[clang] 16d1a64 - [DirectX] Fix HLSL bitshifts to leverage the OpenCL pipeline for bitshifting (#81030)

[via cfe-commits]

Author: Cooper Partin
Date: 2024-02-08T11:50:21-06:00
New Revision: 16d1a6486c25769d264a6ddb70a48bbb1c23c077

URL: https://github.com/llvm/llvm-project/commit/16d1a6486c25769d264a6ddb70a48bbb1c23c077
DIFF: https://github.com/llvm/llvm-project/commit/16d1a6486c25769d264a6ddb70a48bbb1c23c077.diff

LOG: [DirectX] Fix HLSL bitshifts to leverage the OpenCL pipeline for bitshifting (#81030)

Fixes #55106

In HLSL bit shifts are defined to shift by shift size % type size. This
contains the following changes:

HLSL codegen bit shifts will be emitted as x << (y & (sizeof(x) - 1) and
bitshift masking leverages the OpenCL pipeline for this.

Tests were also added to validate this behavior.


Before this change the following was being emitted:
; Function Attrs: noinline nounwind optnone
define noundef i32 @"?shl32@@YAHHH at Z"(i32 noundef %V, i32 noundef %S) #0
{
entry:
  %S.addr = alloca i32, align 4
  %V.addr = alloca i32, align 4
  store i32 %S, ptr %S.addr, align 4
  store i32 %V, ptr %V.addr, align 4
  %0 = load i32, ptr %V.addr, align 4
  %1 = load i32, ptr %S.addr, align 4
  %shl = shl i32 %0, %1
  ret i32 %shl
}

After this change:
; Function Attrs: noinline nounwind optnone
define noundef i32 @"?shl32@@YAHHH at Z"(i32 noundef %V, i32 noundef %S) #0
{
entry:
  %S.addr = alloca i32, align 4
  %V.addr = alloca i32, align 4
  store i32 %S, ptr %S.addr, align 4
  store i32 %V, ptr %V.addr, align 4
  %0 = load i32, ptr %V.addr, align 4
  %1 = load i32, ptr %S.addr, align 4
  %shl.mask = and i32 %1, 31
  %shl = shl i32 %0, %shl.mask
  ret i32 %shl
}

---------

Co-authored-by: Cooper Partin <coopp at ntdev.microsoft.com>

Added: 
    clang/test/CodeGenHLSL/shift-mask.hlsl

Modified: 
    clang/lib/CodeGen/CGExprScalar.cpp

Removed: 
    


################################################################################
diff  --git a/clang/lib/CodeGen/CGExprScalar.cpp b/clang/lib/CodeGen/CGExprScalar.cpp
index df8f71cf1d9008..fa03163bbde577 100644
--- a/clang/lib/CodeGen/CGExprScalar.cpp
+++ b/clang/lib/CodeGen/CGExprScalar.cpp
@@ -4168,7 +4168,7 @@ Value *ScalarExprEmitter::EmitShl(const BinOpInfo &Ops) {
   bool SanitizeBase = SanitizeSignedBase || SanitizeUnsignedBase;
   bool SanitizeExponent = CGF.SanOpts.has(SanitizerKind::ShiftExponent);
   // OpenCL 6.3j: shift values are effectively % word size of LHS.
-  if (CGF.getLangOpts().OpenCL)
+  if (CGF.getLangOpts().OpenCL || CGF.getLangOpts().HLSL)
     RHS = ConstrainShiftValue(Ops.LHS, RHS, "shl.mask");
   else if ((SanitizeBase || SanitizeExponent) &&
            isa<llvm::IntegerType>(Ops.LHS->getType())) {
@@ -4237,7 +4237,7 @@ Value *ScalarExprEmitter::EmitShr(const BinOpInfo &Ops) {
     RHS = Builder.CreateIntCast(RHS, Ops.LHS->getType(), false, "sh_prom");
 
   // OpenCL 6.3j: shift values are effectively % word size of LHS.
-  if (CGF.getLangOpts().OpenCL)
+  if (CGF.getLangOpts().OpenCL || CGF.getLangOpts().HLSL)
     RHS = ConstrainShiftValue(Ops.LHS, RHS, "shr.mask");
   else if (CGF.SanOpts.has(SanitizerKind::ShiftExponent) &&
            isa<llvm::IntegerType>(Ops.LHS->getType())) {

diff  --git a/clang/test/CodeGenHLSL/shift-mask.hlsl b/clang/test/CodeGenHLSL/shift-mask.hlsl
new file mode 100644
index 00000000000000..d046efaf9c1f9c
--- /dev/null
+++ b/clang/test/CodeGenHLSL/shift-mask.hlsl
@@ -0,0 +1,35 @@
+// RUN: %clang_cc1 -finclude-default-header -x hlsl -triple \
+// RUN:   dxil-pc-shadermodel6.3-library %s \
+// RUN:   -emit-llvm -disable-llvm-passes -o - | FileCheck %s
+
+int shl32(int V, int S) {
+  return V << S;
+}
+
+// CHECK: define noundef i32 @"?shl32{{[@$?.A-Za-z0-9_]+}}"(i32 noundef %V, i32 noundef %S) #0 {
+// CHECK-DAG:  %[[Masked:.*]] = and i32 %{{.*}}, 31
+// CHECK-DAG:  %{{.*}} = shl i32 %{{.*}}, %[[Masked]]
+
+int shr32(int V, int S) {
+  return V >> S;
+}
+
+// CHECK: define noundef i32 @"?shr32{{[@$?.A-Za-z0-9_]+}}"(i32 noundef %V, i32 noundef %S) #0 {
+// CHECK-DAG:  %[[Masked:.*]] = and i32 %{{.*}}, 31
+// CHECK-DAG:  %{{.*}} = ashr i32 %{{.*}}, %[[Masked]]
+
+int64_t shl64(int64_t V, int64_t S) {
+  return V << S;
+}
+
+// CHECK: define noundef i64 @"?shl64{{[@$?.A-Za-z0-9_]+}}"(i64 noundef %V, i64 noundef %S) #0 {
+// CHECK-DAG:  %[[Masked:.*]] = and i64 %{{.*}}, 63
+// CHECK-DAG:  %{{.*}} = shl i64 %{{.*}}, %[[Masked]]
+
+int64_t shr64(int64_t V, int64_t S) {
+  return V >> S;
+}
+
+// CHECK: define noundef i64 @"?shr64{{[@$?.A-Za-z0-9_]+}}"(i64 noundef %V, i64 noundef %S) #0 {
+// CHECK-DAG:  %[[Masked:.*]] = and i64 %{{.*}}, 63
+// CHECK-DAG:  %{{.*}} = ashr i64 %{{.*}}, %[[Masked]]