Rewriting the lower-buffer-element-type pass to avoid unnecessary packing/unpacking. (#8526)

Part of the effort to improve the performance of generated SPIRV code.

The existing lower-buffer-element-type pass works by loading the entire
buffer element content from memory, and translate it to logical type
stored in a local variable at the earliest reference of a buffer handle.
This means that is can generate inefficient code that reads more than
necessary.

Consider this example:
```
struct BigStruct { bool values[1024]; }
ConstantBuffer<BigStruct> cb;

void test(BigStruct v)
{
      if (v.values[0]) { printf("ok"); }
}

[numthreads(1,1,1)]
void computeMain()
{
    test(cb);
}
```

In IR, the `computeMain` function before lower-buffer-element-type pass
is something like following:
```
func test:
   %v = param : BigStruct
   %barr = fieldExtract(%v, "values")
   %element = elementExtract(%barr, 0)
    ... // uses %element 

func computeMain:
  %v = load(cb)
  call %test %v
```

The existing lower-buffer-element-type pass will rewrite the bool array
in `BigStruct` into `int` array so it is legal in SPIRV. However, it
does so by inserting the translation on the first `load` of the constant
buffer:

```
struct BigStruct_std430 {
    int values[1024];
}
var cb : ConstantBuffer<BigStruct_std430>;
func computeMain:
   %tmpVar : var<BigStruct>
    call %unpackStorage(%tmpVar, cb)
   %v : BigStruct = load %tmpVar
   call %test %v
```

This means that the entire array will be loaded and translated to int,
before calling `test`, which only uses one element. It turns out that
the downstream compiler isn't always able to optimize out this
inefficient translation/copy.

This PR completely rewrites the way buffer-element-type lowering is
handled to avoid producing this inefficient code. It works in two parts:
first we turn on the `transformParamsToConstRef` pass for SPIRV target
as well, so we will translate the `test` function to take the `v`
parameter as `constref`. The second part is a redesigned
buffer-element-type pass that defers the storage-type to logical-type
translation until a value is actually used by a `load` instruction.

In this example, after `transformParamsToConstRef`, the IR is:

```
func test:
   %v = param : ConstRef<BigStruct>
   %barr = fieldAddr(%v, "values")
   %elementPtr = elementAddr(%barr, 0)
   %element = load(%elementPtr)
    ... // uses %element 

func computeMain:
  call %test %cb
```

The new `buffer-element-type-lowering` pass will take this IR, and
insert translation at latest possible time across the entire call graph,
and translate the IR into:

```
func test:
   %v = param : ConstRef<BigStruct_std430>
   %barr = fieldAddr(%v, "values")
   %elementPtr : ptr<int> = elementAddr(%barr, 0)
   %element_int = load(%elementPtr)
    %element = cast(%element_int) : %bool
    ... // uses %element 

func computeMain:
  call %test %cb
```

In this new IR, there is no longer a load and conversion of the entire
array.

See new comment in `slang-ir-lower-buffer-element-type.cpp` for more
details of how the pass works.

This PR also address many other issues surfaced by turning on
`transformParamsToConstRef` pass on SPIRV backend.

---------

Co-authored-by: slangbot <186143334+slangbot@users.noreply.github.com>

1 files changed, 77 insertions, 0 deletions

diff --git a/source/slang/slang-ir-util.cpp b/source/slang/slang-ir-util.cpp
index 9b852b803..8584ea95e 100644
--- a/source/slang/slang-ir-util.cpp
+++ b/source/slang/slang-ir-util.cpp
@@ -2128,6 +2128,40 @@ IRType* getIRVectorBaseType(IRType* type)
     return as<IRVectorType>(type)->getElementType();
 }
 
+IRType* getElementType(IRBuilder& builder, IRType* valueType)
+{
+    valueType = (IRType*)unwrapAttributedType(valueType);
+    if (auto arrayType = as<IRArrayTypeBase>(valueType))
+    {
+        return arrayType->getElementType();
+    }
+    else if (auto vectorType = as<IRVectorType>(valueType))
+    {
+        return vectorType->getElementType();
+    }
+    else if (auto basicType = as<IRBasicType>(valueType))
+    {
+        return basicType;
+    }
+    else if (auto coopVecType = as<IRCoopVectorType>(valueType))
+    {
+        return coopVecType->getElementType();
+    }
+    else if (auto matrixType = as<IRMatrixType>(valueType))
+    {
+        return builder.getVectorType(matrixType->getElementType(), matrixType->getColumnCount());
+    }
+    else if (auto coopMatType = as<IRCoopMatrixType>(valueType))
+    {
+        return coopMatType->getElementType();
+    }
+    else if (auto hlslInputPatchType = as<IRHLSLInputPatchType>(valueType))
+    {
+        return hlslInputPatchType->getElementType();
+    }
+    return nullptr;
+}
+
 Int getSpecializationConstantId(IRGlobalParam* param)
 {
     auto layout = findVarLayout(param);
@@ -2483,4 +2517,47 @@ bool isIROpaqueType(IRType* type)
     }
 }
 
+bool isPointerToImmutableLocation(IRInst* loc)
+{
+    switch (loc->getOp())
+    {
+    case kIROp_GetStructuredBufferPtr:
+    case kIROp_ImageSubscript:
+        return isPointerToImmutableLocation(loc->getOperand(0));
+    default:
+        break;
+    }
+
+    auto type = loc->getDataType();
+    if (!type)
+        return false;
+
+    switch (type->getOp())
+    {
+    case kIROp_HLSLStructuredBufferType:
+    case kIROp_HLSLByteAddressBufferType:
+    case kIROp_ConstantBufferType:
+    case kIROp_ParameterBlockType:
+        return true;
+    default:
+        break;
+    }
+
+    if (auto textureType = as<IRTextureType>(type))
+        return textureType->getAccess() == SLANG_RESOURCE_ACCESS_READ;
+
+    if (auto ptrType = as<IRPtrTypeBase>(type))
+    {
+        switch (ptrType->getAddressSpace())
+        {
+        case AddressSpace::BuiltinInput:
+        case AddressSpace::Input:
+        case AddressSpace::MetalObjectData:
+        case AddressSpace::Uniform:
+        case AddressSpace::UniformConstant:
+            return true;
+        }
+    }
+    return false;
+}
 } // namespace Slang