[AMDGPU][True16][MC][CodeGen] true16 for v_alignbyte_b32 (llvm#125706)

Support true16 format for v_alignbyte_b32 in MC and CodeGen

Author: broxigarchen

llvm/lib/Target/AMDGPU/VOP3Instructions.td

@@ -212,7 +212,13 @@ defm V_BFE_U32 : VOP3Inst <"v_bfe_u32", VOP3_Profile<VOP_I32_I32_I32_I32>, AMDGP
 defm V_BFE_I32 : VOP3Inst <"v_bfe_i32", VOP3_Profile<VOP_I32_I32_I32_I32>, AMDGPUbfe_i32>;
 defm V_BFI_B32 : VOP3Inst <"v_bfi_b32", VOP3_Profile<VOP_I32_I32_I32_I32>, AMDGPUbfi>;
 defm V_ALIGNBIT_B32 : VOP3Inst <"v_alignbit_b32", VOP3_Profile<VOP_I32_I32_I32_I32>, fshr>;
+
+let True16Predicate = NotHasTrue16BitInsts in
 defm V_ALIGNBYTE_B32 : VOP3Inst <"v_alignbyte_b32", VOP3_Profile<VOP_I32_I32_I32_I32>, int_amdgcn_alignbyte>;
+let True16Predicate = UseRealTrue16Insts in
+defm V_ALIGNBYTE_B32_t16 : VOP3Inst <"v_alignbyte_b32_t16", VOP3_Profile_True16<VOP_I32_I32_I32_I16, VOP3_OPSEL>>;
+let True16Predicate = UseFakeTrue16Insts in 
+defm V_ALIGNBYTE_B32_fake16 : VOP3Inst <"v_alignbyte_b32_fake16", VOP3_Profile_Fake16<VOP_I32_I32_I32_I16, VOP3_OPSEL>>;
 
 // XXX - No FPException seems suspect but manual doesn't say it does
 let mayRaiseFPException = 0 in {
@@ -250,6 +256,25 @@ let SchedRW = [WriteDoubleAdd], FPDPRounding = 1 in {
 } // End SchedRW = [WriteDoubleAdd], FPDPRounding = 1
 } // End isReMaterializable = 1
 
+let True16Predicate = UseFakeTrue16Insts in
+def : GCNPat <
+(i32 (int_amdgcn_alignbyte (i32 (VOP3OpSelMods i32:$src0, i32:$src0_modifiers)),
+                           (i32 (VOP3OpSelMods i32:$src1, i32:$src1_modifiers)),
+                           (i32 (VOP3OpSelMods i32:$src2, i32:$src2_modifiers)))),
+(V_ALIGNBYTE_B32_fake16_e64 i32:$src0_modifiers, VSrc_b32:$src0,
+                            i32:$src1_modifiers, VSrc_b32:$src1,
+                            i32:$src2_modifiers, VGPR_32:$src2)
+>;
+
+let True16Predicate = UseRealTrue16Insts in
+def : GCNPat <
+(i32 (int_amdgcn_alignbyte (i32 (VOP3OpSelMods i32:$src0, i32:$src0_modifiers)),
+                           (i32 (VOP3OpSelMods i32:$src1, i32:$src1_modifiers)),
+                           (i32 (VOP3OpSelMods i32:$src2, i32:$src2_modifiers)))),
+(V_ALIGNBYTE_B32_t16_e64 i32:$src0_modifiers, VSrc_b32:$src0,
+                         i32:$src1_modifiers, VSrc_b32:$src1,
+                         i32:$src2_modifiers, (i16 (EXTRACT_SUBREG VGPR_32:$src2, lo16)))
+>;
 
 let mayRaiseFPException = 0 in { // Seems suspicious but manual doesn't say it does.
   let SchedRW = [WriteFloatFMA, WriteSALU] in
@@ -1690,7 +1715,7 @@ defm V_FMA_F32             : VOP3_Realtriple_gfx11_gfx12<0x213>;
 defm V_FMA_F64             : VOP3_Real_Base_gfx11_gfx12<0x214>;
 defm V_LERP_U8             : VOP3_Realtriple_gfx11_gfx12<0x215>;
 defm V_ALIGNBIT_B32        : VOP3_Realtriple_gfx11_gfx12<0x216>;
-defm V_ALIGNBYTE_B32       : VOP3_Realtriple_gfx11_gfx12<0x217>;
+defm V_ALIGNBYTE_B32       : VOP3_Realtriple_t16_and_fake16_gfx11_gfx12<0x217, "v_alignbyte_b32">;
 defm V_MULLIT_F32          : VOP3_Realtriple_gfx11_gfx12<0x218>;
 defm V_MIN3_F32            : VOP3_Realtriple_gfx11<0x219>;
 defm V_MIN3_I32            : VOP3_Realtriple_gfx11_gfx12<0x21a>;

