Device-wide chained scan with lookback

include/nbl/builtin/hlsl/concepts/accessors/device_arithmetic.hlsl

@@ -0,0 +1,65 @@
+#ifndef _NBL_BUILTIN_HLSL_CONCEPTS_ACCESSORS_DEVICE_ARITHMETIC_INCLUDED_
+#define _NBL_BUILTIN_HLSL_CONCEPTS_ACCESSORS_DEVICE_ARITHMETIC_INCLUDED_
+
+#include "nbl/builtin/hlsl/concepts/accessors/generic_shared_data.hlsl"
+
+namespace nbl
+{
+namespace hlsl
+{
+namespace scan
+{
+
+template<typename T, typename V, typename I=uint32_t>
+NBL_BOOL_CONCEPT ArithmeticSharedMemoryAccessor = concepts::accessors::GenericSharedMemoryAccessor<T,V,I>;
+
+template<typename T, typename V, typename I=uint32_t>
+NBL_BOOL_CONCEPT ArithmeticReadOnlyDataAccessor = concepts::accessors::GenericReadAccessor<T,V,I>;
+
+template<typename T, typename V, typename I=uint32_t>
+NBL_BOOL_CONCEPT ArithmeticDataAccessor = concepts::accessors::GenericDataAccessor<T,V,I>;
+
+#define NBL_CONCEPT_NAME DeviceReductionsAccessor
+#define NBL_CONCEPT_TPLT_PRM_KINDS (typename)(typename)
+#define NBL_CONCEPT_TPLT_PRM_NAMES (T)(V)
+#define NBL_CONCEPT_PARAM_0 (accessor, T)
+#define NBL_CONCEPT_PARAM_1 (val, V)
+#define NBL_CONCEPT_PARAM_2 (index, uint64_t)
+NBL_CONCEPT_BEGIN(3)
+#define accessor NBL_CONCEPT_PARAM_T NBL_CONCEPT_PARAM_0
+#define val NBL_CONCEPT_PARAM_T NBL_CONCEPT_PARAM_1
+#define index NBL_CONCEPT_PARAM_T NBL_CONCEPT_PARAM_2
+NBL_CONCEPT_END(
+    ((NBL_CONCEPT_REQ_TYPE_ALIAS_CONCEPT)(concepts::accessors::GenericDataAccessor, T, V, uint64_t))
+    ((NBL_CONCEPT_REQ_EXPR_RET_TYPE)((accessor.atomicMax(index, val)), is_same_v, V))
+    ((NBL_CONCEPT_REQ_EXPR_RET_TYPE)((accessor.atomicExchange(index, val)), is_same_v, V))
+);
+#undef val
+#undef index
+#undef accessor
+#include <nbl/builtin/hlsl/concepts/__end.hlsl>
+
+// TODO: as counter, maybe just increment 1 always?
+#define NBL_CONCEPT_NAME WorkgroupCounterAccessor
+#define NBL_CONCEPT_TPLT_PRM_KINDS (typename)
+#define NBL_CONCEPT_TPLT_PRM_NAMES (T)
+#define NBL_CONCEPT_PARAM_0 (accessor, T)
+#define NBL_CONCEPT_PARAM_1 (val, uint32_t)
+#define NBL_CONCEPT_PARAM_2 (index, uint64_t)
+NBL_CONCEPT_BEGIN(3)
+#define accessor NBL_CONCEPT_PARAM_T NBL_CONCEPT_PARAM_0
+#define val NBL_CONCEPT_PARAM_T NBL_CONCEPT_PARAM_1
+#define index NBL_CONCEPT_PARAM_T NBL_CONCEPT_PARAM_2
+NBL_CONCEPT_END(
+    ((NBL_CONCEPT_REQ_EXPR_RET_TYPE)((accessor.atomicAdd(index, val)), is_same_v, uint32_t))
+);
+#undef val
+#undef index
+#undef accessor
+#include <nbl/builtin/hlsl/concepts/__end.hlsl>
+
+}
+}
+}
+
+#endif

include/nbl/builtin/hlsl/glsl_compat/core.hlsl

@@ -116,16 +116,6 @@ enable_if_t<spirv::is_pointer_v<Ptr_T>, T> atomicXor(Ptr_T ptr, T value)
 {
     return spirv::atomicXor<T, Ptr_T>(ptr, spv::ScopeDevice, spv::MemorySemanticsMaskNone, value);
 }
-/* TODO: @Hazardu struct dispatchers like for `bitfieldExtract`
-template<typename T>
-T atomicMin(NBL_REF_ARG(T) ptr, T value)
-{
-}
-template<typename T>
-T atomicMax(NBL_REF_ARG(T) ptr, T value)
-{
-}
-*/
 template<typename T>
 T atomicExchange(NBL_REF_ARG(T) ptr, T value)
 {
@@ -147,6 +137,100 @@ enable_if_t<spirv::is_pointer_v<Ptr_T>, T> atomicCompSwap(Ptr_T ptr, T comparato
     return spirv::atomicCompareExchange<T, Ptr_T>(ptr, spv::ScopeDevice, spv::MemorySemanticsMaskNone, spv::MemorySemanticsMaskNone, value, comparator);
 }
 
