Addition of `Load`/`Store` coherent operations (#8395)

Fixes: https://github.com/shader-slang/slang/issues/7634
Duplicate of PR https://github.com/shader-slang/slang/pull/8052

Primary Changes:
* Added `storeCoherent` and `loadCoherent` for coherent load/store via
pointers. This is backed by `IRMemoryScopeAttr` which is an `IRAttr`
attached to `IRLoad` and `IRStore`
* Logic in `source\slang\slang-emit-spirv.cpp` for load/store emitting
has been reworked to be less messy and more maintainable
* Add to `hlsl.meta.slang` coop vector and coop matrix coherent
load/store operations

Secondary Changes:
* Added a missing load/store test for coop matrix:
`tests\cooperative-matrix\load-store-pointer.slang`

---------

Co-authored-by: ArielG-NV <aglasroth@nvidia.com>
Co-authored-by: ArielG-NV <159081215+ArielG-NV@users.noreply.github.com>
Co-authored-by: slangbot <186143334+slangbot@users.noreply.github.com>
Co-authored-by: Nathan V. Morrical <natemorrical@gmail.com>

1 files changed, 24 insertions, 0 deletions

diff --git a/tests/language-feature/pointer/coherent-load-store-physical-storage-buffer.slang b/tests/language-feature/pointer/coherent-load-store-physical-storage-buffer.slang
new file mode 100644
index 000000000..b70664d82
--- /dev/null
+++ b/tests/language-feature/pointer/coherent-load-store-physical-storage-buffer.slang
@@ -0,0 +1,24 @@
+//TEST:SIMPLE(filecheck=SPIRV):-stage compute -entry computeMain -target spirv -capability vk_mem_model
+//TEST(compute):COMPARE_COMPUTE(filecheck-buffer=CHECK):-vk -output-using-type -emit-spirv-directly -capability vk_mem_model
+
+// Ensure SPIRV emits coherent operations here
+// SPIRV: MakePointerVisible
+// SPIRV: MakePointerAvailable
+
+// CHECK: 2
+
+//TEST_INPUT:ubuffer(data=[1 2 3], stride=4):name=inputBuffer
+uniform int* inputBuffer;
+
+//TEST_INPUT:ubuffer(data=[0 0 0], stride=4):out,name=outputBuffer
+uniform int* outputBuffer;
+
+[shader("compute")]
+[numthreads(32, 1, 1)]
+void computeMain()
+{
+    Ptr<int> ptrIn = inputBuffer;
+    Ptr<int> secondPtrIn = ptrIn;
+    Ptr<int> ptrOut = outputBuffer;
+    storeCoherent<4, MemoryScope::Device>(ptrOut, loadCoherent<4, MemoryScope::Device>(&secondPtrIn[1]));
+}
\ No newline at end of file