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.alignbyte.ll

@@ -1,14 +1,128 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
 ; RUN: llc -mtriple=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
+; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+real-true16 -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX11-TRUE16 %s
+; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX11-FAKE16 %s
 
 declare i32 @llvm.amdgcn.alignbyte(i32, i32, i32) #0
 
-; GCN-LABEL: {{^}}v_alignbyte_b32:
-; GCN: v_alignbyte_b32 {{[vs][0-9]+}}, {{[vs][0-9]+}}, {{[vs][0-9]+}}
 define amdgpu_kernel void @v_alignbyte_b32(ptr addrspace(1) %out, i32 %src1, i32 %src2, i32 %src3) #1 {
+; GCN-LABEL: v_alignbyte_b32:
+; GCN:       ; %bb.0:
+; GCN-NEXT:    s_load_dwordx4 s[0:3], s[4:5], 0xb
+; GCN-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x9
+; GCN-NEXT:    s_mov_b32 s7, 0xf000
+; GCN-NEXT:    s_mov_b32 s6, -1
+; GCN-NEXT:    s_waitcnt lgkmcnt(0)
+; GCN-NEXT:    v_mov_b32_e32 v0, s1
+; GCN-NEXT:    v_mov_b32_e32 v1, s2
+; GCN-NEXT:    v_alignbyte_b32 v0, s0, v0, v1
+; GCN-NEXT:    buffer_store_dword v0, off, s[4:7], 0
+; GCN-NEXT:    s_endpgm
+;
+; GFX11-TRUE16-LABEL: v_alignbyte_b32:
+; GFX11-TRUE16:       ; %bb.0:
+; GFX11-TRUE16-NEXT:    s_clause 0x1
+; GFX11-TRUE16-NEXT:    s_load_b128 s[0:3], s[4:5], 0x2c
+; GFX11-TRUE16-NEXT:    s_load_b64 s[4:5], s[4:5], 0x24
+; GFX11-TRUE16-NEXT:    v_mov_b32_e32 v1, 0
+; GFX11-TRUE16-NEXT:    s_waitcnt lgkmcnt(0)
+; GFX11-TRUE16-NEXT:    v_mov_b16_e32 v0.l, s2
+; GFX11-TRUE16-NEXT:    s_delay_alu instid0(VALU_DEP_1)
+; GFX11-TRUE16-NEXT:    v_alignbyte_b32 v0, s0, s1, v0.l
+; GFX11-TRUE16-NEXT:    global_store_b32 v1, v0, s[4:5]
+; GFX11-TRUE16-NEXT:    s_endpgm
+;
+; GFX11-FAKE16-LABEL: v_alignbyte_b32:
+; GFX11-FAKE16:       ; %bb.0:
+; GFX11-FAKE16-NEXT:    s_clause 0x1
+; GFX11-FAKE16-NEXT:    s_load_b128 s[0:3], s[4:5], 0x2c
+; GFX11-FAKE16-NEXT:    s_load_b64 s[4:5], s[4:5], 0x24
+; GFX11-FAKE16-NEXT:    s_waitcnt lgkmcnt(0)
+; GFX11-FAKE16-NEXT:    v_dual_mov_b32 v1, 0 :: v_dual_mov_b32 v0, s2
+; GFX11-FAKE16-NEXT:    s_delay_alu instid0(VALU_DEP_1)
+; GFX11-FAKE16-NEXT:    v_alignbyte_b32 v0, s0, s1, v0
+; GFX11-FAKE16-NEXT:    global_store_b32 v1, v0, s[4:5]
+; GFX11-FAKE16-NEXT:    s_endpgm
   %val = call i32 @llvm.amdgcn.alignbyte(i32 %src1, i32 %src2, i32 %src3) #0
   store i32 %val, ptr addrspace(1) %out
   ret void
 }
 
