[AMDGPU] Emit separate v_mov_b32s if v_mov_b64_pseudo destination vgprs are misaligned

Author: JanekvO

llvm/lib/Target/AMDGPU/SIInstrInfo.cpp

@@ -2149,7 +2149,9 @@ bool SIInstrInfo::expandPostRAPseudo(MachineInstr &MI) const {
     const MachineOperand &SrcOp = MI.getOperand(1);
     // FIXME: Will this work for 64-bit floating point immediates?
     assert(!SrcOp.isFPImm());
-    if (ST.hasMovB64()) {
+    MachineRegisterInfo &MRI = MI.getMF()->getRegInfo();
+    const TargetRegisterClass *RC = RI.getRegClassForReg(MRI, Dst);
+    if (ST.hasMovB64() && RI.isProperlyAlignedRC(*RC)) {
       MI.setDesc(get(AMDGPU::V_MOV_B64_e32));
       if (SrcOp.isReg() || isInlineConstant(MI, 1) ||
           isUInt<32>(SrcOp.getImm()) || ST.has64BitLiterals())
@@ -2159,7 +2161,8 @@ bool SIInstrInfo::expandPostRAPseudo(MachineInstr &MI) const {
       APInt Imm(64, SrcOp.getImm());
       APInt Lo(32, Imm.getLoBits(32).getZExtValue());
       APInt Hi(32, Imm.getHiBits(32).getZExtValue());
-      if (ST.hasPkMovB32() && Lo == Hi && isInlineConstant(Lo)) {
+      if (ST.hasPkMovB32() && Lo == Hi && isInlineConstant(Lo) &&
+          RI.isProperlyAlignedRC(*RC)) {
         BuildMI(MBB, MI, DL, get(AMDGPU::V_PK_MOV_B32), Dst)
           .addImm(SISrcMods::OP_SEL_1)
           .addImm(Lo.getSExtValue())

llvm/test/CodeGen/AMDGPU/misaligned-vgpr-regsequence.mir

@@ -0,0 +1,33 @@
+# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx942 -start-after=si-load-store-opt %s -o - | FileCheck %s
+
+# CHECK: "misaligned-regsequence":
+# CHECK: ; %bb.0:
+# CHECK:         s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+# CHECK:         s_load_dwordx2 s[0:1], s[4:5], 0x0
+# CHECK:         v_mov_b32_e32 v5, 0
+# CHECK:         v_mov_b32_e32 v4, 0
+# CHECK:         v_mov_b32_e32 v6, 0
+# CHECK:         s_waitcnt lgkmcnt(0)
+# CHECK:         v_mov_b64_e32 v[2:3], s[0:1]
+# CHECK:         flat_store_dwordx3 v[2:3], v[4:6]
+# CHECK:         s_endpgm
+
+--- |
+  define void @misaligned-regsequence() { ret void }
+...
+---
+name: misaligned-regsequence
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $sgpr4_sgpr5
+
+    %3:sgpr_64(p4) = COPY $sgpr4_sgpr5
+    %8:sreg_64_xexec = S_LOAD_DWORDX2_IMM %3:sgpr_64(p4), 0, 0 :: (dereferenceable invariant load (s64), align 16, addrspace 4)
+    %9:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
+    %10:vreg_64_align2 = COPY %8:sreg_64_xexec
+    %11:vreg_64_align2 = V_MOV_B64_PSEUDO 0, implicit $exec
+    %13:vreg_96_align2 = REG_SEQUENCE killed %9:vgpr_32, %subreg.sub0, killed %11:vreg_64_align2, %subreg.sub1_sub2
+    FLAT_STORE_DWORDX3 %10:vreg_64_align2, killed %13:vreg_96_align2, 0, 0, implicit $exec, implicit $flat_scr :: (store (s96) into `ptr addrspace(1) undef`, align 4)
+    S_ENDPGM 0
+...

llvm/test/CodeGen/AMDGPU/vgpr-mov64-align.mir

@@ -0,0 +1,31 @@
+# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx942 -start-before=postrapseudos %s -o - | FileCheck %s
+
+# CHECK: v_mov_b64_misalign:
+# CHECK: ; %bb.0:
+# CHECK:         s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+# CHECK:         s_load_dwordx2 s[0:1], s[4:5], 0x0
+# CHECK:         v_mov_b32_e32 v5, 0
+# CHECK:         v_mov_b32_e32 v4, 0
+# CHECK:         v_mov_b32_e32 v6, 0
+# CHECK:         s_waitcnt lgkmcnt(0)
+# CHECK:         v_mov_b64_e32 v[2:3], s[0:1]
+# CHECK:         flat_store_dwordx3 v[2:3], v[4:6]
+# CHECK:         s_endpgm
+
+---
+name:            v_mov_b64_misalign
+tracksRegLiveness: true
+body:             |
+  bb.0.entry:
+    liveins: $sgpr4_sgpr5
+  
+    frame-setup CFI_INSTRUCTION escape 0x0f, 0x04, 0x30, 0x36, 0xe9, 0x02
+    frame-setup CFI_INSTRUCTION undefined $pc_reg
+    renamable $sgpr0_sgpr1 = S_LOAD_DWORDX2_IMM killed renamable $sgpr4_sgpr5, 0, 0 :: (dereferenceable invariant load (s64), align 16, addrspace 4)
+    renamable $vgpr4 = AV_MOV_B32_IMM_PSEUDO 0, implicit $exec
+    renamable $vgpr5_vgpr6 = AV_MOV_B64_IMM_PSEUDO 0, implicit $exec
+    renamable $vgpr2_vgpr3 = COPY killed renamable $sgpr0_sgpr1, implicit $exec
+    FLAT_STORE_DWORDX3 killed renamable $vgpr2_vgpr3, killed renamable $vgpr4_vgpr5_vgpr6, 0, 0, implicit $exec, implicit $flat_scr :: (store (s96) into `ptr addrspace(1) undef`, align 4)
+    S_ENDPGM 0
+...
+