From 862766e01e9000ef1ad760ce602563cb0b4b9de4 Mon Sep 17 00:00:00 2001
From: Florian Hahn <flo@fhahn.com>
Date: Wed, 1 Apr 2020 09:10:24 +0100
Subject: [PATCH] [Verifier] Verify matrix dimensions operands match vector
 size.

This patch adds checks to the verifier to ensure the dimension arguments
passed to the matrix intrinsics match the vector types for their
arugments/return values.

Reviewers: anemet, Gerolf, andrew.w.kaylor, LuoYuanke

Reviewed By: anemet

Differential Revision: https://reviews.llvm.org/D77129
---
 llvm/lib/IR/Verifier.cpp                | 36 +++++++++++++++++++++++++++++
 llvm/test/Verifier/matrix-intrinsics.ll | 40 +++++++++++++++++++++++++++++++++
 2 files changed, 76 insertions(+)
 create mode 100644 llvm/test/Verifier/matrix-intrinsics.ll

diff --git a/llvm/lib/IR/Verifier.cpp b/llvm/lib/IR/Verifier.cpp
index a31a917..b0b9af9 100644
--- a/llvm/lib/IR/Verifier.cpp
+++ b/llvm/lib/IR/Verifier.cpp
@@ -4791,6 +4791,42 @@ void Verifier::visitIntrinsicCall(Intrinsic::ID ID, CallBase &Call) {
     Assert(Size % 16 == 0, "bswap must be an even number of bytes", &Call);
     break;
   }
+  case Intrinsic::matrix_multiply:
+  case Intrinsic::matrix_transpose:
+  case Intrinsic::matrix_columnwise_load:
+  case Intrinsic::matrix_columnwise_store: {
+    ConstantInt *NumRows;
+    ConstantInt *NumColumns;
+    VectorType *TypeToCheck;
+    switch (ID) {
+    case Intrinsic::matrix_multiply:
+      NumRows = cast<ConstantInt>(Call.getArgOperand(2));
+      NumColumns = cast<ConstantInt>(Call.getArgOperand(4));
+      TypeToCheck = cast<VectorType>(Call.getType());
+      break;
+    case Intrinsic::matrix_transpose:
+      NumRows = cast<ConstantInt>(Call.getArgOperand(1));
+      NumColumns = cast<ConstantInt>(Call.getArgOperand(2));
+      TypeToCheck = cast<VectorType>(Call.getType());
+      break;
+    case Intrinsic::matrix_columnwise_load:
+      NumRows = cast<ConstantInt>(Call.getArgOperand(2));
+      NumColumns = cast<ConstantInt>(Call.getArgOperand(3));
+      TypeToCheck = cast<VectorType>(Call.getType());
+      break;
+    case Intrinsic::matrix_columnwise_store:
+      NumRows = cast<ConstantInt>(Call.getArgOperand(3));
+      NumColumns = cast<ConstantInt>(Call.getArgOperand(4));
+      TypeToCheck = cast<VectorType>(Call.getArgOperand(0)->getType());
+      break;
+    default:
+      llvm_unreachable("unexpected intrinsic");
+    }
+    Assert(TypeToCheck->getNumElements() ==
+               NumRows->getZExtValue() * NumColumns->getZExtValue(),
+           "result of a matrix operation does not fit in the returned vector");
+    break;
+  }
   };
 }
 
diff --git a/llvm/test/Verifier/matrix-intrinsics.ll b/llvm/test/Verifier/matrix-intrinsics.ll
new file mode 100644
index 0000000..d2f23ab
--- /dev/null
+++ b/llvm/test/Verifier/matrix-intrinsics.ll
@@ -0,0 +1,40 @@
+; RUN: not llvm-as < %s -o /dev/null 2>&1 | FileCheck %s
+
+declare <4 x float> @llvm.matrix.transpose.v4f32(<4 x float>, i32, i32)
+define <4 x float> @transpose(<4 x float> %m) {
+; CHECK: assembly parsed, but does not verify as correct!
+; CHECK-NEXT: result of a matrix operation does not fit in the returned vector
+; CHECK-NEXT: result of a matrix operation does not fit in the returned vector
+  %result.1 = call <4 x float> @llvm.matrix.transpose.v4f32(<4 x float> %m, i32 3, i32 2)
+  %result.2 = call <4 x float> @llvm.matrix.transpose.v4f32(<4 x float> %result.1, i32 2, i32 1)
+  ret <4 x float> %result.2
+}
+
+declare <4 x float> @llvm.matrix.multiply.v4f32.v4f32.v4f32(<4 x float>, <4 x float>, i32, i32, i32)
+define <4 x float> @multiply(<4 x float> %m) {
+; CHECK-NEXT: result of a matrix operation does not fit in the returned vector
+; CHECK-NEXT: result of a matrix operation does not fit in the returned vector
+  %result.1 = call <4 x float> @llvm.matrix.multiply.v4f32.v4f32.v4f32(<4 x float> %m, <4 x float> %m, i32 3, i32 2, i32 2)
+  %result.2 = call <4 x float> @llvm.matrix.multiply.v4f32.v4f32.v4f32(<4 x float> %result.1, <4 x float> %m, i32 2, i32 2, i32 1)
+  ret <4 x float> %result.2
+}
+
+declare <4 x float> @llvm.matrix.columnwise.load.v4f32.p0v4f32(<4 x float>*, i32, i32, i32)
+declare <6 x float> @llvm.matrix.columnwise.load.v6f32.p0v6f32(<6 x float>*, i32, i32, i32)
+define <4 x float> @columnwise_load(<4 x float>* %m, <6 x float>* %n) {
+; CHECK-NEXT: result of a matrix operation does not fit in the returned vector
+; CHECK-NEXT: result of a matrix operation does not fit in the returned vector
+  %result.1 = call <4 x float> @llvm.matrix.columnwise.load.v4f32.p0v4f32(<4 x float>* %m, i32 2, i32 1, i32 2)
+  %result.2 = call <6 x float> @llvm.matrix.columnwise.load.v6f32.p0v6f32(<6 x float>* %n, i32 2, i32 3, i32 3)
+  ret <4 x float> %result.1
+}
+
+declare void @llvm.matrix.columnwise.store.v4f32.p0v4f32(<4 x float>, <4 x float>*, i32, i32, i32)
+declare void @llvm.matrix.columnwise.store.v6f32.p0v6f32(<6 x float>, <6 x float>*, i32, i32, i32)
+define void @columnwise_store(<4 x float>* %m, <6 x float>* %n) {
+; CHECK-NEXT: result of a matrix operation does not fit in the returned vector
+; CHECK-NEXT: result of a matrix operation does not fit in the returned vector
+  call void @llvm.matrix.columnwise.store.v4f32.p0v4f32(<4 x float> zeroinitializer, <4 x float>* %m, i32 2, i32 1, i32 2)
+  call void @llvm.matrix.columnwise.store.v6f32.p0v6f32(<6 x float> zeroinitializer, <6 x float>* %n, i32 2, i32 3, i32 3)
+  ret void
+}
-- 
2.7.4