[llvm] [DAG] Teach SelectionDAGBuilder to read parameter alignment of compressstore/expandload. (PR #83763)
via llvm-commits
llvm-commits at lists.llvm.org
Sun Mar 3 20:58:37 PST 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-llvm-selectiondag
@llvm/pr-subscribers-backend-x86
Author: Yeting Kuo (yetingk)
<details>
<summary>Changes</summary>
Previously SelectionDAGBuilder used ABI alignment for compressstore/expandload. This patch allows SelectionDAGBuilder to use parameter alignment like vp intrinsics and stills uses ABI alignment for them when they don't have alignment attriubtes.
---
Full diff: https://github.com/llvm/llvm-project/pull/83763.diff
3 Files Affected:
- (modified) llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp (+4)
- (modified) llvm/test/CodeGen/X86/masked_compressstore_isel.ll (+17-1)
- (added) llvm/test/CodeGen/X86/masked_expandload_isel.ll (+33)
``````````diff
diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
index ab2f42d2024ccc..39628f4fb3689d 100644
--- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
@@ -4582,6 +4582,8 @@ void SelectionDAGBuilder::visitMaskedStore(const CallInst &I,
Ptr = I.getArgOperand(1);
Mask = I.getArgOperand(2);
Alignment = std::nullopt;
+ if (MaybeAlign Align = I.getParamAlign(1))
+ Alignment = Align;
};
Value *PtrOperand, *MaskOperand, *Src0Operand;
@@ -4746,6 +4748,8 @@ void SelectionDAGBuilder::visitMaskedLoad(const CallInst &I, bool IsExpanding) {
// @llvm.masked.expandload.*(Ptr, Mask, Src0)
Ptr = I.getArgOperand(0);
Alignment = std::nullopt;
+ if (MaybeAlign Align = I.getParamAlign(0))
+ Alignment = Align;
Mask = I.getArgOperand(1);
Src0 = I.getArgOperand(2);
};
diff --git a/llvm/test/CodeGen/X86/masked_compressstore_isel.ll b/llvm/test/CodeGen/X86/masked_compressstore_isel.ll
index 1851a21c8c0641..b5857b22382da0 100644
--- a/llvm/test/CodeGen/X86/masked_compressstore_isel.ll
+++ b/llvm/test/CodeGen/X86/masked_compressstore_isel.ll
@@ -7,7 +7,7 @@ entry:
ret void
}
-; CHECK-LABEL: bb.0.entry:
+; CHECK-LABEL: name: _Z3fooiPiPs
; CHECK: %1:vr128x = COPY $xmm1
; CHECK-NEXT: %0:vr256x = COPY $ymm0
; CHECK-NEXT: %2:vr128x = VPSLLWZ128ri %1, 15
@@ -16,6 +16,22 @@ entry:
; CHECK-NEXT: VPCOMPRESSWZ128mrk $noreg, 1, $noreg, 0, $noreg, killed %3, killed %4 :: (store unknown-size into `ptr null`, align 16)
; CHECK-NEXT: RET 0
+define void @_Z3foo2iPiPs(<8 x i32> %gepload, <8 x i1> %0) #0 {
+entry:
+ %1 = trunc <8 x i32> %gepload to <8 x i16>
+ tail call void @llvm.masked.compressstore.v8i16(<8 x i16> %1, ptr align 32 null, <8 x i1> %0)
+ ret void
+}
+
+; CHECK-LABEL: name: _Z3foo2iPiPs
+; CHECK: %1:vr128x = COPY $xmm1
+; CHECK-NEXT: %0:vr256x = COPY $ymm0
+; CHECK-NEXT: %2:vr128x = VPSLLWZ128ri %1, 15
+; CHECK-NEXT: %3:vk16wm = VPMOVW2MZ128rr killed %2
+; CHECK-NEXT: %4:vr128x = VPMOVDWZ256rr %0
+; CHECK-NEXT: VPCOMPRESSWZ128mrk $noreg, 1, $noreg, 0, $noreg, killed %3, killed %4 :: (store unknown-size into `ptr null`, align 32)
+; CHECK-NEXT: RET 0
+
; Function Attrs: nocallback nofree nosync nounwind willreturn memory(argmem: write)
declare void @llvm.masked.compressstore.v8i16(<8 x i16>, ptr nocapture, <8 x i1>) #1
diff --git a/llvm/test/CodeGen/X86/masked_expandload_isel.ll b/llvm/test/CodeGen/X86/masked_expandload_isel.ll
new file mode 100644
index 00000000000000..7f20e03d343cdb
--- /dev/null
+++ b/llvm/test/CodeGen/X86/masked_expandload_isel.ll
@@ -0,0 +1,33 @@
+; RUN: llc < %s -mtriple=x86_64-unknown-linux-gnu -start-after=codegenprepare -stop-before finalize-isel | FileCheck %s
+
+define <8 x i16> @_Z3fooiPiPs(<8 x i16> %src, <8 x i1> %0) #0 {
+entry:
+ %res = call <8 x i16> @llvm.masked.expandload.v8i16(ptr null, <8 x i1> %0, <8 x i16> %src)
+ ret <8 x i16> %res
+}
+
+; CHECK-LABEL: name: _Z3fooiPiPs
+; CHECK: %1:vr128x = COPY $xmm1
+; CHECK-NEXT: %0:vr128x = COPY $xmm0
+; CHECK-NEXT: %2:vr128x = VPSLLWZ128ri %1, 15
+; CHECK-NEXT: %3:vk16wm = VPMOVW2MZ128rr killed %2
+; CHECK-NEXT: %4:vr128x = VPEXPANDWZ128rmk %0, killed %3, $noreg, 1, $noreg, 0, $noreg :: (load unknown-size from `ptr null`, align 16)
+
+define <8 x i16> @_Z3foo2iPiPs(<8 x i16> %src, <8 x i1> %0) #0 {
+entry:
+ %res = call <8 x i16> @llvm.masked.expandload.v8i16(ptr align 32 null, <8 x i1> %0, <8 x i16> %src)
+ ret <8 x i16> %res
+}
+
+; CHECK-LABEL: name: _Z3foo2iPiPs
+; CHECK: %1:vr128x = COPY $xmm1
+; CHECK-NEXT: %0:vr128x = COPY $xmm0
+; CHECK-NEXT: %2:vr128x = VPSLLWZ128ri %1, 15
+; CHECK-NEXT: %3:vk16wm = VPMOVW2MZ128rr killed %2
+; CHECK-NEXT: %4:vr128x = VPEXPANDWZ128rmk %0, killed %3, $noreg, 1, $noreg, 0, $noreg :: (load unknown-size from `ptr null`, align 32)
+
+; Function Attrs: nocallback nofree nosync nounwind willreturn memory(argmem: write)
+declare <8 x i16> @llvm.masked.expandload.v8i16(ptr, <8 x i1>, <8 x i16>)
+
+attributes #0 = { "target-cpu"="icelake-server" }
+attributes #1 = { nocallback nofree nosync nounwind willreturn memory(argmem: write) }
``````````
</details>
https://github.com/llvm/llvm-project/pull/83763
More information about the llvm-commits
mailing list