revert intrinsic change, update pattern

Author: broxigarchen

llvm/lib/Target/AMDGPU/SIInstructions.td

@@ -3802,6 +3802,26 @@ def : FPMinCanonMaxPat<V_MINIMUMMAXIMUM_F16_fake16_e64, f16, DivergentBinFrag<fm
 def : FPMinCanonMaxPat<V_MAXIMUMMINIMUM_F16_fake16_e64, f16, DivergentBinFrag<fminimum>, fmaximum_oneuse>;
 }
 
+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)))
+>;
+
 // Convert a floating-point power of 2 to the integer exponent.
 def FPPow2ToExponentXForm : SDNodeXForm<fpimm, [{
   const auto &APF = N->getValueAPF();

llvm/lib/Target/AMDGPU/VOP3Instructions.td

@@ -212,11 +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>;
-defm V_ALIGNBYTE_B32 : VOP3Inst_t16_with_profiles <"v_alignbyte_b32",
-                                                   VOP3_Profile<VOP_I32_I32_I32_I32>,
-                                                   VOP3_Profile_True16<VOP_I32_I32_I32_I16, VOP3_OPSEL>,
-                                                   VOP3_Profile_Fake16<VOP_I32_I32_I32_I16, VOP3_OPSEL>,
-                                                   int_amdgcn_alignbyte>;
+
+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 {

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

@@ -1,10 +1,48 @@
+; 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