+define amdgpu_kernel void @v_alignbyte_b32_2(ptr addrspace(1) %out, ptr addrspace(1) %src1, ptr addrspace(1) %src2, i32 %src3) #1 {
+; GCN-LABEL: v_alignbyte_b32_2:
+; GCN:       ; %bb.0:
+; GCN-NEXT:    s_load_dwordx4 s[0:3], s[4:5], 0x9
+; GCN-NEXT:    s_load_dwordx2 s[8:9], s[4:5], 0xd
+; GCN-NEXT:    s_load_dword s16, s[4:5], 0xf
+; GCN-NEXT:    s_mov_b32 s7, 0xf000
+; GCN-NEXT:    s_mov_b32 s14, 0
+; GCN-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
+; GCN-NEXT:    v_mov_b32_e32 v1, 0
+; GCN-NEXT:    s_mov_b32 s15, s7
+; GCN-NEXT:    s_mov_b64 s[10:11], s[14:15]
+; GCN-NEXT:    s_waitcnt lgkmcnt(0)
+; GCN-NEXT:    s_mov_b64 s[12:13], s[2:3]
+; GCN-NEXT:    buffer_load_dword v2, v[0:1], s[12:15], 0 addr64 glc
+; GCN-NEXT:    s_waitcnt vmcnt(0)
+; GCN-NEXT:    buffer_load_dword v0, v[0:1], s[8:11], 0 addr64 glc
+; GCN-NEXT:    s_waitcnt vmcnt(0)
+; GCN-NEXT:    s_mov_b32 s6, -1
+; GCN-NEXT:    s_mov_b32 s4, s0
+; GCN-NEXT:    s_mov_b32 s5, s1
+; GCN-NEXT:    v_alignbyte_b32 v0, v2, v0, s16
+; GCN-NEXT:    buffer_store_dword v0, off, s[4:7], 0
+; GCN-NEXT:    s_endpgm
+;
+; GFX11-TRUE16-LABEL: v_alignbyte_b32_2:
+; GFX11-TRUE16:       ; %bb.0:
+; GFX11-TRUE16-NEXT:    s_clause 0x1
+; GFX11-TRUE16-NEXT:    s_load_b128 s[0:3], s[4:5], 0x24
+; GFX11-TRUE16-NEXT:    s_load_b64 s[6:7], s[4:5], 0x34
+; GFX11-TRUE16-NEXT:    v_dual_mov_b32 v3, 0 :: v_dual_and_b32 v0, 0x3ff, v0
+; GFX11-TRUE16-NEXT:    s_delay_alu instid0(VALU_DEP_1)
+; GFX11-TRUE16-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
+; GFX11-TRUE16-NEXT:    s_waitcnt lgkmcnt(0)
+; GFX11-TRUE16-NEXT:    global_load_b32 v1, v0, s[2:3] glc dlc
+; GFX11-TRUE16-NEXT:    s_waitcnt vmcnt(0)
+; GFX11-TRUE16-NEXT:    global_load_b32 v2, v0, s[6:7] glc dlc
+; GFX11-TRUE16-NEXT:    s_waitcnt vmcnt(0)
+; GFX11-TRUE16-NEXT:    s_load_b32 s2, s[4:5], 0x3c
+; GFX11-TRUE16-NEXT:    s_waitcnt lgkmcnt(0)
+; GFX11-TRUE16-NEXT:    v_mov_b16_e32 v0.l, s2
+; GFX11-TRUE16-NEXT:    s_delay_alu instid0(VALU_DEP_1)
+; GFX11-TRUE16-NEXT:    v_alignbyte_b32 v0, v1, v2, v0.l
+; GFX11-TRUE16-NEXT:    global_store_b32 v3, v0, s[0:1]
+; GFX11-TRUE16-NEXT:    s_endpgm
+;
+; GFX11-FAKE16-LABEL: v_alignbyte_b32_2:
+; GFX11-FAKE16:       ; %bb.0:
+; GFX11-FAKE16-NEXT:    s_clause 0x1
+; GFX11-FAKE16-NEXT:    s_load_b128 s[0:3], s[4:5], 0x24
+; GFX11-FAKE16-NEXT:    s_load_b64 s[6:7], s[4:5], 0x34
+; GFX11-FAKE16-NEXT:    v_and_b32_e32 v0, 0x3ff, v0
+; GFX11-FAKE16-NEXT:    v_mov_b32_e32 v2, 0
+; GFX11-FAKE16-NEXT:    s_delay_alu instid0(VALU_DEP_2)
+; GFX11-FAKE16-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
+; GFX11-FAKE16-NEXT:    s_waitcnt lgkmcnt(0)
+; GFX11-FAKE16-NEXT:    global_load_b32 v1, v0, s[2:3] glc dlc
+; GFX11-FAKE16-NEXT:    s_waitcnt vmcnt(0)
+; GFX11-FAKE16-NEXT:    global_load_b32 v0, v0, s[6:7] glc dlc
+; GFX11-FAKE16-NEXT:    s_waitcnt vmcnt(0)
+; GFX11-FAKE16-NEXT:    s_load_b32 s2, s[4:5], 0x3c
+; GFX11-FAKE16-NEXT:    s_waitcnt lgkmcnt(0)
+; GFX11-FAKE16-NEXT:    v_alignbyte_b32 v0, v1, v0, s2
+; GFX11-FAKE16-NEXT:    global_store_b32 v2, v0, s[0:1]
+; GFX11-FAKE16-NEXT:    s_endpgm
+  %tid = call i32 @llvm.amdgcn.workitem.id.x()
+  %a.gep = getelementptr inbounds i32, ptr addrspace(1) %src1, i32 %tid
+  %b.gep = getelementptr inbounds i32, ptr addrspace(1) %src2, i32 %tid
+  %a.val = load volatile i32, ptr addrspace(1) %a.gep
+  %b.val = load volatile i32, ptr addrspace(1) %b.gep
+
+  %val = call i32 @llvm.amdgcn.alignbyte(i32 %a.val, i32 %b.val, i32 %src3) #0
+  store i32 %val, ptr addrspace(1) %out
+  ret void
+}
+
 attributes #0 = { nounwind readnone }
 attributes #1 = { nounwind }

