU32 value, ScalarU32 direction);
void EmitFSwizzleAdd(EmitContext& ctx, IR::Inst& inst, ScalarF32 op_a, ScalarF32 op_b,
ScalarU32 swizzle);
void EmitDPdxFine(EmitContext& ctx, IR::Inst& inst, ScalarF32 op_a);
diff --git a/src/shader_recompiler/backend/glasm/emit_glasm_warp.cpp b/src/shader_recompiler/backend/glasm/emit_glasm_warp.cpp
index fb6a597d4e..7c07ec3247 100644
--- a/src/shader_recompiler/backend/glasm/emit_glasm_warp.cpp
+++ b/src/shader_recompiler/backend/glasm/emit_glasm_warp.cpp
@@ -1,3 +1,6 @@
+// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-License-Identifier: GPL-3.0-or-later
+
// SPDX-FileCopyrightText: Copyright 2021 yuzu Emulator Project
// SPDX-License-Identifier: GPL-2.0-or-later
@@ -97,6 +100,24 @@ void EmitShuffleButterfly(EmitContext& ctx, IR::Inst& inst, ScalarU32 value, Sca
Shuffle(ctx, inst, value, index, clamp, segmentation_mask, "XOR");
}
+void EmitQuadBroadcast(EmitContext& ctx, IR::Inst& inst, ScalarU32 value, ScalarU32 lane) {
+ const Register ret{ctx.reg_alloc.Define(inst)};
+ ctx.Add("AND.U RC.x,{}.threadid,~3;"
+ "AND.U RC.y,{},3;"
+ "OR.U RC.x,RC.x,RC.y;"
+ "SHFIDX.U {},{},RC.x,0x1C03;"
+ "MOV.U {}.x,{}.y;",
+ ctx.stage_name, lane, ret, value, ret, ret);
+}
+
+void EmitQuadSwap(EmitContext& ctx, IR::Inst& inst, ScalarU32 value, ScalarU32 direction) {
+ const Register ret{ctx.reg_alloc.Define(inst)};
+ ctx.Add("ADD.U RC.x,{},1;"
+ "SHFXOR.U {},{},RC.x,0x1C03;"
+ "MOV.U {}.x,{}.y;",
+ direction, ret, value, ret, ret);
+}
+
void EmitFSwizzleAdd(EmitContext& ctx, IR::Inst& inst, ScalarF32 op_a, ScalarF32 op_b,
ScalarU32 swizzle) {
const auto ret{ctx.reg_alloc.Define(inst)};
diff --git a/src/shader_recompiler/backend/glsl/emit_glsl_instructions.h b/src/shader_recompiler/backend/glsl/emit_glsl_instructions.h
index d508b84cec..96aac502d5 100644
--- a/src/shader_recompiler/backend/glsl/emit_glsl_instructions.h
+++ b/src/shader_recompiler/backend/glsl/emit_glsl_instructions.h
@@ -1,4 +1,4 @@
-// SPDX-FileCopyrightText: Copyright 2025 Eden Emulator Project
+// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
// SPDX-License-Identifier: GPL-3.0-or-later
// SPDX-FileCopyrightText: Copyright 2021 yuzu Emulator Project
@@ -743,6 +743,10 @@ void EmitShuffleDown(EmitContext& ctx, IR::Inst& inst, std::string_view value,
void EmitShuffleButterfly(EmitContext& ctx, IR::Inst& inst, std::string_view value,
std::string_view index, std::string_view clamp,
std::string_view segmentation_mask);
+void EmitQuadBroadcast(EmitContext& ctx, IR::Inst& inst, std::string_view value,
+ std::string_view lane);
+void EmitQuadSwap(EmitContext& ctx, IR::Inst& inst, std::string_view value,
+ std::string_view direction);
void EmitFSwizzleAdd(EmitContext& ctx, IR::Inst& inst, std::string_view op_a, std::string_view op_b,
std::string_view swizzle);
