| ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 2 |
| ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1250 < %s | FileCheck -check-prefixes=GCN,GCN-SDAG %s |
| ; RUN: llc -global-isel -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1250 < %s | FileCheck -check-prefixes=GCN,GCN-GISEL %s |
| |
| ; Test S_WAIT_XCNT insertion for global_load/store clauses. |
| ; Introduced additional operations in between the clauses to have the register dependency |
| ; between the operands of VMEM operations and the def ops of VALU instructions that followed. |
| |
| define void @test_i8load_v4i8store(ptr addrspace(1) %ptr_a, ptr addrspace(1) %ptr_b, ptr addrspace(1) %ptr_c, ptr addrspace(1) %ptr_d, ptr addrspace(1) %out) { |
| ; GCN-SDAG-LABEL: test_i8load_v4i8store: |
| ; GCN-SDAG: ; %bb.0: |
| ; GCN-SDAG-NEXT: s_wait_loadcnt_dscnt 0x0 |
| ; GCN-SDAG-NEXT: s_wait_kmcnt 0x0 |
| ; GCN-SDAG-NEXT: global_load_u8 v2, v[2:3], off |
| ; GCN-SDAG-NEXT: global_load_u8 v3, v[4:5], off |
| ; GCN-SDAG-NEXT: global_load_u8 v0, v[0:1], off |
| ; GCN-SDAG-NEXT: s_wait_loadcnt 0x2 |
| ; GCN-SDAG-NEXT: s_wait_xcnt 0x0 |
| ; GCN-SDAG-NEXT: v_lshlrev_b16 v1, 8, v2 |
| ; GCN-SDAG-NEXT: s_wait_loadcnt 0x1 |
| ; GCN-SDAG-NEXT: v_lshlrev_b16 v2, 8, v3 |
| ; GCN-SDAG-NEXT: s_wait_loadcnt 0x0 |
| ; GCN-SDAG-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_2) |
| ; GCN-SDAG-NEXT: v_or_b32_e32 v0, v0, v1 |
| ; GCN-SDAG-NEXT: v_or_b32_e32 v1, v3, v2 |
| ; GCN-SDAG-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_3) |
| ; GCN-SDAG-NEXT: v_lshlrev_b32_e32 v1, 16, v1 |
| ; GCN-SDAG-NEXT: v_and_b32_e32 v0, 0xffff, v0 |
| ; GCN-SDAG-NEXT: s_delay_alu instid0(VALU_DEP_1) |
| ; GCN-SDAG-NEXT: v_or_b32_e32 v0, v0, v1 |
| ; GCN-SDAG-NEXT: global_store_b32 v[8:9], v0, off |
| ; GCN-SDAG-NEXT: s_set_pc_i64 s[30:31] |
| ; |
| ; GCN-GISEL-LABEL: test_i8load_v4i8store: |
| ; GCN-GISEL: ; %bb.0: |
| ; GCN-GISEL-NEXT: s_wait_loadcnt_dscnt 0x0 |
| ; GCN-GISEL-NEXT: s_wait_kmcnt 0x0 |
| ; GCN-GISEL-NEXT: global_load_u8 v0, v[0:1], off |
| ; GCN-GISEL-NEXT: global_load_u8 v1, v[2:3], off |
| ; GCN-GISEL-NEXT: global_load_u8 v2, v[4:5], off |
| ; GCN-GISEL-NEXT: s_wait_loadcnt 0x1 |
| ; GCN-GISEL-NEXT: v_lshl_or_b32 v0, v1, 8, v0 |
| ; GCN-GISEL-NEXT: s_wait_loadcnt 0x0 |
| ; GCN-GISEL-NEXT: v_dual_lshlrev_b32 v1, 16, v2 :: v_dual_lshlrev_b32 v2, 24, v2 |
| ; GCN-GISEL-NEXT: s_delay_alu instid0(VALU_DEP_1) |
| ; GCN-GISEL-NEXT: v_or3_b32 v0, v0, v1, v2 |
| ; GCN-GISEL-NEXT: global_store_b32 v[8:9], v0, off |
| ; GCN-GISEL-NEXT: s_set_pc_i64 s[30:31] |
| %a = load i8, ptr addrspace(1) %ptr_a |
| %b = load i8, ptr addrspace(1) %ptr_b |
| %c = load i8, ptr addrspace(1) %ptr_c |
| %d = load i8, ptr addrspace(1) %ptr_d |