llvm/test/MC/AMDGPU/gfx11_asm_vop3.s

@@ -461,11 +461,11 @@ v_alignbyte_b32 v5, s1, v255, s3
 v_alignbyte_b32 v5, s105, s105, s105
 // GFX11: v_alignbyte_b32 v5, s105, s105, s105    ; encoding: [0x05,0x00,0x17,0xd6,0x69,0xd2,0xa4,0x01]
 
-v_alignbyte_b32 v5, vcc_lo, ttmp15, v3
-// GFX11: v_alignbyte_b32 v5, vcc_lo, ttmp15, v3  ; encoding: [0x05,0x00,0x17,0xd6,0x6a,0xf6,0x0c,0x04]
+v_alignbyte_b32 v5, vcc_lo, ttmp15, v3.l
+// GFX11: v_alignbyte_b32 v5, vcc_lo, ttmp15, v3.l ; encoding: [0x05,0x00,0x17,0xd6,0x6a,0xf6,0x0c,0x04]
 
-v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255
-// GFX11: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255 ; encoding: [0x05,0x00,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.l
+// GFX11: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.l ; encoding: [0x05,0x00,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
 
 v_alignbyte_b32 v5, ttmp15, src_scc, ttmp15
 // GFX11: v_alignbyte_b32 v5, ttmp15, src_scc, ttmp15 ; encoding: [0x05,0x00,0x17,0xd6,0x7b,0xfa,0xed,0x01]
@@ -494,6 +494,9 @@ v_alignbyte_b32 v5, src_scc, vcc_lo, -1
 v_alignbyte_b32 v255, 0xaf123456, vcc_hi, null
 // GFX11: v_alignbyte_b32 v255, 0xaf123456, vcc_hi, null ; encoding: [0xff,0x00,0x17,0xd6,0xff,0xd6,0xf0,0x01,0x56,0x34,0x12,0xaf]
 
+v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.h
+// GFX11: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.h op_sel:[0,0,1,0] ; encoding: [0x05,0x20,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+
 v_and_b16 v5.l, v1.l, v2.l
 // GFX11: v_and_b16 v5.l, v1.l, v2.l              ; encoding: [0x05,0x00,0x62,0xd7,0x01,0x05,0x02,0x00]
 

llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16.s

@@ -363,22 +363,22 @@ v_alignbit_b32_e64_dpp v5, v1, v2, -1 row_xmask:0 row_mask:0x1 bank_mask:0x3 bou
 v_alignbit_b32_e64_dpp v255, v255, v255, src_scc row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
 // GFX11: v_alignbit_b32_e64_dpp v255, v255, v255, src_scc row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xff,0x00,0x16,0xd6,0xfa,0xfe,0xf7,0x03,0xff,0x6f,0x05,0x30]
 
