From 487ae034e2b03ddd67945132c8fecbd937952705 Mon Sep 17 00:00:00 2001
From: Sriram Murali <85252063+sriramm-nv@users.noreply.github.com>
Date: Mon, 13 May 2024 23:57:57 -0700
Subject: Add LoadAligned and StoreAligned methods to ByteAddressBuffers
 (#4066)

Fixes #4062

This change enables wide load/stores for byte-address-buffer backed
resources, when the data is accessed at an offset that is aligned.

**Goals**
- Improve performance by issuing wider instructions instead of sequence
  of scalar instructions, for load and stores of byte-address buffers.
- Reduce code-size and readability of the generated shaders.
- Help naive users as well as ninja programmers, generate optimal code.

**Non Goals**
- Help with Structured buffers, or other resources.
- Target compilation time improvements.

**Key changes**
Adds 2 new overloads for Load and Store operations on ByteAddress Buffers.
1. Load / Store with an extra alignment parameter
```
    resource.Load<T>(offset, alignment);
    resource.Store<T>(offset, value, alignment);
```
2. LoadAligned / StoreAligned with no extra parameter,
   with the same signature as orignial Load / Store.
```
    resource.LoadAligned<T>(offset);
    resource.StoreAligned<T>(offset, value);
```
    - This overload will implicitly identify the alignment value,
    from the base type T of the elementary unit of the resource.

**Supported resources**
1. Vectors
   This can be upto 4 elements, i.e. float -- float4.
2. Arrays
   This does not have a limit on number of elements, but on a
   conservative estimate, we can limit to few hundreds.
3. Structures
   This is used to group a resource of a single type.
```
 struct {
    float4 x;
 }
```
**Code updates**
- Modified byte-address-ir legalize to handle struct, array and vector
  kinds of load or store access
- Added custom hlsl stdlib functions to implement all the overloads for Load,
  Store etc.
- Added C-like emitter, SPIR-V emitter for handling ByteAddressBuffers.
- Added a new core stdlib function intrinsic to wrap around alignOf<T>().
- Added a new peephole optimization entry to identify the equivalent
  IntLiteral value from the alignOf<T>() inst.
- Added tests to check explicit, and implicit aligned Load and Store
  operations.
---
 tests/compute/byte-address-buffer-aligned.slang | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'tests/compute/byte-address-buffer-aligned.slang')

diff --git a/tests/compute/byte-address-buffer-aligned.slang b/tests/compute/byte-address-buffer-aligned.slang
index 5024987aa..f959ec66d 100644
--- a/tests/compute/byte-address-buffer-aligned.slang
+++ b/tests/compute/byte-address-buffer-aligned.slang
@@ -109,8 +109,8 @@ void computeMain(uint3 threadId : SV_DispatchThreadID)
     // CHECK3-DAG: OpStore %[[V33]] %[[V28]]
     // CHECK3-DAG: %[[V34:[a-zA-Z0-9_]+]] = OpAccessChain %[[SBf]] %[[BUF00]]
     // CHECK3-DAG: OpStore %[[V34]] %[[V30]]
-    buffer0.Store(32, buffer0.Load<float4>(32));
-	buffer0.Store(32, buffer0.Load<float4>(8));
-	buffer0.Store(8, buffer0.Load<float4>(32));
-	buffer0.Store(8, buffer0.Load<float4>(8));
+    buffer0.StoreAligned(32, buffer0.LoadAligned<float4>(32));
+    buffer0.StoreAligned(32, buffer0.LoadAligned<float4>(8));
+    buffer0.StoreAligned(8, buffer0.LoadAligned<float4>(32));
+    buffer0.StoreAligned(8, buffer0.LoadAligned<float4>(8));
 }
-- 
cgit v1.2.3