void EmitDPdxFine(EmitContext& ctx, IR::Inst& inst, std::string_view op_a);
diff --git a/src/shader_recompiler/backend/glsl/emit_glsl_warp.cpp b/src/shader_recompiler/backend/glsl/emit_glsl_warp.cpp
index f9be5de1c0..b2f65550fb 100644
--- a/src/shader_recompiler/backend/glsl/emit_glsl_warp.cpp
+++ b/src/shader_recompiler/backend/glsl/emit_glsl_warp.cpp
@@ -1,3 +1,6 @@
+// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-License-Identifier: GPL-3.0-or-later
+
// SPDX-FileCopyrightText: Copyright 2021 yuzu Emulator Project
// SPDX-License-Identifier: GPL-2.0-or-later
@@ -200,6 +203,18 @@ void EmitShuffleButterfly(EmitContext& ctx, IR::Inst& inst, std::string_view val
ctx.AddU32("{}=shfl_in_bounds?shfl_result:{};", inst, value);
}
+void EmitQuadBroadcast(EmitContext& ctx, IR::Inst& inst, std::string_view value,
+ std::string_view lane) {
+ const auto src_thread_id{fmt::format("(({}&~3)|({}& 3))", THREAD_ID, lane)};
+ ctx.AddU32("{}=readInvocationARB({},{});", inst, value, src_thread_id);
+}
+
+void EmitQuadSwap(EmitContext& ctx, IR::Inst& inst, std::string_view value,
+ std::string_view direction) {
+ const auto src_thread_id{fmt::format("({}^({}+1))", THREAD_ID, direction)};
+ ctx.AddU32("{}=readInvocationARB({},{});", inst, value, src_thread_id);
+}
+
void EmitFSwizzleAdd(EmitContext& ctx, IR::Inst& inst, std::string_view op_a, std::string_view op_b,
std::string_view swizzle) {
const auto mask{fmt::format("({}>>((gl_SubGroupInvocationARB&3)<<1))&3", swizzle)};
diff --git a/src/shader_recompiler/backend/spirv/emit_spirv.cpp b/src/shader_recompiler/backend/spirv/emit_spirv.cpp
index 67329eea0d..c221888c09 100644
--- a/src/shader_recompiler/backend/spirv/emit_spirv.cpp
+++ b/src/shader_recompiler/backend/spirv/emit_spirv.cpp
@@ -322,6 +322,11 @@ void DefineEntryPoint(const IR::Program& program, EmitContext& ctx, Id main) {
if (ctx.runtime_info.force_early_z) {
ctx.AddExecutionMode(main, spv::ExecutionMode::EarlyFragmentTests);
}
+ if (ctx.profile.support_shader_quad_control && program.info.uses_quad_shuffles) {
+ ctx.AddExtension("SPV_KHR_quad_control");
+ ctx.AddCapability(spv::Capability::QuadControlKHR);
+ ctx.AddExecutionMode(main, spv::ExecutionMode::RequireFullQuadsKHR);
+ }
break;
default:
throw NotImplementedException("Stage {}", program.stage);
@@ -443,6 +448,12 @@ void SetupCapabilities(const Profile& profile, const Info& info, EmitContext& ct
ctx.AddCapability(spv::Capability::GroupNonUniformVote);
}
}
+ if (info.uses_quad_shuffles) {
+ if (profile.support_quad_shuffles) {
+ ctx.AddCapability(spv::Capability::GroupNonUniformQuad);
+ }
+ ctx.AddCapability(spv::Capability::GroupNonUniformShuffle);
+ }
if (info.uses_int64_bit_atomics && profile.support_int64_atomics) {
ctx.AddCapability(spv::Capability::Int64Atomics);
}
