[AMDGPU][True16][CodeGen] srl pattern for true16 mode (#132987)

Added a srl pattern for true16 flow. Changing right shift 16bit to a
reg_sequence
`srl vgpr32, 16 -> reg_sequence (vgpr32.hi16,  0)`

and finally it's lowered to two COPY
`vdst.lo16 = COPY vsrc.hi16`
`vdst.hi16 = COPY 0`

The benefits of this transform is allowing the following pass to
optimize out these copy.

Author: broxigarchen

llvm/lib/Target/AMDGPU/SIInstructions.td

@@ -2425,6 +2425,13 @@ def : GCNPat <(i1 imm:$imm),
   let WaveSizePredicate = isWave32;
 }
 
+let True16Predicate = UseRealTrue16Insts in
+foreach vt = [i32, v2i16] in
+def : GCNPat <
+  (vt (DivergentBinFrag<srl> VGPR_32:$src, (i32 16))),
+  (REG_SEQUENCE VGPR_32, (i16 (EXTRACT_SUBREG $src, hi16)), lo16, (V_MOV_B16_t16_e64 0, (i16 0x0000), 0), hi16)
+>;
+
 /********** ================== **********/
 /********** Intrinsic Patterns **********/
 /********** ================== **********/

llvm/test/CodeGen/AMDGPU/add.v2i16.ll

@@ -658,26 +658,47 @@ define amdgpu_kernel void @v_test_add_v2i16_zext_to_v2i32(ptr addrspace(1) %out,
 ; GFX10-NEXT:    global_store_dwordx2 v2, v[0:1], s[0:1]
 ; GFX10-NEXT:    s_endpgm
 ;
-; GFX11-LABEL: v_test_add_v2i16_zext_to_v2i32:
-; GFX11:       ; %bb.0:
-; GFX11-NEXT:    s_clause 0x1
-; GFX11-NEXT:    s_load_b128 s[0:3], s[4:5], 0x24
-; GFX11-NEXT:    s_load_b64 s[4:5], s[4:5], 0x34
-; GFX11-NEXT:    v_and_b32_e32 v0, 0x3ff, v0
-; GFX11-NEXT:    v_mov_b32_e32 v2, 0
-; GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_2)
-; GFX11-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
-; GFX11-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX11-NEXT:    global_load_b32 v1, v0, s[2:3] glc dlc
-; GFX11-NEXT:    s_waitcnt vmcnt(0)
-; GFX11-NEXT:    global_load_b32 v0, v0, s[4:5] glc dlc
-; GFX11-NEXT:    s_waitcnt vmcnt(0)
-; GFX11-NEXT:    v_pk_add_u16 v0, v1, v0
-; GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_1)
-; GFX11-NEXT:    v_lshrrev_b32_e32 v1, 16, v0
-; GFX11-NEXT:    v_and_b32_e32 v0, 0xffff, v0
-; GFX11-NEXT:    global_store_b64 v2, v[0:1], s[0:1]
-; GFX11-NEXT:    s_endpgm
+; GFX11-TRUE16-LABEL: v_test_add_v2i16_zext_to_v2i32:
+; 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[4:5], 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 v0, v0, s[4:5] glc dlc
+; GFX11-TRUE16-NEXT:    s_waitcnt vmcnt(0)
+; GFX11-TRUE16-NEXT:    v_pk_add_u16 v2, v1, v0
+; GFX11-TRUE16-NEXT:    v_mov_b16_e32 v1.h, 0
+; GFX11-TRUE16-NEXT:    s_delay_alu instid0(VALU_DEP_2)
+; GFX11-TRUE16-NEXT:    v_and_b32_e32 v0, 0xffff, v2
+; GFX11-TRUE16-NEXT:    v_mov_b16_e32 v1.l, v2.h
+; GFX11-TRUE16-NEXT:    global_store_b64 v3, v[0:1], s[0:1]
+; GFX11-TRUE16-NEXT:    s_endpgm
+;
+; GFX11-FAKE16-LABEL: v_test_add_v2i16_zext_to_v2i32:
+; 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[4:5], 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[4:5] glc dlc
+; GFX11-FAKE16-NEXT:    s_waitcnt vmcnt(0)
+; GFX11-FAKE16-NEXT:    v_pk_add_u16 v0, v1, v0
+; GFX11-FAKE16-NEXT:    s_delay_alu instid0(VALU_DEP_1)
+; GFX11-FAKE16-NEXT:    v_lshrrev_b32_e32 v1, 16, v0
+; GFX11-FAKE16-NEXT:    v_and_b32_e32 v0, 0xffff, v0
+; GFX11-FAKE16-NEXT:    global_store_b64 v2, v[0:1], s[0:1]
+; GFX11-FAKE16-NEXT:    s_endpgm
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
   %gep.out = getelementptr inbounds <2 x i32>, ptr addrspace(1) %out, i32 %tid
   %gep.in0 = getelementptr inbounds <2 x i16>, ptr addrspace(1) %in0, i32 %tid
@@ -971,30 +992,57 @@ define amdgpu_kernel void @v_test_add_v2i16_sext_to_v2i64(ptr addrspace(1) %out,
 ; GFX10-NEXT:    global_store_dwordx4 v4, v[0:3], s[0:1]
 ; GFX10-NEXT:    s_endpgm
 ;
