diff --git a/llvm/lib/Target/AMDGPU/DSInstructions.td b/llvm/lib/Target/AMDGPU/DSInstructions.td
--- a/llvm/lib/Target/AMDGPU/DSInstructions.td
+++ b/llvm/lib/Target/AMDGPU/DSInstructions.td
@@ -713,38 +713,6 @@
 defm : DSReadPat_mc <DS_READ_B32, i32, "atomic_load_32_local">;
 defm : DSReadPat_mc <DS_READ_B64, i64, "atomic_load_64_local">;
 
-let AddedComplexity = 100 in {
-
-foreach vt = VReg_64.RegTypes in {
-defm : DSReadPat_mc <DS_READ_B64, vt, "load_align8_local">;
-}
-
-let SubtargetPredicate = isGFX7Plus in {
-
-foreach vt = VReg_96.RegTypes in {
-defm : DSReadPat_mc <DS_READ_B96, vt, "load_align16_local">;
-}
-
-foreach vt = VReg_128.RegTypes in {
-defm : DSReadPat_mc <DS_READ_B128, vt, "load_align16_local">;
-}
-
-let SubtargetPredicate = HasUnalignedAccessMode in {
-
-foreach vt = VReg_96.RegTypes in {
-defm : DSReadPat_mc <DS_READ_B96, vt, "load_local">;
-}
-
-foreach vt = VReg_128.RegTypes in {
-defm : DSReadPat_mc <DS_READ_B128, vt, "load_local">;
-}
-
-} // End SubtargetPredicate = HasUnalignedAccessMode
-
-} // End SubtargetPredicate = isGFX7Plus
-
-} // End AddedComplexity = 100
-
 let OtherPredicates = [D16PreservesUnusedBits] in {
 def : DSReadPat_D16<DS_READ_U16_D16_HI, load_d16_hi_local, v2i16>;
 def : DSReadPat_D16<DS_READ_U16_D16_HI, load_d16_hi_local, v2f16>;
@@ -870,6 +838,10 @@
 
 let AddedComplexity = 100 in {
 
+foreach vt = VReg_64.RegTypes in {
+defm : DSReadPat_mc <DS_READ_B64, vt, "load_align8_local">;
+}
+
 foreach vt = VReg_64.RegTypes in {
 defm : DSWritePat_mc <DS_WRITE_B64, vt, "store_align8_local">;
 }
@@ -877,24 +849,20 @@
 let SubtargetPredicate = isGFX7Plus in {
 
 foreach vt = VReg_96.RegTypes in {
-defm : DSWritePat_mc <DS_WRITE_B96, vt, "store_align16_local">;
-}
-
-foreach vt = VReg_128.RegTypes in {
-defm : DSWritePat_mc <DS_WRITE_B128, vt, "store_align16_local">;
+defm : DSReadPat_mc <DS_READ_B96, vt, "load_align16_local">;
 }
 
-let SubtargetPredicate = HasUnalignedAccessMode in {
-
 foreach vt = VReg_96.RegTypes in {
-defm : DSWritePat_mc <DS_WRITE_B96, vt, "store_local">;
+defm : DSWritePat_mc <DS_WRITE_B96, vt, "store_align16_local">;
 }
 
 foreach vt = VReg_128.RegTypes in {
-defm : DSWritePat_mc <DS_WRITE_B128, vt, "store_local">;
+defm : DSReadPat_mc <DS_READ_B128, vt, "load_align16_local">;
 }
 
-} // End SubtargetPredicate = HasUnalignedAccessMode
+foreach vt = VReg_128.RegTypes in {
+defm : DSWritePat_mc <DS_WRITE_B128, vt, "store_align16_local">;
+}
 
 } // End SubtargetPredicate = isGFX7Plus
 
diff --git a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
--- a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
@@ -1431,10 +1431,8 @@
       return Aligned;
     }
     if (Size == 128) {
-      // ds_read/write_b128 require 16-byte alignment on gfx8 and older, but we
-      // can do a 8 byte aligned, 16 byte access in a single operation using
-      // ds_read2/write2_b64.
-      bool Aligned = Alignment >= Align(8);
+      // ds_read/write_b128 require 16-byte alignment on gfx8 and older.
+      bool Aligned = Alignment >= Align(16);
       if (IsFast)
         *IsFast = Aligned;