From 678cf3a36644847cac4b0be2d919aba77416088a Mon Sep 17 00:00:00 2001
From: Nikita Popov <npopov@redhat.com>
Date: Mon, 04 Mar 2024 07:00:37 +0800
Subject: [PATCH] [Backport][X86][Inline] Skip inline asm in inlining target
 feature check

When inlining across functions with different target features, we
perform roughly two checks:
1. The caller features must be a superset of the callee features.
2. Calls in the callee cannot use types where the target features would
change the call ABI (e.g. by changing whether something is passed in a
zmm or two ymm registers). The latter check is very crude right now.

The latter check currently also catches inline asm "calls". I believe
that inline asm should be excluded from this check, as it is independent
from the usual call ABI, and instead governed by the inline asm
constraint string.
---
 .../lib/Target/X86/X86TargetTransformInfo.cpp |  4 +++
 .../Inline/X86/call-abi-compatibility.ll      | 26 +++++++++++++++++++
 2 files changed, 30 insertions(+)

diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
index 129a2646d..9c7954230 100644
--- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -6046,6 +6046,10 @@ bool X86TTIImpl::areInlineCompatible(const Function *Caller,
 
   for (const Instruction &I : instructions(Callee)) {
     if (const auto *CB = dyn_cast<CallBase>(&I)) {
+      // Having more target features is fine for inline ASM.
+      if (CB->isInlineAsm())
+        continue;
+
       SmallVector<Type *, 8> Types;
       for (Value *Arg : CB->args())
         Types.push_back(Arg->getType());
diff --git a/llvm/test/Transforms/Inline/X86/call-abi-compatibility.ll b/llvm/test/Transforms/Inline/X86/call-abi-compatibility.ll
index 3a30980fe..6f582cab2 100644
--- a/llvm/test/Transforms/Inline/X86/call-abi-compatibility.ll
+++ b/llvm/test/Transforms/Inline/X86/call-abi-compatibility.ll
@@ -93,3 +93,29 @@ define internal void @caller_not_avx4() {
 }
 
 declare i64 @caller_unknown_simple(i64)
+
+; This call should get inlined, because the callee only contains
+; inline ASM, not real calls.
+define <8 x i64> @caller_inline_asm(ptr %p0, i64 %k, ptr %p1, ptr %p2) #0 {
+; CHECK-LABEL: define {{[^@]+}}@caller_inline_asm
+; CHECK-SAME: (ptr [[P0:%.*]], i64 [[K:%.*]], ptr [[P1:%.*]], ptr [[P2:%.*]]) #[[ATTR2:[0-9]+]] {
+; CHECK-NEXT:    [[SRC_I:%.*]] = load <8 x i64>, ptr [[P0]], align 64
+; CHECK-NEXT:    [[A_I:%.*]] = load <8 x i64>, ptr [[P1]], align 64
+; CHECK-NEXT:    [[B_I:%.*]] = load <8 x i64>, ptr [[P2]], align 64
+; CHECK-NEXT:    [[TMP1:%.*]] = call <8 x i64> asm "vpaddb\09$($3, $2, $0 {$1}", "=v,^Yk,v,v,0,~{dirflag},~{fpsr},~{flags}"(i64 [[K]], <8 x i64> [[A_I]], <8 x i64> [[B_I]], <8 x i64> [[SRC_I]])
+; CHECK-NEXT:    ret <8 x i64> [[TMP1]]
+;
+  %call = call <8 x i64> @callee_inline_asm(ptr %p0, i64 %k, ptr %p1, ptr %p2)
+  ret <8 x i64> %call
+}
+
+define internal <8 x i64> @callee_inline_asm(ptr %p0, i64 %k, ptr %p1, ptr %p2) #1 {
+  %src = load <8 x i64>, ptr %p0, align 64
+  %a = load <8 x i64>, ptr %p1, align 64
+  %b = load <8 x i64>, ptr %p2, align 64
+  %1 = tail call <8 x i64> asm "vpaddb\09$($3, $2, $0 {$1}", "=v,^Yk,v,v,0,~{dirflag},~{fpsr},~{flags}"(i64 %k, <8 x i64> %a, <8 x i64> %b, <8 x i64> %src) #2
+  ret <8 x i64> %1
+}
+
+attributes #0 = { "min-legal-vector-width"="512" "target-features"="+avx,+avx2,+avx512bw,+avx512dq,+avx512f,+cmov,+crc32,+cx8,+evex512,+f16c,+fma,+fxsr,+mmx,+popcnt,+sse,+sse2,+sse3,+sse4.1,+sse4.2,+ssse3,+x87,+xsave" "tune-cpu"="generic" }
+attributes #1 = { "min-legal-vector-width"="512" "target-features"="+avx,+avx2,+avx512bw,+avx512f,+cmov,+crc32,+cx8,+evex512,+f16c,+fma,+fxsr,+mmx,+popcnt,+sse,+sse2,+sse3,+sse4.1,+sse4.2,+ssse3,+x87,+xsave" "tune-cpu"="generic" }
-- 
2.33.0