-; GFX11-LABEL: v_test_add_v2i16_sext_to_v2i64:
-; GFX11:       ; %bb.0:
-; GFX11-NEXT:    s_clause 0x1
-; GFX11-NEXT:    s_load_b128 s[0:3], s[4:5], 0x24
-; GFX11-NEXT:    s_load_b64 s[4:5], s[4:5], 0x34
-; GFX11-NEXT:    v_and_b32_e32 v0, 0x3ff, v0
-; GFX11-NEXT:    v_mov_b32_e32 v4, 0
-; GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_2)
-; GFX11-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
-; GFX11-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX11-NEXT:    s_clause 0x1
-; GFX11-NEXT:    global_load_b32 v1, v0, s[2:3]
-; GFX11-NEXT:    global_load_b32 v0, v0, s[4:5]
-; GFX11-NEXT:    s_waitcnt vmcnt(0)
-; GFX11-NEXT:    v_pk_add_u16 v0, v1, v0
-; GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_1) | instskip(SKIP_1) | instid1(VALU_DEP_2)
-; GFX11-NEXT:    v_lshrrev_b32_e32 v1, 16, v0
-; GFX11-NEXT:    v_bfe_i32 v0, v0, 0, 16
-; GFX11-NEXT:    v_bfe_i32 v2, v1, 0, 16
-; GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_2)
-; GFX11-NEXT:    v_ashrrev_i32_e32 v1, 31, v0
-; GFX11-NEXT:    v_ashrrev_i32_e32 v3, 31, v2
-; GFX11-NEXT:    global_store_b128 v4, v[0:3], s[0:1]
-; GFX11-NEXT:    s_endpgm
+; GFX11-TRUE16-LABEL: v_test_add_v2i16_sext_to_v2i64:
+; 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[4:5], s[4:5], 0x34
+; GFX11-TRUE16-NEXT:    v_and_b32_e32 v0, 0x3ff, v0
+; GFX11-TRUE16-NEXT:    v_mov_b32_e32 v4, 0
+; GFX11-TRUE16-NEXT:    s_delay_alu instid0(VALU_DEP_2)
+; GFX11-TRUE16-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
+; GFX11-TRUE16-NEXT:    s_waitcnt lgkmcnt(0)
+; GFX11-TRUE16-NEXT:    s_clause 0x1
+; GFX11-TRUE16-NEXT:    global_load_b32 v1, v0, s[2:3]
+; GFX11-TRUE16-NEXT:    global_load_b32 v0, v0, s[4:5]
+; GFX11-TRUE16-NEXT:    s_waitcnt vmcnt(0)
+; GFX11-TRUE16-NEXT:    v_pk_add_u16 v0, v1, v0
+; GFX11-TRUE16-NEXT:    v_mov_b16_e32 v1.h, 0
+; GFX11-TRUE16-NEXT:    s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_3)
+; GFX11-TRUE16-NEXT:    v_mov_b16_e32 v1.l, v0.h
+; GFX11-TRUE16-NEXT:    v_bfe_i32 v0, v0, 0, 16
+; GFX11-TRUE16-NEXT:    s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_2)
+; GFX11-TRUE16-NEXT:    v_bfe_i32 v2, v1, 0, 16
+; GFX11-TRUE16-NEXT:    v_ashrrev_i32_e32 v1, 31, v0
+; GFX11-TRUE16-NEXT:    s_delay_alu instid0(VALU_DEP_2)
+; GFX11-TRUE16-NEXT:    v_ashrrev_i32_e32 v3, 31, v2
+; GFX11-TRUE16-NEXT:    global_store_b128 v4, v[0:3], s[0:1]
+; GFX11-TRUE16-NEXT:    s_endpgm
+;
+; GFX11-FAKE16-LABEL: v_test_add_v2i16_sext_to_v2i64:
+; 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[4:5], s[4:5], 0x34
+; GFX11-FAKE16-NEXT:    v_and_b32_e32 v0, 0x3ff, v0
+; GFX11-FAKE16-NEXT:    v_mov_b32_e32 v4, 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:    s_clause 0x1
+; GFX11-FAKE16-NEXT:    global_load_b32 v1, v0, s[2:3]
+; GFX11-FAKE16-NEXT:    global_load_b32 v0, v0, s[4:5]
+; GFX11-FAKE16-NEXT:    s_waitcnt vmcnt(0)
+; GFX11-FAKE16-NEXT:    v_pk_add_u16 v0, v1, v0
+; GFX11-FAKE16-NEXT:    s_delay_alu instid0(VALU_DEP_1) | instskip(SKIP_1) | instid1(VALU_DEP_2)
+; GFX11-FAKE16-NEXT:    v_lshrrev_b32_e32 v1, 16, v0
+; GFX11-FAKE16-NEXT:    v_bfe_i32 v0, v0, 0, 16
+; GFX11-FAKE16-NEXT:    v_bfe_i32 v2, v1, 0, 16
+; GFX11-FAKE16-NEXT:    s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_2)
+; GFX11-FAKE16-NEXT:    v_ashrrev_i32_e32 v1, 31, v0
+; GFX11-FAKE16-NEXT:    v_ashrrev_i32_e32 v3, 31, v2
+; GFX11-FAKE16-NEXT:    global_store_b128 v4, v[0:3], s[0:1]
+; GFX11-FAKE16-NEXT:    s_endpgm
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
   %gep.out = getelementptr inbounds <2 x i64>, ptr addrspace(1) %out, i32 %tid
   %gep.in0 = getelementptr inbounds <2 x i16>, ptr addrspace(1) %in0, i32 %tid