| %ins_0 = insertelement <4 x i8> poison, i8 %a, i32 0 |
| %ins_1 = insertelement <4 x i8> %ins_0, i8 %b, i32 1 |
| %ins_2 = insertelement <4 x i8> %ins_1, i8 %c, i32 2 |
| %ins_3 = insertelement <4 x i8> %ins_2, i8 %c, i32 3 |
| store <4 x i8> %ins_3, ptr addrspace(1) %out |
| ret void |
| } |
| |
| define i16 @test_v7i16_load_store(ptr addrspace(1) %ptr1, ptr addrspace(1) %ptr2) { |
| ; GCN-SDAG-LABEL: test_v7i16_load_store: |
| ; GCN-SDAG: ; %bb.0: |
| ; GCN-SDAG-NEXT: s_wait_loadcnt_dscnt 0x0 |
| ; GCN-SDAG-NEXT: s_wait_kmcnt 0x0 |
| ; GCN-SDAG-NEXT: global_load_b128 v[4:7], v[0:1], off |
| ; GCN-SDAG-NEXT: global_load_b128 v[0:3], v[2:3], off |
| ; GCN-SDAG-NEXT: v_mov_b64_e32 v[8:9], 0 |
| ; GCN-SDAG-NEXT: s_wait_loadcnt 0x0 |
| ; GCN-SDAG-NEXT: v_pk_add_u16 v10, v6, v2 |
| ; GCN-SDAG-NEXT: v_pk_add_u16 v11, v7, v3 |
| ; GCN-SDAG-NEXT: s_wait_xcnt 0x0 |
| ; GCN-SDAG-NEXT: v_mov_b64_e32 v[2:3], 12 |
| ; GCN-SDAG-NEXT: v_mov_b64_e32 v[6:7], 8 |
| ; GCN-SDAG-NEXT: v_pk_add_u16 v4, v4, v0 |
| ; GCN-SDAG-NEXT: v_lshrrev_b32_e32 v0, 16, v10 |
| ; GCN-SDAG-NEXT: v_pk_add_u16 v5, v5, v1 |
| ; GCN-SDAG-NEXT: s_clause 0x2 |
| ; GCN-SDAG-NEXT: global_store_b16 v[2:3], v11, off |
| ; GCN-SDAG-NEXT: global_store_b32 v[6:7], v10, off |
| ; GCN-SDAG-NEXT: global_store_b64 v[8:9], v[4:5], off |
| ; GCN-SDAG-NEXT: s_set_pc_i64 s[30:31] |
| ; |
| ; GCN-GISEL-LABEL: test_v7i16_load_store: |
| ; GCN-GISEL: ; %bb.0: |
| ; GCN-GISEL-NEXT: s_wait_loadcnt_dscnt 0x0 |
| ; GCN-GISEL-NEXT: s_wait_kmcnt 0x0 |
| ; GCN-GISEL-NEXT: global_load_b128 v[4:7], v[0:1], off |
| ; GCN-GISEL-NEXT: global_load_b128 v[0:3], v[2:3], off |
| ; GCN-GISEL-NEXT: v_mov_b64_e32 v[8:9], 0 |
| ; GCN-GISEL-NEXT: v_mov_b64_e32 v[10:11], 2 |
| ; GCN-GISEL-NEXT: v_mov_b64_e32 v[12:13], 4 |
| ; GCN-GISEL-NEXT: v_mov_b64_e32 v[14:15], 6 |
| ; GCN-GISEL-NEXT: v_mov_b64_e32 v[16:17], 8 |
| ; GCN-GISEL-NEXT: v_mov_b64_e32 v[18:19], 10 |
| ; GCN-GISEL-NEXT: v_mov_b64_e32 v[20:21], 12 |
| ; GCN-GISEL-NEXT: s_wait_loadcnt 0x0 |
| ; GCN-GISEL-NEXT: v_pk_add_u16 v2, v6, v2 |
| ; GCN-GISEL-NEXT: v_pk_add_u16 v4, v4, v0 |
| ; GCN-GISEL-NEXT: v_pk_add_u16 v1, v5, v1 |
| ; GCN-GISEL-NEXT: v_pk_add_u16 v3, v7, v3 |
| ; GCN-GISEL-NEXT: s_clause 0x6 |
| ; GCN-GISEL-NEXT: global_store_b16 v[8:9], v4, off |
| ; GCN-GISEL-NEXT: global_store_d16_hi_b16 v[10:11], v4, off |
| ; GCN-GISEL-NEXT: global_store_b16 v[12:13], v1, off |
| ; GCN-GISEL-NEXT: global_store_d16_hi_b16 v[14:15], v1, off |
| ; GCN-GISEL-NEXT: global_store_b16 v[16:17], v2, off |
| ; GCN-GISEL-NEXT: global_store_d16_hi_b16 v[18:19], v2, off |
| ; GCN-GISEL-NEXT: global_store_b16 v[20:21], v3, off |
| ; GCN-GISEL-NEXT: v_lshrrev_b32_e32 v0, 16, v2 |
