[AArch64] Create proper memoperand for multi-vector stores

Include all of the store's source vector operands when creating the
MachineMemOperand. Previously, we were missing the first operand,
making the store size seem smaller than it really is.

Differential Revision: https://reviews.llvm.org/D52816

llvm-svn: 345315

2 files changed, 165 insertions, 1 deletions

diff --git a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
index a7a1b0a5feb..2a42d2db75d 100644
--- a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -7972,7 +7972,7 @@ bool AArch64TargetLowering::getTgtMemIntrinsic(IntrinsicInfo &Info,
     Info.opc = ISD::INTRINSIC_VOID;
     // Conservatively set memVT to the entire set of vectors stored.
     unsigned NumElts = 0;
-    for (unsigned ArgI = 1, ArgE = I.getNumArgOperands(); ArgI < ArgE; ++ArgI) {
+    for (unsigned ArgI = 0, ArgE = I.getNumArgOperands(); ArgI < ArgE; ++ArgI) {
       Type *ArgTy = I.getArgOperand(ArgI)->getType();
       if (!ArgTy->isVectorTy())
         break;
diff --git a/llvm/test/CodeGen/AArch64/multi-vector-store-size.ll b/llvm/test/CodeGen/AArch64/multi-vector-store-size.ll
new file mode 100644
index 00000000000..9627556168a
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/multi-vector-store-size.ll
@@ -0,0 +1,164 @@
+; RUN: llc -mtriple=aarch64-linux-gnu -stop-after=isel < %s | FileCheck %s
+
+declare void @llvm.aarch64.neon.st2.v4f32.p0f32(<4 x float>, <4 x float>, float*)
+declare void @llvm.aarch64.neon.st3.v4f32.p0f32(<4 x float>, <4 x float>, <4 x float>, float*)
+declare void @llvm.aarch64.neon.st4.v4f32.p0f32(<4 x float>, <4 x float>, <4 x float>, <4 x float>, float*)
+
+declare void @llvm.aarch64.neon.st1x2.v4f32.p0f32(<4 x float>, <4 x float>, float*)
+declare void @llvm.aarch64.neon.st1x3.v4f32.p0f32(<4 x float>, <4 x float>, <4 x float>, float*)
+declare void @llvm.aarch64.neon.st1x4.v4f32.p0f32(<4 x float>, <4 x float>, <4 x float>, <4 x float>, float*)
+
+declare void @llvm.aarch64.neon.st2lane.v4f32.p0f32(<4 x float>, <4 x float>, i64, float*)
+declare void @llvm.aarch64.neon.st3lane.v4f32.p0f32(<4 x float>, <4 x float>, <4 x float>, i64, float*)
+declare void @llvm.aarch64.neon.st4lane.v4f32.p0f32(<4 x float>, <4 x float>, <4 x float>, <4 x float>, i64, float*)
+
+define void @addstx(float* %res, <4 x float>* %a,  <4 x float>* %b, <4 x float>* %c, <4 x float>* %d) {
+  %al = load <4 x float>, <4 x float>* %a
+  %bl = load <4 x float>, <4 x float>* %b
+  %cl = load <4 x float>, <4 x float>* %c
+  %dl = load <4 x float>, <4 x float>* %d
+
+  %ar = fadd <4 x float> %al, %bl
+  %br = fadd <4 x float> %bl, %cl
+  %cr = fadd <4 x float> %cl, %dl
+  %dr = fadd <4 x float> %dl, %al
+
+; The sizes below are conservative.  AArch64TargetLowering
+; conservatively assumes the entire vector is stored.
+  tail call void @llvm.aarch64.neon.st2.v4f32.p0f32(<4 x float> %ar, <4 x float> %br, float* %res)
+; CHECK: ST2Twov4s {{.*}} :: (store 32 {{.*}})
+  tail call void @llvm.aarch64.neon.st3.v4f32.p0f32(<4 x float> %ar, <4 x float> %br, <4 x float> %cr, float* %res)
+; CHECK: ST3Threev4s {{.*}} :: (store 48 {{.*}})
+  tail call void @llvm.aarch64.neon.st4.v4f32.p0f32(<4 x float> %ar, <4 x float> %br, <4 x float> %cr, <4 x float> %dr, float* %res)