diff --git a/src/shader_recompiler/backend/spirv/emit_spirv_instructions.h b/src/shader_recompiler/backend/spirv/emit_spirv_instructions.h
index 171977c85c..165ec3fe84 100644
--- a/src/shader_recompiler/backend/spirv/emit_spirv_instructions.h
+++ b/src/shader_recompiler/backend/spirv/emit_spirv_instructions.h
@@ -1,4 +1,4 @@
-// SPDX-FileCopyrightText: Copyright 2025 Eden Emulator Project
+// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
// SPDX-License-Identifier: GPL-3.0-or-later
// SPDX-FileCopyrightText: Copyright 2021 yuzu Emulator Project
@@ -622,6 +622,8 @@ Id EmitShuffleDown(EmitContext& ctx, IR::Inst* inst, Id value, Id index, Id clam
Id segmentation_mask);
Id EmitShuffleButterfly(EmitContext& ctx, IR::Inst* inst, Id value, Id index, Id clamp,
Id segmentation_mask);
+Id EmitQuadBroadcast(EmitContext& ctx, Id value, Id lane);
+Id EmitQuadSwap(EmitContext& ctx, Id value, Id direction);
Id EmitFSwizzleAdd(EmitContext& ctx, Id op_a, Id op_b, Id swizzle);
Id EmitDPdxFine(EmitContext& ctx, Id op_a);
Id EmitDPdyFine(EmitContext& ctx, Id op_a);
diff --git a/src/shader_recompiler/backend/spirv/emit_spirv_warp.cpp b/src/shader_recompiler/backend/spirv/emit_spirv_warp.cpp
index 242426ec08..ffd5d9c29f 100644
--- a/src/shader_recompiler/backend/spirv/emit_spirv_warp.cpp
+++ b/src/shader_recompiler/backend/spirv/emit_spirv_warp.cpp
@@ -260,6 +260,21 @@ Id EmitShuffleButterfly(EmitContext& ctx, IR::Inst* inst, Id value, Id index, Id
return SelectValue(ctx, in_range, value, src_thread_id);
}
+Id EmitQuadBroadcast(EmitContext& ctx, Id value, Id lane) {
+ if (ctx.profile.support_quad_shuffles) {
+ return ctx.OpGroupNonUniformQuadBroadcast(ctx.U32[1], SubgroupScope(ctx), value, lane);
+ }
+ const Id base{ctx.OpBitwiseAnd(ctx.U32[1], GetThreadId(ctx), ctx.Const(~3u))};
+ const Id local_lane{ctx.OpBitwiseAnd(ctx.U32[1], lane, ctx.Const(3u))};
+ const Id src_thread_id{ctx.OpBitwiseOr(ctx.U32[1], base, local_lane)};
+ return ctx.OpGroupNonUniformShuffle(ctx.U32[1], SubgroupScope(ctx), value, src_thread_id);
+}
+
+Id EmitQuadSwap(EmitContext& ctx, Id value, Id direction) {
+ const Id xor_mask{ctx.OpIAdd(ctx.U32[1], direction, ctx.Const(1u))};
+ return ctx.OpGroupNonUniformShuffleXor(ctx.U32[1], SubgroupScope(ctx), value, xor_mask);
+}
+
Id EmitFSwizzleAdd(EmitContext& ctx, Id op_a, Id op_b, Id swizzle) {
const Id three{ctx.Const(3U)};
Id mask{GetThreadId(ctx)};
diff --git a/src/shader_recompiler/frontend/ir/ir_emitter.cpp b/src/shader_recompiler/frontend/ir/ir_emitter.cpp
index 171161ffd1..95815d7d51 100644
--- a/src/shader_recompiler/frontend/ir/ir_emitter.cpp
+++ b/src/shader_recompiler/frontend/ir/ir_emitter.cpp
@@ -1,4 +1,4 @@
-// SPDX-FileCopyrightText: Copyright 2025 Eden Emulator Project
+// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
