[DirectX] Add 32- and 64-bit 3-element vectors to DataLayout (#160955)

This explicitly adds two 3-element vectors to the DataLayout so that
they'll be element-aligned. We need to do this more generally for
vectors, but this unblocks some very common cases.

Workaround for #123968

Author: bogner

clang/lib/Basic/Targets/DirectX.h

@@ -64,8 +64,11 @@ class LLVM_LIBRARY_VISIBILITY DirectXTargetInfo : public TargetInfo {
     NoAsmVariants = true;
     PlatformMinVersion = Triple.getOSVersion();
     PlatformName = llvm::Triple::getOSTypeName(Triple.getOS());
+    // TODO: We need to align vectors on the element size generally, but for now
+    // we hard code this for 3-element 32- and 64-bit vectors as a workaround.
+    // See https://github.com/llvm/llvm-project/issues/123968
     resetDataLayout("e-m:e-p:32:32-i1:32-i8:8-i16:16-i32:32-i64:64-f16:16-f32:"
-                    "32-f64:64-n8:16:32:64");
+                    "32-f64:64-n8:16:32:64-v48:16:16-v96:32:32-v192:64:64");
     TheCXXABI.set(TargetCXXABI::GenericItanium);
   }
   bool useFP16ConversionIntrinsics() const override { return false; }

clang/test/CodeGenHLSL/basic-target.c

@@ -6,5 +6,5 @@
 // RUN: %clang -cc1 -triple dxil-pc-shadermodel6.0-domain -emit-llvm -o - %s | FileCheck %s
 // RUN: %clang -cc1 -triple dxil-pc-shadermodel6.0-geometry -emit-llvm -o - %s | FileCheck %s
 
-// CHECK: target datalayout = "e-m:e-p:32:32-i1:32-i8:8-i16:16-i32:32-i64:64-f16:16-f32:32-f64:64-n8:16:32:64"
+// CHECK: target datalayout = "e-m:e-p:32:32-i1:32-i8:8-i16:16-i32:32-i64:64-f16:16-f32:32-f64:64-n8:16:32:64-v48:16:16-v96:32:32-v192:64:64"
 // CHECK: target triple = "dxilv1.0-pc-shadermodel6.0-{{[a-z]+}}"

llvm/lib/TargetParser/TargetDataLayout.cpp

@@ -548,8 +548,11 @@ std::string Triple::computeDataLayout(StringRef ABIName) const {
   case Triple::csky:
     return computeCSKYDataLayout(*this);
   case Triple::dxil:
+    // TODO: We need to align vectors on the element size generally, but for now
+    // we hard code this for 3-element 32- and 64-bit vectors as a workaround.
+    // See https://github.com/llvm/llvm-project/issues/123968
     return "e-m:e-p:32:32-i1:32-i8:8-i16:16-i32:32-i64:64-f16:16-"
-           "f32:32-f64:64-n8:16:32:64";
+           "f32:32-f64:64-n8:16:32:64-v48:16:16-v96:32:32-v192:64:64";
   case Triple::hexagon:
     return "e-m:e-p:32:32:32-a:0-n16:32-"
            "i64:64:64-i32:32:32-i16:16:16-i1:8:8-f32:32:32-f64:64:64-"

llvm/test/CodeGen/DirectX/CBufferAccess/memcpy.ll

@@ -74,7 +74,7 @@ entry:
 ; CHECK:    [[UPTO1:%.*]] = insertelement <3 x double> [[UPTO0]], double [[Y]], i32 1
 ; CHECK:    [[UPTO2:%.*]] = insertelement <3 x double> [[UPTO1]], double [[Z]], i32 2
 ; CHECK:    [[DEST:%.*]] = getelementptr inbounds i8, ptr [[A2_COPY:%.*]], i32 0
-; CHECK:    store <3 x double> [[UPTO2]], ptr [[DEST]], align 32
+; CHECK:    store <3 x double> [[UPTO2]], ptr [[DEST]], align 8
 ; CHECK:    [[LOAD:%.*]] = call { double, double } @llvm.dx.resource.load.cbufferrow.2.{{.*}}(target("dx.CBuffer", {{.*}})) [[CB]], i32 5)
 ; CHECK:    [[X:%.*]] = extractvalue { double, double } [[LOAD]], 0
 ; CHECK:    [[Y:%.*]] = extractvalue { double, double } [[LOAD]], 1
@@ -83,9 +83,9 @@ entry:
 ; CHECK:    [[UPTO0:%.*]] = insertelement <3 x double> poison, double [[X]], i32 0
 ; CHECK:    [[UPTO1:%.*]] = insertelement <3 x double> [[UPTO0]], double [[Y]], i32 1
 ; CHECK:    [[UPTO2:%.*]] = insertelement <3 x double> [[UPTO1]], double [[Z]], i32 2
-; CHECK:    [[DEST:%.*]] = getelementptr inbounds i8, ptr [[A2_COPY]], i32 32
-; CHECK:    store <3 x double> [[UPTO2]], ptr [[DEST]], align 32
-  call void @llvm.memcpy.p0.p2.i32(ptr align 32 %a2.copy, ptr addrspace(2) align 32 @a2, i32 64, i1 false)
+; CHECK:    [[DEST:%.*]] = getelementptr inbounds i8, ptr [[A2_COPY]], i32 24
+; CHECK:    store <3 x double> [[UPTO2]], ptr [[DEST]], align 8
+  call void @llvm.memcpy.p0.p2.i32(ptr align 32 %a2.copy, ptr addrspace(2) align 32 @a2, i32 48, i1 false)
 
 ; CHECK:    [[CB:%.*]] = load target("dx.CBuffer", {{.*}})), ptr @CB.cb, align 4
 ; CHECK:    [[LOAD:%.*]] = call { half, half, half, half, half, half, half, half } @llvm.dx.resource.load.cbufferrow.8.{{.*}}(target("dx.CBuffer", {{.*}})) [[CB]], i32 7)