-v_alignbyte_b32_e64_dpp v5, v1, v2, v3 quad_perm:[3,2,1,0]
-// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l quad_perm:[3,2,1,0]
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff]
 
-v_alignbyte_b32_e64_dpp v5, v1, v2, v3 quad_perm:[0,1,2,3]
-// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3 quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0xe4,0x00,0xff]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l quad_perm:[0,1,2,3]
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0xe4,0x00,0xff]
 
-v_alignbyte_b32_e64_dpp v5, v1, v2, v3 row_mirror
-// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x40,0x01,0xff]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l row_mirror row_mask:0xf bank_mask:0xf
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x40,0x01,0xff]
 
-v_alignbyte_b32_e64_dpp v5, v1, v2, v3 row_half_mirror
-// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x41,0x01,0xff]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l row_half_mirror row_mask:0xf bank_mask:0xf
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x41,0x01,0xff]
 
-v_alignbyte_b32_e64_dpp v5, v1, v2, v255 row_shl:1
-// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v255 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xfe,0x07,0x01,0x01,0x01,0xff]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v255.l row_shl:1 row_mask:0xf bank_mask:0xf
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v255.l row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xfe,0x07,0x01,0x01,0x01,0xff]
 
-v_alignbyte_b32_e64_dpp v5, v1, v2, s105 row_shl:15
+v_alignbyte_b32_e64_dpp v5, v1, v2, s105 row_shl:15 row_mask:0xf bank_mask:0xf
 // GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, s105 row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xa6,0x01,0x01,0x0f,0x01,0xff]
 
 v_alignbyte_b32_e64_dpp v5, v1, v2, vcc_hi row_shr:1
@@ -387,7 +387,7 @@ v_alignbyte_b32_e64_dpp v5, v1, v2, vcc_hi row_shr:1
 v_alignbyte_b32_e64_dpp v5, v1, v2, vcc_lo row_shr:15
 // GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, vcc_lo row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xaa,0x01,0x01,0x1f,0x01,0xff]
 
-v_alignbyte_b32_e64_dpp v5, v1, v2, ttmp15 row_ror:1
+v_alignbyte_b32_e64_dpp v5, v1, v2, ttmp15 row_ror:1 row_mask:0xf bank_mask:0xf
 // GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, ttmp15 row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xee,0x01,0x01,0x21,0x01,0xff]
 
 v_alignbyte_b32_e64_dpp v5, v1, v2, exec_hi row_ror:15
@@ -405,6 +405,24 @@ v_alignbyte_b32_e64_dpp v5, v1, v2, -1 row_xmask:0 row_mask:0x1 bank_mask:0x3 bo
 v_alignbyte_b32_e64_dpp v255, v255, v255, src_scc row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
 // GFX11: v_alignbyte_b32_e64_dpp v255, v255, v255, src_scc row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xff,0x00,0x17,0xd6,0xfa,0xfe,0xf7,0x03,0xff,0x6f,0x05,0x30]
 
+v_alignbyte_b32_e64_dpp v5, v1, v2, v255.l row_mirror
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v255.l row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xfe,0x07,0x01,0x40,0x01,0xff]
+
+v_alignbyte_b32_e64_dpp v5, v1, v2, s3 row_half_mirror
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, s3 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x00,0x01,0x41,0x01,0xff]
+
+v_alignbyte_b32_e64_dpp v5, v1, v2, s105 row_shl:1
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, s105 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xa6,0x01,0x01,0x01,0x01,0xff]
+
+v_alignbyte_b32_e64_dpp v5, v1, v2, ttmp15 row_shl:15
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, ttmp15 row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xee,0x01,0x01,0x0f,0x01,0xff]
+
+v_alignbyte_b32_e64_dpp v5, v1, v2, m0 row_ror:1
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, m0 row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xf6,0x01,0x01,0x21,0x01,0xff]
+
+v_alignbyte_b32_e64_dpp v5, v1, v2, v255.h row_mirror
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v255.h op_sel:[0,0,1,0] row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x20,0x17,0xd6,0xfa,0x04,0xfe,0x07,0x01,0x40,0x01,0xff]
+
 v_and_b16_e64_dpp v5.l, v1.l, v2.l quad_perm:[3,2,1,0]
 // GFX11: v_and_b16_e64_dpp v5.l, v1.l, v2.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x62,0xd7,0xfa,0x04,0x02,0x00,0x01,0x1b,0x00,0xff]
 

llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp8.s

@@ -187,11 +187,11 @@ v_alignbit_b32_e64_dpp v5, v1, v2, -1 dpp8:[7,6,5,4,3,2,1,0] fi:1
 v_alignbit_b32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] fi:0
 // GFX11: v_alignbit_b32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0x00,0x16,0xd6,0xe9,0xfe,0xf7,0x03,0xff,0x00,0x00,0x00]
 
