From 2a87314e75a47796186a7e846802d2bde4cb63c1 Mon Sep 17 00:00:00 2001
From: Craig Topper <craig.topper@intel.com>
Date: Tue, 14 Aug 2018 20:21:05 +0000
Subject: [PATCH] [InlineAsm] Update the min-legal-vector-width function
 attribute based on inputs and outputs to inline assembly

Summary:
Another piece of my ongoing to work for prefer-vector-width.

min-legal-vector-width will eventually be used by the X86 backend to know whether it needs to make 512 bits type legal when prefer-vector-width=256. If the user used inline assembly that passed in/out a 512-bit register, we need to make sure 512 bits are considered legal. Otherwise we'll get an assert failure when we try to wire up the inline assembly to the rest of the code.

This patch just checks the LLVM IR types to see if they are vectors and then updates the attribute based on their total width. I'm not sure if this is the best way to do this or if there's any subtlety I might have missed. So if anyone has other opinions on how to do this I'm open to suggestions.

Reviewers: chandlerc, rsmith, rnk

Reviewed By: rnk

Subscribers: eraman, cfe-commits

Differential Revision: https://reviews.llvm.org/D50678

llvm-svn: 339721
---
 clang/lib/CodeGen/CGStmt.cpp                  | 14 ++++++
 .../CodeGen/x86-inline-asm-min-vector-width.c | 45 +++++++++++++++++++
 2 files changed, 59 insertions(+)
 create mode 100644 clang/test/CodeGen/x86-inline-asm-min-vector-width.c

diff --git a/clang/lib/CodeGen/CGStmt.cpp b/clang/lib/CodeGen/CGStmt.cpp
index 4eff1ca08119..09c322a8529d 100644
--- a/clang/lib/CodeGen/CGStmt.cpp
+++ b/clang/lib/CodeGen/CGStmt.cpp
@@ -1979,6 +1979,11 @@ void CodeGenFunction::EmitAsmStmt(const AsmStmt &S) {
                               diag::err_asm_invalid_type_in_input)
             << OutExpr->getType() << OutputConstraint;
       }
+
+      // Update largest vector width for any vector types.
+      if (auto *VT = dyn_cast<llvm::VectorType>(ResultRegTypes.back()))
+        LargestVectorWidth = std::max(LargestVectorWidth,
+                                      VT->getPrimitiveSizeInBits());
     } else {
       ArgTypes.push_back(Dest.getAddress().getType());
       Args.push_back(Dest.getPointer());
@@ -2000,6 +2005,10 @@ void CodeGenFunction::EmitAsmStmt(const AsmStmt &S) {
                                                Arg->getType()))
         Arg = Builder.CreateBitCast(Arg, AdjTy);
 
+      // Update largest vector width for any vector types.
+      if (auto *VT = dyn_cast<llvm::VectorType>(Arg->getType()))
+        LargestVectorWidth = std::max(LargestVectorWidth,
+                                      VT->getPrimitiveSizeInBits());
       if (Info.allowsRegister())
         InOutConstraints += llvm::utostr(i);
       else
@@ -2080,6 +2089,11 @@ void CodeGenFunction::EmitAsmStmt(const AsmStmt &S) {
       CGM.getDiags().Report(S.getAsmLoc(), diag::err_asm_invalid_type_in_input)
           << InputExpr->getType() << InputConstraint;
 
+    // Update largest vector width for any vector types.
+    if (auto *VT = dyn_cast<llvm::VectorType>(Arg->getType()))
+      LargestVectorWidth = std::max(LargestVectorWidth,
+                                    VT->getPrimitiveSizeInBits());
+
     ArgTypes.push_back(Arg->getType());
     Args.push_back(Arg);
     Constraints += InputConstraint;
diff --git a/clang/test/CodeGen/x86-inline-asm-min-vector-width.c b/clang/test/CodeGen/x86-inline-asm-min-vector-width.c
new file mode 100644
index 000000000000..8d08ca0c6f9a
--- /dev/null
+++ b/clang/test/CodeGen/x86-inline-asm-min-vector-width.c
@@ -0,0 +1,45 @@
+// RUN: %clang_cc1 %s -triple x86_64-unknown-linux-gnu -emit-llvm -target-feature +avx512f -o - | FileCheck %s
+
+typedef long long __m128i __attribute__ ((vector_size (16)));
+typedef long long __m256i __attribute__ ((vector_size (32)));
+typedef long long __m512i __attribute__ ((vector_size (64)));
+
+// CHECK: define <2 x i64> @testXMMout(<2 x i64>* %p) #0
+__m128i testXMMout(__m128i *p) {
+  __m128i xmm0;
+  __asm__("vmovdqu %1, %0" :"=v"(xmm0) : "m"(*(__m128i*)p));
+  return xmm0;
+}
+
+// CHECK: define <4 x i64> @testYMMout(<4 x i64>* %p) #1
+__m256i testYMMout(__m256i *p) {
+  __m256i ymm0;
+  __asm__("vmovdqu %1, %0" :"=v"(ymm0) : "m"(*(__m256i*)p));
+  return ymm0;
+}
+
+// CHECK: define <8 x i64> @testZMMout(<8 x i64>* %p) #2
+__m512i testZMMout(__m512i *p) {
+  __m512i zmm0;
+  __asm__("vmovdqu64 %1, %0" :"=v"(zmm0) : "m"(*(__m512i*)p));
+  return zmm0;
+}
+
+// CHECK: define void @testXMMin(<2 x i64> %xmm0, <2 x i64>* %p) #0
+void testXMMin(__m128i xmm0, __m128i *p) {
+  __asm__("vmovdqu %0, %1" : : "v"(xmm0), "m"(*(__m128i*)p));
+}
+
+// CHECK: define void @testYMMin(<4 x i64> %ymm0, <4 x i64>* %p) #1
+void testYMMin(__m256i ymm0, __m256i *p) {
+  __asm__("vmovdqu %0, %1" : : "v"(ymm0), "m"(*(__m256i*)p));
+}
+
+// CHECK: define void @testZMMin(<8 x i64> %zmm0, <8 x i64>* %p) #2
+void testZMMin(__m512i zmm0, __m512i *p) {
+  __asm__("vmovdqu64 %0, %1" : : "v"(zmm0), "m"(*(__m512i*)p));
+}
+
+// CHECK: attributes #0 = {{.*}}"min-legal-vector-width"="128"
+// CHECK: attributes #1 = {{.*}}"min-legal-vector-width"="256"
+// CHECK: attributes #2 = {{.*}}"min-legal-vector-width"="512"