+; CHECK: ST4Fourv4s {{.*}} :: (store 64 {{.*}})
+
+  ret void
+}
+
+define void @addst1x(float* %res, <4 x float>* %a,  <4 x float>* %b, <4 x float>* %c, <4 x float>* %d) {
+  %al = load <4 x float>, <4 x float>* %a
+  %bl = load <4 x float>, <4 x float>* %b
+  %cl = load <4 x float>, <4 x float>* %c
+  %dl = load <4 x float>, <4 x float>* %d
+
+  %ar = fadd <4 x float> %al, %bl
+  %br = fadd <4 x float> %bl, %cl
+  %cr = fadd <4 x float> %cl, %dl
+  %dr = fadd <4 x float> %dl, %al
+
+; The sizes below are conservative.  AArch64TargetLowering
+; conservatively assumes the entire vector is stored.
+  tail call void @llvm.aarch64.neon.st1x2.v4f32.p0f32(<4 x float> %ar, <4 x float> %br, float* %res)
+; CHECK: ST1Twov4s {{.*}} :: (store 32 {{.*}})
+  tail call void @llvm.aarch64.neon.st1x3.v4f32.p0f32(<4 x float> %ar, <4 x float> %br, <4 x float> %cr, float* %res)
+; CHECK: ST1Threev4s {{.*}} :: (store 48 {{.*}})
+  tail call void @llvm.aarch64.neon.st1x4.v4f32.p0f32(<4 x float> %ar, <4 x float> %br, <4 x float> %cr, <4 x float> %dr, float* %res)
+; CHECK: ST1Fourv4s {{.*}} :: (store 64 {{.*}})
+
+  ret void
+}
+
+define void @addstxlane(float* %res, <4 x float>* %a,  <4 x float>* %b, <4 x float>* %c, <4 x float>* %d) {
+  %al = load <4 x float>, <4 x float>* %a
+  %bl = load <4 x float>, <4 x float>* %b
+  %cl = load <4 x float>, <4 x float>* %c
+  %dl = load <4 x float>, <4 x float>* %d
+
+  %ar = fadd <4 x float> %al, %bl
+  %br = fadd <4 x float> %bl, %cl
+  %cr = fadd <4 x float> %cl, %dl
+  %dr = fadd <4 x float> %dl, %al
+
+; The sizes below are conservative.  AArch64TargetLowering
+; conservatively assumes the entire vector is stored.
+  tail call void @llvm.aarch64.neon.st2lane.v4f32.p0f32(<4 x float> %ar, <4 x float> %br, i64 1, float* %res)
+; CHECK: ST2i32 {{.*}} :: (store 32 {{.*}})
+  tail call void @llvm.aarch64.neon.st3lane.v4f32.p0f32(<4 x float> %ar, <4 x float> %br, <4 x float> %cr, i64 1, float* %res)
+; CHECK: ST3i32 {{.*}} :: (store 48 {{.*}})
+  tail call void @llvm.aarch64.neon.st4lane.v4f32.p0f32(<4 x float> %ar, <4 x float> %br, <4 x float> %cr, <4 x float> %dr, i64 1, float* %res)
+; CHECK: ST4i32 {{.*}} :: (store 64 {{.*}})
+
+  ret void
+}
+; RUN: llc -mtriple=aarch64-linux-gnu -stop-after=isel < %s | FileCheck %s
+
+declare void @llvm.aarch64.neon.st2.v4f32.p0f32(<4 x float>, <4 x float>, float*)
+declare void @llvm.aarch64.neon.st3.v4f32.p0f32(<4 x float>, <4 x float>, <4 x float>, float*)
+declare void @llvm.aarch64.neon.st4.v4f32.p0f32(<4 x float>, <4 x float>, <4 x float>, <4 x float>, float*)
+
+declare void @llvm.aarch64.neon.st1x2.v4f32.p0f32(<4 x float>, <4 x float>, float*)
+declare void @llvm.aarch64.neon.st1x3.v4f32.p0f32(<4 x float>, <4 x float>, <4 x float>, float*)
+declare void @llvm.aarch64.neon.st1x4.v4f32.p0f32(<4 x float>, <4 x float>, <4 x float>, <4 x float>, float*)
+
+declare void @llvm.aarch64.neon.st2lane.v4f32.p0f32(<4 x float>, <4 x float>, i64, float*)
+declare void @llvm.aarch64.neon.st3lane.v4f32.p0f32(<4 x float>, <4 x float>, <4 x float>, i64, float*)
+declare void @llvm.aarch64.neon.st4lane.v4f32.p0f32(<4 x float>, <4 x float>, <4 x float>, <4 x float>, i64, float*)