// SPDX-License-Identifier: GPL-3.0-or-later
// SPDX-FileCopyrightText: Copyright 2021 yuzu Emulator Project
@@ -2100,6 +2100,14 @@ U32 IREmitter::ShuffleButterfly(const IR::U32& value, const IR::U32& index, cons
return Inst<U32>(Opcode::ShuffleButterfly, value, index, clamp, seg_mask);
}
+U32 IREmitter::QuadBroadcast(const IR::U32& value, const IR::U32& lane) {
+ return Inst<U32>(Opcode::QuadBroadcast, value, lane);
+}
+
+U32 IREmitter::QuadSwap(const IR::U32& value, const IR::U32& direction) {
+ return Inst<U32>(Opcode::QuadSwap, value, direction);
+}
+
F32 IREmitter::FSwizzleAdd(const F32& a, const F32& b, const U32& swizzle, FpControl control) {
return Inst<F32>(Opcode::FSwizzleAdd, Flags{control}, a, b, swizzle);
}
diff --git a/src/shader_recompiler/frontend/ir/ir_emitter.h b/src/shader_recompiler/frontend/ir/ir_emitter.h
index 725eac3951..f22f0f75e2 100644
--- a/src/shader_recompiler/frontend/ir/ir_emitter.h
+++ b/src/shader_recompiler/frontend/ir/ir_emitter.h
@@ -1,4 +1,4 @@
-// SPDX-FileCopyrightText: Copyright 2025 Eden Emulator Project
+// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
// SPDX-License-Identifier: GPL-3.0-or-later
// SPDX-FileCopyrightText: Copyright 2021 yuzu Emulator Project
@@ -394,6 +394,8 @@ public:
const IR::U32& seg_mask);
[[nodiscard]] U32 ShuffleButterfly(const IR::U32& value, const IR::U32& index,
const IR::U32& clamp, const IR::U32& seg_mask);
+ [[nodiscard]] U32 QuadBroadcast(const IR::U32& value, const IR::U32& lane);
+ [[nodiscard]] U32 QuadSwap(const IR::U32& value, const IR::U32& direction);
[[nodiscard]] F32 FSwizzleAdd(const F32& a, const F32& b, const U32& swizzle,
FpControl control = {});
diff --git a/src/shader_recompiler/frontend/ir/opcodes.cpp b/src/shader_recompiler/frontend/ir/opcodes.cpp
index 7fb6694a9b..94ba0f6ae0 100644
--- a/src/shader_recompiler/frontend/ir/opcodes.cpp
+++ b/src/shader_recompiler/frontend/ir/opcodes.cpp
@@ -10,7 +10,7 @@ namespace Shader::IR {
namespace Detail {
-OpcodeMeta META_TABLE[532] = {
+OpcodeMeta META_TABLE[534] = {
#define OPCODE(name_token, type_token, ...) \
{ \
.name{#name_token}, \
@@ -21,7 +21,7 @@ OpcodeMeta META_TABLE[532] = {
#undef OPCODE
};
-u8 NUM_ARGS[532] = {
+u8 NUM_ARGS[534] = {
#define OPCODE(name_token, type_token, ...) u8(CalculateNumArgsOf(Opcode::name_token)),
#include "opcodes.inc"
#undef OPCODE
diff --git a/src/shader_recompiler/frontend/ir/opcodes.h b/src/shader_recompiler/frontend/ir/opcodes.h
index 5549edc9d7..50f9d7b155 100644
--- a/src/shader_recompiler/frontend/ir/opcodes.h
+++ b/src/shader_recompiler/frontend/ir/opcodes.h
@@ -57,12 +57,12 @@ static constexpr Type F64x2{Type::F64x2};
static constexpr Type F64x3{Type::F64x3};
static constexpr Type F64x4{Type::F64x4};
-extern OpcodeMeta META_TABLE[532];
+extern OpcodeMeta META_TABLE[534];