| ; GCN-GISEL-NEXT: s_set_pc_i64 s[30:31] |
| %vec1 = load <7 x i16>, ptr addrspace(1) %ptr1 |
| %insert = insertelement <7 x i16> %vec1, i16 20, i32 4 |
| %vec2 = load <7 x i16>, ptr addrspace(1) %ptr2 |
| %add = add <7 x i16> %vec1, %vec2 |
| store <7 x i16> %add, ptr addrspace(1) null |
| %elt = extractelement <7 x i16> %add, i32 5 |
| ret i16 %elt |
| } |
| |
| define i32 @test_v64i32_load_store(ptr addrspace(1) %ptr, i32 %idx, ptr addrspace(1) %out) { |
| ; GCN-SDAG-LABEL: test_v64i32_load_store: |
| ; GCN-SDAG: ; %bb.0: |
| ; GCN-SDAG-NEXT: s_wait_loadcnt_dscnt 0x0 |
| ; GCN-SDAG-NEXT: s_wait_kmcnt 0x0 |
| ; GCN-SDAG-NEXT: v_dual_mov_b32 v39, v4 :: v_dual_mov_b32 v38, v3 |
| ; GCN-SDAG-NEXT: s_clause 0xf |
| ; GCN-SDAG-NEXT: global_load_b128 v[2:5], v[0:1], off offset:224 |
| ; GCN-SDAG-NEXT: global_load_b128 v[6:9], v[0:1], off offset:240 |
| ; GCN-SDAG-NEXT: global_load_b128 v[10:13], v[0:1], off offset:192 |
| ; GCN-SDAG-NEXT: global_load_b128 v[14:17], v[0:1], off offset:208 |
| ; GCN-SDAG-NEXT: global_load_b128 v[18:21], v[0:1], off offset:160 |
| ; GCN-SDAG-NEXT: global_load_b128 v[22:25], v[0:1], off offset:176 |
| ; GCN-SDAG-NEXT: global_load_b128 v[26:29], v[0:1], off offset:128 |
| ; GCN-SDAG-NEXT: global_load_b128 v[30:33], v[0:1], off offset:144 |
| ; GCN-SDAG-NEXT: global_load_b128 v[34:37], v[0:1], off offset:96 |
| ; GCN-SDAG-NEXT: global_load_b128 v[48:51], v[0:1], off offset:112 |
| ; GCN-SDAG-NEXT: global_load_b128 v[52:55], v[0:1], off offset:64 |
| ; GCN-SDAG-NEXT: global_load_b128 v[64:67], v[0:1], off offset:80 |
| ; GCN-SDAG-NEXT: global_load_b128 v[68:71], v[0:1], off offset:32 |
| ; GCN-SDAG-NEXT: global_load_b128 v[80:83], v[0:1], off offset:48 |
| ; GCN-SDAG-NEXT: global_load_b128 v[84:87], v[0:1], off |
| ; GCN-SDAG-NEXT: global_load_b128 v[96:99], v[0:1], off offset:16 |
| ; GCN-SDAG-NEXT: s_wait_loadcnt 0xf |
| ; GCN-SDAG-NEXT: global_store_b128 v[38:39], v[2:5], off offset:224 |
| ; GCN-SDAG-NEXT: s_wait_loadcnt 0xe |
| ; GCN-SDAG-NEXT: global_store_b128 v[38:39], v[6:9], off offset:240 |
| ; GCN-SDAG-NEXT: s_wait_loadcnt 0xd |
| ; GCN-SDAG-NEXT: global_store_b128 v[38:39], v[10:13], off offset:192 |
| ; GCN-SDAG-NEXT: s_wait_loadcnt 0xc |
| ; GCN-SDAG-NEXT: global_store_b128 v[38:39], v[14:17], off offset:208 |
| ; GCN-SDAG-NEXT: s_wait_loadcnt 0xb |
| ; GCN-SDAG-NEXT: global_store_b128 v[38:39], v[18:21], off offset:160 |
| ; GCN-SDAG-NEXT: s_wait_loadcnt 0xa |
| ; GCN-SDAG-NEXT: global_store_b128 v[38:39], v[22:25], off offset:176 |
| ; GCN-SDAG-NEXT: s_wait_loadcnt 0x9 |
| ; GCN-SDAG-NEXT: global_store_b128 v[38:39], v[26:29], off offset:128 |
| ; GCN-SDAG-NEXT: s_wait_loadcnt 0x8 |
| ; GCN-SDAG-NEXT: global_store_b128 v[38:39], v[30:33], off offset:144 |