-v_alignbyte_b32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0]
-// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x17,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x17,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05]
 
-v_alignbyte_b32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0]
-// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x17,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v255.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v255.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x17,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05]
 
 v_alignbyte_b32_e64_dpp v5, v1, v2, s105 dpp8:[7,6,5,4,3,2,1,0]
 // GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, s105 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x17,0xd6,0xe9,0x04,0xa6,0x01,0x01,0x77,0x39,0x05]
@@ -220,6 +220,15 @@ v_alignbyte_b32_e64_dpp v5, v1, v2, -1 dpp8:[7,6,5,4,3,2,1,0] fi:1
 v_alignbyte_b32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] fi:0
 // GFX11: v_alignbyte_b32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0x00,0x17,0xd6,0xe9,0xfe,0xf7,0x03,0xff,0x00,0x00,0x00]
 
+v_alignbyte_b32_e64_dpp v5, v1, v2, s3 dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, s3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x17,0xd6,0xe9,0x04,0x0e,0x00,0x01,0x77,0x39,0x05]
+
+v_alignbyte_b32_e64_dpp v5, v1, v2, m0 dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, m0 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x17,0xd6,0xe9,0x04,0xf6,0x01,0x01,0x77,0x39,0x05]
+
+v_alignbyte_b32_e64_dpp v5, v1, v2, v255.h dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v255.h op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x20,0x17,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05]
+
 v_and_b16_e64_dpp v5.l, v1.l, v2.l dpp8:[7,6,5,4,3,2,1,0]
 // GFX11: v_and_b16_e64_dpp v5.l, v1.l, v2.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x62,0xd7,0xe9,0x04,0x02,0x00,0x01,0x77,0x39,0x05]
 

llvm/test/MC/AMDGPU/gfx12_asm_vop3.s

@@ -452,6 +452,9 @@ v_alignbyte_b32 v5, src_scc, vcc_lo, -1
 v_alignbyte_b32 v255, 0xaf123456, vcc_hi, null
 // GFX12: v_alignbyte_b32 v255, 0xaf123456, vcc_hi, null ; encoding: [0xff,0x00,0x17,0xd6,0xff,0xd6,0xf0,0x01,0x56,0x34,0x12,0xaf]
 
+v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.h
+// GFX12: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.h op_sel:[0,0,1,0] ; encoding: [0x05,0x20,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+
 v_and_b16 v5.l, v1.l, v2.l
 // GFX12: v_and_b16 v5.l, v1.l, v2.l              ; encoding: [0x05,0x00,0x62,0xd7,0x01,0x05,0x02,0x00]
 

llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp16.s

@@ -485,6 +485,9 @@ v_alignbyte_b32_e64_dpp v5, v1, v2, -1 row_xmask:0 row_mask:0x1 bank_mask:0x3 bo
 v_alignbyte_b32_e64_dpp v255, v255, v255, src_scc row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
 // GFX12: v_alignbyte_b32_e64_dpp v255, v255, v255, src_scc row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xff,0x00,0x17,0xd6,0xfa,0xfe,0xf7,0x03,0xff,0x6f,0x05,0x30]
 
+v_alignbyte_b32_e64_dpp v5, v1, v2, v255.h row_mirror
+// GFX12: v_alignbyte_b32_e64_dpp v5, v1, v2, v255.h op_sel:[0,0,1,0] row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x20,0x17,0xd6,0xfa,0x04,0xfe,0x07,0x01,0x40,0x01,0xff]
+
 v_and_b16_e64_dpp v5.l, v1.l, v2.l quad_perm:[3,2,1,0]
 // GFX12: v_and_b16_e64_dpp v5.l, v1.l, v2.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x62,0xd7,0xfa,0x04,0x02,0x00,0x01,0x1b,0x00,0xff]