constexpr size_t CalculateNumArgsOf(Opcode op) noexcept {
const auto& arg_types = META_TABLE[size_t(op)].arg_types;
return size_t(std::distance(arg_types.begin(), std::ranges::find(arg_types, Type::Void)));
}
-extern u8 NUM_ARGS[532];
+extern u8 NUM_ARGS[534];
} // namespace Detail
/// Get return type of an opcode
diff --git a/src/shader_recompiler/frontend/ir/opcodes.inc b/src/shader_recompiler/frontend/ir/opcodes.inc
index 960009d89e..fee0afaf33 100644
--- a/src/shader_recompiler/frontend/ir/opcodes.inc
+++ b/src/shader_recompiler/frontend/ir/opcodes.inc
@@ -1,3 +1,6 @@
+// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-License-Identifier: GPL-3.0-or-later
+
// SPDX-FileCopyrightText: Copyright 2021 yuzu Emulator Project
// SPDX-License-Identifier: GPL-2.0-or-later
@@ -579,6 +582,8 @@ OPCODE(ShuffleIndex, U32, U32,
OPCODE(ShuffleUp, U32, U32, U32, U32, U32, )
OPCODE(ShuffleDown, U32, U32, U32, U32, U32, )
OPCODE(ShuffleButterfly, U32, U32, U32, U32, U32, )
+OPCODE(QuadBroadcast, U32, U32, U32, )
+OPCODE(QuadSwap, U32, U32, U32, )
OPCODE(FSwizzleAdd, F32, F32, F32, U32, )
OPCODE(DPdxFine, F32, F32, )
OPCODE(DPdyFine, F32, F32, )
diff --git a/src/shader_recompiler/frontend/maxwell/translate/impl/warp_shuffle.cpp b/src/shader_recompiler/frontend/maxwell/translate/impl/warp_shuffle.cpp
index 972eec8276..2a19237ab2 100644
--- a/src/shader_recompiler/frontend/maxwell/translate/impl/warp_shuffle.cpp
+++ b/src/shader_recompiler/frontend/maxwell/translate/impl/warp_shuffle.cpp
@@ -1,4 +1,4 @@
-// SPDX-FileCopyrightText: Copyright 2025 Eden Emulator Project
+// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
// SPDX-License-Identifier: GPL-3.0-or-later
// SPDX-FileCopyrightText: Copyright 2021 yuzu Emulator Project
@@ -36,7 +36,10 @@ enum class ShuffleMode : u64 {
}
}
-void Shuffle(TranslatorVisitor& v, u64 insn, const IR::U32& index, const IR::U32& mask) {
+constexpr u32 QUAD_MASK = (28u << 8) | 3u;
+
+void Shuffle(TranslatorVisitor& v, u64 insn, const IR::U32& index, const IR::U32& mask,
+ bool index_is_imm, u32 index_imm, bool mask_is_imm, u32 mask_imm) {
union {
u64 insn;
BitField<0, 8, IR::Reg> dest_reg;
@@ -45,6 +48,21 @@ void Shuffle(TranslatorVisitor& v, u64 insn, const IR::U32& index, const IR::U32
BitField<48, 3, IR::Pred> pred;
} const shfl{insn};
+ const bool is_quad_candidate{mask_is_imm && mask_imm == QUAD_MASK && index_is_imm &&
+ v.env.ShaderStage() == Stage::Fragment};
+ if (is_quad_candidate) {
+ if (shfl.mode == ShuffleMode::IDX && index_imm <= 3) {
+ v.X(shfl.dest_reg, v.ir.QuadBroadcast(v.X(shfl.src_reg), v.ir.Imm32(index_imm)));
+ v.ir.SetPred(shfl.pred, v.ir.Imm1(true));
+ return;
+ }
+ if (shfl.mode == ShuffleMode::BFLY && index_imm >= 1 && index_imm <= 3) {
+ v.X(shfl.dest_reg, v.ir.QuadSwap(v.X(shfl.src_reg), v.ir.Imm32(index_imm - 1)));
