IR/Verifier: Allow vector type in atomic load and store (llvm#148893)

Vector types on atomics are assumed to be invalid by the verifier. However,
this type can be valid if it is lowered by codegen.

Author: jofrn

llvm/docs/LangRef.rst

@@ -11455,9 +11455,9 @@ If the ``load`` is marked as ``atomic``, it takes an extra :ref:`ordering
 <ordering>` and optional ``syncscope("<target-scope>")`` argument. The
 ``release`` and ``acq_rel`` orderings are not valid on ``load`` instructions.
 Atomic loads produce :ref:`defined <memmodel>` results when they may see
-multiple atomic stores. The type of the pointee must be an integer, pointer, or
-floating-point type whose bit width is a power of two greater than or equal to
-eight. ``align`` must be
+multiple atomic stores. The type of the pointee must be an integer, pointer,
+floating-point, or vector type whose bit width is a power of two greater than
+or equal to eight. ``align`` must be
 explicitly specified on atomic loads. Note: if the alignment is not greater or
 equal to the size of the `<value>` type, the atomic operation is likely to
 require a lock and have poor performance. ``!nontemporal`` does not have any
@@ -11594,9 +11594,9 @@ If the ``store`` is marked as ``atomic``, it takes an extra :ref:`ordering
 <ordering>` and optional ``syncscope("<target-scope>")`` argument. The
 ``acquire`` and ``acq_rel`` orderings aren't valid on ``store`` instructions.
 Atomic loads produce :ref:`defined <memmodel>` results when they may see
-multiple atomic stores. The type of the pointee must be an integer, pointer, or
-floating-point type whose bit width is a power of two greater than or equal to
-eight. ``align`` must be
+multiple atomic stores. The type of the pointee must be an integer, pointer,
+floating-point, or vector type whose bit width is a power of two greater than
+or equal to eight. ``align`` must be
 explicitly specified on atomic stores. Note: if the alignment is not greater or
 equal to the size of the `<value>` type, the atomic operation is likely to
 require a lock and have poor performance. ``!nontemporal`` does not have any

llvm/docs/ReleaseNotes.md

@@ -66,6 +66,7 @@ Changes to the LLVM IR
   `@llvm.masked.gather` and `@llvm.masked.scatter` intrinsics has been removed.
   Instead, the `align` attribute should be placed on the pointer (or vector of
   pointers) argument.
+* A `load atomic` may now be used with vector types on x86.
 
 Changes to LLVM infrastructure
 ------------------------------

llvm/lib/IR/Verifier.cpp

@@ -4446,10 +4446,12 @@ void Verifier::visitLoadInst(LoadInst &LI) {
     Check(LI.getOrdering() != AtomicOrdering::Release &&
               LI.getOrdering() != AtomicOrdering::AcquireRelease,
           "Load cannot have Release ordering", &LI);
-    Check(ElTy->isIntOrPtrTy() || ElTy->isFloatingPointTy(),
-          "atomic load operand must have integer, pointer, or floating point "
-          "type!",
+    Check(ElTy->getScalarType()->isIntOrPtrTy() ||
+              ElTy->getScalarType()->isFloatingPointTy(),
+          "atomic load operand must have integer, pointer, floating point, "
+          "or vector type!",
           ElTy, &LI);
+
     checkAtomicMemAccessSize(ElTy, &LI);
   } else {
     Check(LI.getSyncScopeID() == SyncScope::System,
@@ -4472,9 +4474,10 @@ void Verifier::visitStoreInst(StoreInst &SI) {
     Check(SI.getOrdering() != AtomicOrdering::Acquire &&
               SI.getOrdering() != AtomicOrdering::AcquireRelease,
           "Store cannot have Acquire ordering", &SI);
-    Check(ElTy->isIntOrPtrTy() || ElTy->isFloatingPointTy(),
-          "atomic store operand must have integer, pointer, or floating point "
-          "type!",
+    Check(ElTy->getScalarType()->isIntOrPtrTy() ||
+              ElTy->getScalarType()->isFloatingPointTy(),
+          "atomic store operand must have integer, pointer, floating point, "
+          "or vector type!",
           ElTy, &SI);
     checkAtomicMemAccessSize(ElTy, &SI);
   } else {

llvm/test/Assembler/atomic.ll

@@ -52,6 +52,25 @@ define void @f(ptr %x) {
   ; CHECK: atomicrmw volatile usub_sat ptr %x, i32 10 syncscope("agent") monotonic
   atomicrmw volatile usub_sat ptr %x, i32 10 syncscope("agent") monotonic
 
+  ; CHECK : load atomic <1 x i32>, ptr %x unordered, align 4
+  load atomic <1 x i32>, ptr %x unordered, align 4
+  ; CHECK : store atomic <1 x i32> splat (i32 3), ptr %x release, align 4
+  store atomic <1 x i32> <i32 3>, ptr %x release, align 4
+  ; CHECK : load atomic <2 x i32>, ptr %x unordered, align 4
+  load atomic <2 x i32>, ptr %x unordered, align 4
+  ; CHECK : store atomic <2 x i32> <i32 3, i32 4>, ptr %x release, align 4
+  store atomic <2 x i32> <i32 3, i32 4>, ptr %x release, align 4
+
+  ; CHECK : load atomic <2 x ptr>, ptr %x unordered, align 4
+  load atomic <2 x ptr>, ptr %x unordered, align 4
+  ; CHECK : store atomic <2 x ptr> zeroinitializer, ptr %x release, align 4
+  store atomic <2 x ptr> zeroinitializer, ptr %x release, align 4
+
+  ; CHECK : load atomic <2 x float>, ptr %x unordered, align 4
+  load atomic <2 x float>, ptr %x unordered, align 4
+  ; CHECK : store atomic <2 x float> <float 3.0, float 4.0>, ptr %x release, align 4
+  store atomic <2 x float> <float 3.0, float 4.0>, ptr %x release, align 4
+
   ; CHECK: fence syncscope("singlethread") release
   fence syncscope("singlethread") release
   ; CHECK: fence seq_cst

llvm/test/Verifier/atomics.ll

@@ -1,14 +1,15 @@
 ; RUN: not opt -passes=verify < %s 2>&1 | FileCheck %s
+; CHECK: atomic store operand must have integer, pointer, floating point, or vector type!
+; CHECK: atomic load operand must have integer, pointer, floating point, or vector type!
 
-; CHECK: atomic store operand must have integer, pointer, or floating point type!
-; CHECK: atomic load operand must have integer, pointer, or floating point type!
+%ty = type { i32 };
 
-define void @foo(ptr %P, <1 x i64> %v) {
-  store atomic <1 x i64> %v, ptr %P unordered, align 8
+define void @foo(ptr %P, %ty %v) {
+  store atomic %ty %v, ptr %P unordered, align 8
   ret void
 }
 
-define <1 x i64> @bar(ptr %P) {
-  %v = load atomic <1 x i64>, ptr %P unordered, align 8
-  ret <1 x i64> %v
+define %ty @bar(ptr %P) {
+  %v = load atomic %ty, ptr %P unordered, align 8
+  ret %ty %v
 }