+
+define void @addstx(float* %res, <4 x float>* %a,  <4 x float>* %b, <4 x float>* %c, <4 x float>* %d) {
+  %al = load <4 x float>, <4 x float>* %a
+  %bl = load <4 x float>, <4 x float>* %b
+  %cl = load <4 x float>, <4 x float>* %c
+  %dl = load <4 x float>, <4 x float>* %d
+
+  %ar = fadd <4 x float> %al, %bl
+  %br = fadd <4 x float> %bl, %cl
+  %cr = fadd <4 x float> %cl, %dl
+  %dr = fadd <4 x float> %dl, %al
+
+; The sizes below are conservative.  AArch64TargetLowering
+; conservatively assumes the entiew vector is stored.
+  tail call void @llvm.aarch64.neon.st2.v4f32.p0f32(<4 x float> %ar, <4 x float> %br, float* %res)
+; CHECK: ST2Twov4s {{.*}} :: (store 32 {{.*}})
+  tail call void @llvm.aarch64.neon.st3.v4f32.p0f32(<4 x float> %ar, <4 x float> %br, <4 x float> %cr, float* %res)
+; CHECK: ST3Threev4s {{.*}} :: (store 48 {{.*}})
+  tail call void @llvm.aarch64.neon.st4.v4f32.p0f32(<4 x float> %ar, <4 x float> %br, <4 x float> %cr, <4 x float> %dr, float* %res)
+; CHECK: ST4Fourv4s {{.*}} :: (store 64 {{.*}})
+
+  ret void
+}
+
+define void @addst1x(float* %res, <4 x float>* %a,  <4 x float>* %b, <4 x float>* %c, <4 x float>* %d) {
+  %al = load <4 x float>, <4 x float>* %a
+  %bl = load <4 x float>, <4 x float>* %b
+  %cl = load <4 x float>, <4 x float>* %c
+  %dl = load <4 x float>, <4 x float>* %d
+
+  %ar = fadd <4 x float> %al, %bl
+  %br = fadd <4 x float> %bl, %cl
+  %cr = fadd <4 x float> %cl, %dl
+  %dr = fadd <4 x float> %dl, %al
+
+; The sizes below are conservative.  AArch64TargetLowering
+; conservatively assumes the entiew vector is stored.
+  tail call void @llvm.aarch64.neon.st1x2.v4f32.p0f32(<4 x float> %ar, <4 x float> %br, float* %res)
+; CHECK: ST1Twov4s {{.*}} :: (store 32 {{.*}})
+  tail call void @llvm.aarch64.neon.st1x3.v4f32.p0f32(<4 x float> %ar, <4 x float> %br, <4 x float> %cr, float* %res)
+; CHECK: ST1Threev4s {{.*}} :: (store 48 {{.*}})
+  tail call void @llvm.aarch64.neon.st1x4.v4f32.p0f32(<4 x float> %ar, <4 x float> %br, <4 x float> %cr, <4 x float> %dr, float* %res)
+; CHECK: ST1Fourv4s {{.*}} :: (store 64 {{.*}})
+
+  ret void
+}
+
+define void @addstxlane(float* %res, <4 x float>* %a,  <4 x float>* %b, <4 x float>* %c, <4 x float>* %d) {
+  %al = load <4 x float>, <4 x float>* %a
+  %bl = load <4 x float>, <4 x float>* %b
+  %cl = load <4 x float>, <4 x float>* %c
+  %dl = load <4 x float>, <4 x float>* %d
+
+  %ar = fadd <4 x float> %al, %bl
+  %br = fadd <4 x float> %bl, %cl
+  %cr = fadd <4 x float> %cl, %dl
+  %dr = fadd <4 x float> %dl, %al
+
+; The sizes below are conservative.  AArch64TargetLowering
+; conservatively assumes the entiew vector is stored.
+  tail call void @llvm.aarch64.neon.st2lane.v4f32.p0f32(<4 x float> %ar, <4 x float> %br, i64 1, float* %res)
+; CHECK: ST2i32 {{.*}} :: (store 32 {{.*}})
+  tail call void @llvm.aarch64.neon.st3lane.v4f32.p0f32(<4 x float> %ar, <4 x float> %br, <4 x float> %cr, i64 1, float* %res)
+; CHECK: ST3i32 {{.*}} :: (store 48 {{.*}})
+  tail call void @llvm.aarch64.neon.st4lane.v4f32.p0f32(<4 x float> %ar, <4 x float> %br, <4 x float> %cr, <4 x float> %dr, i64 1, float* %res)
+; CHECK: ST4i32 {{.*}} :: (store 64 {{.*}})
+
+  ret void
+}