+ v.ir.SetPred(shfl.pred, v.ir.Imm1(true));
+ return;
+ }
+ }
+
const IR::U32 result{ShuffleOperation(v.ir, v.X(shfl.src_reg), index, mask, shfl.mode)};
v.ir.SetPred(shfl.pred, v.ir.GetInBoundsFromOp(result));
v.X(shfl.dest_reg, result);
@@ -59,11 +77,14 @@ void TranslatorVisitor::SHFL(u64 insn) {
BitField<29, 1, u64> src_b_flag;
BitField<34, 13, u64> src_b_imm;
} const flags{insn};
- const IR::U32 src_a{flags.src_a_flag != 0 ? ir.Imm32(static_cast<u32>(flags.src_a_imm))
- : GetReg20(insn)};
- const IR::U32 src_b{flags.src_b_flag != 0 ? ir.Imm32(static_cast<u32>(flags.src_b_imm))
- : GetReg39(insn)};
- Shuffle(*this, insn, src_a, src_b);
+ const bool index_is_imm{flags.src_a_flag != 0};
+ const bool mask_is_imm{flags.src_b_flag != 0};
+ const IR::U32 src_a{index_is_imm ? ir.Imm32(static_cast<u32>(flags.src_a_imm))
+ : GetReg20(insn)};
+ const IR::U32 src_b{mask_is_imm ? ir.Imm32(static_cast<u32>(flags.src_b_imm))
+ : GetReg39(insn)};
+ Shuffle(*this, insn, src_a, src_b, index_is_imm, static_cast<u32>(flags.src_a_imm),
+ mask_is_imm, static_cast<u32>(flags.src_b_imm));
}
} // namespace Shader::Maxwell
diff --git a/src/shader_recompiler/ir_opt/collect_shader_info_pass.cpp b/src/shader_recompiler/ir_opt/collect_shader_info_pass.cpp
index 5089f3a101..9010c2bf68 100644
--- a/src/shader_recompiler/ir_opt/collect_shader_info_pass.cpp
+++ b/src/shader_recompiler/ir_opt/collect_shader_info_pass.cpp
@@ -498,6 +498,10 @@ void VisitUsages(Info& info, IR::Inst& inst) {
case IR::Opcode::ShuffleButterfly:
info.uses_subgroup_shuffles = true;
break;
+ case IR::Opcode::QuadBroadcast:
+ case IR::Opcode::QuadSwap:
+ info.uses_quad_shuffles = true;
+ break;
case IR::Opcode::GetCbufU8:
case IR::Opcode::GetCbufS8:
case IR::Opcode::GetCbufU16:
diff --git a/src/shader_recompiler/profile.h b/src/shader_recompiler/profile.h
index eb78683b75..d2ac480ab8 100644
--- a/src/shader_recompiler/profile.h
+++ b/src/shader_recompiler/profile.h
@@ -37,6 +37,8 @@ struct Profile {
bool support_explicit_workgroup_layout{};
bool support_workgroup_layout_8bit_access{};
bool support_workgroup_layout_16bit_access{};
+ bool support_shader_quad_control{};
+ bool support_quad_shuffles{};
bool support_vote{};
u32 supported_subgroup_stages{0x7F};
bool support_viewport_index_layer_non_geometry{};
diff --git a/src/shader_recompiler/shader_info.h b/src/shader_recompiler/shader_info.h
index 0c11a0d72a..71309e040e 100644
--- a/src/shader_recompiler/shader_info.h
+++ b/src/shader_recompiler/shader_info.h
@@ -252,6 +252,7 @@ struct Info {
bool uses_is_helper_invocation{};
bool uses_subgroup_invocation_id{};
bool uses_subgroup_shuffles{};
+ bool uses_quad_shuffles{};
std::array<bool, 30> uses_patches{};
std::array<Interpolation, 32> interpolation{};