+namespace impl
+{
+template<typename T NBL_STRUCT_CONSTRAINABLE>
+struct atomicMin;
+
+template<typename T>
+NBL_PARTIAL_REQ_TOP(concepts::SignedIntegral<T>)
+struct atomicMin<T NBL_PARTIAL_REQ_BOT(concepts::SignedIntegral<T>) >
+{
+    static T __call(NBL_REF_ARG(T) ptr, T value)
+    {
+        return spirv::atomicSMin<T>(ptr, spv::ScopeDevice, spv::MemorySemanticsMaskNone, value);
+    }
+
+    template<typename Ptr_T> // DXC Workaround
+    static T __call(Ptr_T ptr, T value)
+    {
+        return spirv::atomicSMin<T>(ptr, spv::ScopeDevice, spv::MemorySemanticsMaskNone, value);
+    }
+};
+
+template<typename T>
+NBL_PARTIAL_REQ_TOP(concepts::UnsignedIntegral<T>)
+struct atomicMin<T NBL_PARTIAL_REQ_BOT(concepts::UnsignedIntegral<T>) >
+{
+    static T __call(NBL_REF_ARG(T) ptr, T value)
+    {
+        return spirv::atomicUMin<T>(ptr, spv::ScopeDevice, spv::MemorySemanticsMaskNone, value);
+    }
+
+    template<typename Ptr_T> // DXC Workaround
+    static T __call(Ptr_T ptr, T value)
+    {
+        return spirv::atomicUMin<T>(ptr, spv::ScopeDevice, spv::MemorySemanticsMaskNone, value);
+    }
+};
+
+template<typename T NBL_STRUCT_CONSTRAINABLE>
+struct atomicMax;
+
+template<typename T>
+NBL_PARTIAL_REQ_TOP(concepts::SignedIntegral<T>)
+struct atomicMax<T NBL_PARTIAL_REQ_BOT(concepts::SignedIntegral<T>) >
+{
+    static T __call(NBL_REF_ARG(T) ptr, T value)
+    {
+        return spirv::atomicSMax<T>(ptr, spv::ScopeDevice, spv::MemorySemanticsMaskNone, value);
+    }
+
+    template<typename Ptr_T> // DXC Workaround
+    static T __call(Ptr_T ptr, T value)
+    {
+        return spirv::atomicSMax<T>(ptr, spv::ScopeDevice, spv::MemorySemanticsMaskNone, value);
+    }
+};
+
+template<typename T>
+NBL_PARTIAL_REQ_TOP(concepts::UnsignedIntegral<T>)
+struct atomicMax<T NBL_PARTIAL_REQ_BOT(concepts::UnsignedIntegral<T>) >
+{
+    static T __call(NBL_REF_ARG(T) ptr, T value)
+    {
+        return spirv::atomicUMax<T>(ptr, spv::ScopeDevice, spv::MemorySemanticsMaskNone, value);
+    }
+
+    template<typename Ptr_T> // DXC Workaround
+    static T __call(Ptr_T ptr, T value)
+    {
+        return spirv::atomicUMax<T>(ptr, spv::ScopeDevice, spv::MemorySemanticsMaskNone, value);
+    }
+};
+}
+
+template<typename T>
+T atomicMin(NBL_REF_ARG(T) ptr, T value)
+{
+    return impl::atomicMin<T>::__call(ptr, value);
+}
+template<typename T, typename Ptr_T> // DXC Workaround
+enable_if_t<spirv::is_pointer_v<Ptr_T>, T> atomicMin(Ptr_T ptr, T value)
+{
+    return impl::atomicMin<T>::template __call<Ptr_T>(ptr, value);
+}
+template<typename T>
+T atomicMax(NBL_REF_ARG(T) ptr, T value)
+{
+    return impl::atomicMax<T>::__call(ptr, value);
+}
+template<typename T, typename Ptr_T> // DXC Workaround
+enable_if_t<spirv::is_pointer_v<Ptr_T>, T> atomicMax(Ptr_T ptr, T value)
+{
+    return impl::atomicMax<T>::template __call<Ptr_T>(ptr, value);
+}
+
 /**
  * GLSL extended math
  */