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, 29 insertions, 0 deletions

diff --git a/tests/language-feature/pointer/coherent-load-store-image.slang b/tests/language-feature/pointer/coherent-load-store-image.slang
new file mode 100644
index 000000000..359994a0e
--- /dev/null
+++ b/tests/language-feature/pointer/coherent-load-store-image.slang
@@ -0,0 +1,29 @@
+//DISABLE_TEST:SIMPLE(filecheck=SPIRV):-stage compute -entry computeMain -target spirv -capability vk_mem_model
+//DISABLE_TEST(compute):COMPARE_COMPUTE(filecheck-buffer=CHECK):-vk -output-using-type -emit-spirv-directly -profile spirv_1_3 -capability vk_mem_model
+// These tests are expected to fail, pointers to texels are
+// currently a broken feature and do not work.
+// Additionally, we do not allow texel pointers with `__getAddress`.
+
+
+// Ensure SPIRV emits coherent operations here
+// SPIRV: MakeTexelAvailable
+// SPIRV: MakeTexelVisible
+
+// CHECK: 0
+// CHECK-NEXT: 5
+
+//TEST_INPUT: RWTexture1D(format=R32Uint, size=8, content = one, mipMaps = 1):name=texture
+RWTexture1D<uint> texture;
+
+//TEST_INPUT: ubuffer(data=[0 0 0 0], stride=4):out,name outputBuffer
+RWStructuredBuffer<uint> outputBuffer;
+
+[numthreads(32, 1, 1)]
+void computeMain()
+{
+    Ptr<uint> ptrIn = __getAddress(texture[1]);
+    Ptr<uint> secondPtrIn = ptrIn;
+
+    storeCoherent<4, MemoryScope::Device>(ptrIn, 5);
+    outputBuffer[0] = loadCoherent<4, MemoryScope::Device>(ptrIn);
+}