diff --git a/src/video_core/renderer_vulkan/vk_pipeline_cache.cpp b/src/video_core/renderer_vulkan/vk_pipeline_cache.cpp
index 41c3877c14..130b5e4cc2 100644
--- a/src/video_core/renderer_vulkan/vk_pipeline_cache.cpp
+++ b/src/video_core/renderer_vulkan/vk_pipeline_cache.cpp
@@ -404,6 +404,8 @@ PipelineCache::PipelineCache(Tegra::MaxwellDeviceMemoryManager& device_memory_,
device.IsWorkgroupMemoryExplicitLayout8BitAccessSupported(),
.support_workgroup_layout_16bit_access =
device.IsWorkgroupMemoryExplicitLayout16BitAccessSupported(),
+ .support_shader_quad_control = device.IsKhrShaderQuadControlSupported(),
+ .support_quad_shuffles = device.IsSubgroupFeatureSupported(VK_SUBGROUP_FEATURE_QUAD_BIT),
.support_vote = device.IsSubgroupFeatureSupported(VK_SUBGROUP_FEATURE_VOTE_BIT),
.supported_subgroup_stages = supported_subgroup_stages,
.support_viewport_index_layer_non_geometry =
diff --git a/src/video_core/vulkan_common/vulkan_device.cpp b/src/video_core/vulkan_common/vulkan_device.cpp
index 1e46ca951c..9c0bc56a8b 100644
--- a/src/video_core/vulkan_common/vulkan_device.cpp
+++ b/src/video_core/vulkan_common/vulkan_device.cpp
@@ -1386,6 +1386,11 @@ void Device::RemoveUnsuitableExtensions() {
VK_KHR_PIPELINE_EXECUTABLE_PROPERTIES_EXTENSION_NAME);
}
+ // VK_KHR_shader_quad_control
+ extensions.shader_quad_control = features.shader_quad_control.shaderQuadControl;
+ RemoveExtensionFeatureIfUnsuitable(extensions.shader_quad_control, features.shader_quad_control,
+ VK_KHR_SHADER_QUAD_CONTROL_EXTENSION_NAME);
+
// VK_KHR_workgroup_memory_explicit_layout
extensions.workgroup_memory_explicit_layout =
features.workgroup_memory_explicit_layout.workgroupMemoryExplicitLayout &&
diff --git a/src/video_core/vulkan_common/vulkan_device.h b/src/video_core/vulkan_common/vulkan_device.h
index a33ff5cb26..27e6636bdd 100644
--- a/src/video_core/vulkan_common/vulkan_device.h
+++ b/src/video_core/vulkan_common/vulkan_device.h
@@ -75,6 +75,7 @@ VK_DEFINE_HANDLE(VmaAllocator)
FEATURE(KHR, Maintenance6, MAINTENANCE_6, maintenance6) \
FEATURE(KHR, PipelineExecutableProperties, PIPELINE_EXECUTABLE_PROPERTIES, \
pipeline_executable_properties) \
+ FEATURE(KHR, ShaderQuadControl, SHADER_QUAD_CONTROL, shader_quad_control) \
FEATURE(KHR, WorkgroupMemoryExplicitLayout, WORKGROUP_MEMORY_EXPLICIT_LAYOUT, \
workgroup_memory_explicit_layout)
@@ -586,6 +587,11 @@ FN_MAX_LIMIT_LIST
features.features.shaderInt16;
}
+ /// Returns true if the device supports VK_KHR_shader_quad_control.
+ bool IsKhrShaderQuadControlSupported() const {
+ return extensions.shader_quad_control && features.shader_quad_control.shaderQuadControl;
+ }
+
/// Returns true if the device supports VK_KHR_image_format_list.
bool IsKhrImageFormatListSupported() const {
return extensions.image_format_list || instance_version >= VK_API_VERSION_1_2;