[llvm] [LV] Convert scatter w/uniform addr and mask being header mask to scalar store. (PR #172799)

[Elvis Wang via llvm-commits]

================
@@ -186,11 +190,18 @@ define void @store_to_addr_generated_from_invariant_addr(ptr noalias %p0, ptr no
 ; CHECK-NEXT:    call void @llvm.vp.scatter.nxv2p0.nxv2p0(<vscale x 2 x ptr> [[BROADCAST_SPLAT1]], <vscale x 2 x ptr> align 8 [[TMP5]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP3]])
 ; CHECK-NEXT:    [[TMP6:%.*]] = load i64, ptr [[P2:%.*]], align 4
 ; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr i8, ptr [[P3:%.*]], i64 [[TMP6]]
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT3:%.*]] = insertelement <vscale x 2 x ptr> poison, ptr [[TMP8]], i64 0
-; CHECK-NEXT:    [[TMP7:%.*]] = shufflevector <vscale x 2 x ptr> [[BROADCAST_SPLATINSERT3]], <vscale x 2 x ptr> poison, <vscale x 2 x i32> zeroinitializer
-; CHECK-NEXT:    call void @llvm.vp.scatter.nxv2i32.nxv2p0(<vscale x 2 x i32> zeroinitializer, <vscale x 2 x ptr> align 4 [[TMP7]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP3]])
-; CHECK-NEXT:    call void @llvm.vp.scatter.nxv2i32.nxv2p0(<vscale x 2 x i32> zeroinitializer, <vscale x 2 x ptr> align 4 [[TMP7]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP3]])
-; CHECK-NEXT:    call void @llvm.vp.scatter.nxv2i8.nxv2p0(<vscale x 2 x i8> zeroinitializer, <vscale x 2 x ptr> align 1 [[TMP7]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP3]])
+; CHECK-NEXT:    [[TMP17:%.*]] = sub i64 [[TMP4]], 1
+; CHECK-NEXT:    [[TMP18:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP10:%.*]] = mul nuw i64 [[TMP18]], 2
+; CHECK-NEXT:    [[TMP11:%.*]] = mul i64 [[TMP10]], 0
+; CHECK-NEXT:    [[TMP12:%.*]] = extractelement <vscale x 2 x i32> zeroinitializer, i64 [[TMP17]]
+; CHECK-NEXT:    store i32 [[TMP12]], ptr [[TMP8]], align 4
+; CHECK-NEXT:    store i32 [[TMP12]], ptr [[TMP8]], align 4
----------------
ElvisWang123 wrote:

Sure, will do this in follow up patch.

https://github.com/llvm/llvm-project/pull/172799