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.
---
 source/slang/slang-ir-peephole.cpp | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

(limited to 'source/slang/slang-ir-peephole.cpp')

diff --git a/source/slang/slang-ir-peephole.cpp b/source/slang/slang-ir-peephole.cpp
index 88b26fbd3..16e440b32 100644
--- a/source/slang/slang-ir-peephole.cpp
+++ b/source/slang/slang-ir-peephole.cpp
@@ -250,6 +250,30 @@ struct PeepholeContext : InstPassBase
 
         switch (inst->getOp())
         {
+        case kIROp_AlignOf:
+            // Fold all calls to alignOf<T>() that returns a simple integer value.
+            if (inst->getDataType()->getOp() == kIROp_IntType)
+            {
+                if (!targetProgram)
+                    break;
+
+                // Save the alignment information and exit early if it is invalid
+                IRSizeAndAlignment sizeAlignment;
+                auto alignOfInst = as<IRAlignOf>(inst);
+                auto baseType = alignOfInst->getBaseOp()->getDataType();
+                if (SLANG_FAILED(getNaturalSizeAndAlignment(targetProgram->getOptionSet(), baseType, &sizeAlignment)))
+                    break;
+                if (sizeAlignment.size == 0)
+                    break;
+
+                IRBuilder builder(module);
+                builder.setInsertBefore(inst);
+                auto stride = builder.getIntValue(inst->getDataType(), sizeAlignment.getStride());
+                inst->replaceUsesWith(stride);
+                maybeRemoveOldInst(inst);
+                changed = true;
+            }
+            break;
         case kIROp_GetResultError:
             if (inst->getOperand(0)->getOp() == kIROp_MakeResultError)
             {
-- 
cgit v1.2.3