| ; GCN-SDAG-NEXT: s_wait_loadcnt 0x7 |
| ; GCN-SDAG-NEXT: global_store_b128 v[38:39], v[34:37], off offset:96 |
| ; GCN-SDAG-NEXT: s_wait_loadcnt 0x6 |
| ; GCN-SDAG-NEXT: global_store_b128 v[38:39], v[48:51], off offset:112 |
| ; GCN-SDAG-NEXT: s_wait_loadcnt 0x5 |
| ; GCN-SDAG-NEXT: global_store_b128 v[38:39], v[52:55], off offset:64 |
| ; GCN-SDAG-NEXT: s_wait_loadcnt 0x4 |
| ; GCN-SDAG-NEXT: global_store_b128 v[38:39], v[64:67], off offset:80 |
| ; GCN-SDAG-NEXT: s_wait_loadcnt 0x3 |
| ; GCN-SDAG-NEXT: global_store_b128 v[38:39], v[68:71], off offset:32 |
| ; GCN-SDAG-NEXT: s_wait_loadcnt 0x2 |
| ; GCN-SDAG-NEXT: global_store_b128 v[38:39], v[80:83], off offset:48 |
| ; GCN-SDAG-NEXT: s_wait_loadcnt 0x1 |
| ; GCN-SDAG-NEXT: global_store_b128 v[38:39], v[84:87], off |
| ; GCN-SDAG-NEXT: s_wait_loadcnt 0x0 |
| ; GCN-SDAG-NEXT: global_store_b128 v[38:39], v[96:99], off offset:16 |
| ; GCN-SDAG-NEXT: s_wait_xcnt 0x10 |
| ; GCN-SDAG-NEXT: v_mov_b32_e32 v0, v98 |
| ; GCN-SDAG-NEXT: s_set_pc_i64 s[30:31] |
| ; |
| ; GCN-GISEL-LABEL: test_v64i32_load_store: |
| ; GCN-GISEL: ; %bb.0: |
| ; GCN-GISEL-NEXT: s_wait_loadcnt_dscnt 0x0 |
| ; GCN-GISEL-NEXT: s_wait_kmcnt 0x0 |
| ; GCN-GISEL-NEXT: v_dual_mov_b32 v38, v3 :: v_dual_mov_b32 v39, v4 |
| ; GCN-GISEL-NEXT: s_clause 0xf |
| ; GCN-GISEL-NEXT: global_load_b128 v[2:5], v[0:1], off offset:32 |
| ; GCN-GISEL-NEXT: global_load_b128 v[6:9], v[0:1], off offset:48 |
| ; GCN-GISEL-NEXT: global_load_b128 v[10:13], v[0:1], off |
| ; GCN-GISEL-NEXT: global_load_b128 v[14:17], v[0:1], off offset:16 |
| ; GCN-GISEL-NEXT: global_load_b128 v[18:21], v[0:1], off offset:64 |
| ; GCN-GISEL-NEXT: global_load_b128 v[22:25], v[0:1], off offset:80 |
| ; GCN-GISEL-NEXT: global_load_b128 v[26:29], v[0:1], off offset:96 |
| ; GCN-GISEL-NEXT: global_load_b128 v[30:33], v[0:1], off offset:112 |
| ; GCN-GISEL-NEXT: global_load_b128 v[34:37], v[0:1], off offset:128 |
| ; GCN-GISEL-NEXT: global_load_b128 v[48:51], v[0:1], off offset:144 |
| ; GCN-GISEL-NEXT: global_load_b128 v[52:55], v[0:1], off offset:160 |
| ; GCN-GISEL-NEXT: global_load_b128 v[64:67], v[0:1], off offset:176 |
| ; GCN-GISEL-NEXT: global_load_b128 v[68:71], v[0:1], off offset:192 |
| ; GCN-GISEL-NEXT: global_load_b128 v[80:83], v[0:1], off offset:208 |
| ; GCN-GISEL-NEXT: global_load_b128 v[84:87], v[0:1], off offset:224 |
| ; GCN-GISEL-NEXT: global_load_b128 v[96:99], v[0:1], off offset:240 |
| ; GCN-GISEL-NEXT: s_wait_loadcnt 0xf |
| ; GCN-GISEL-NEXT: global_store_b128 v[38:39], v[2:5], off offset:32 |
| ; GCN-GISEL-NEXT: s_wait_loadcnt 0xe |
| ; GCN-GISEL-NEXT: global_store_b128 v[38:39], v[6:9], off offset:48 |
| ; GCN-GISEL-NEXT: s_wait_loadcnt 0xd |
| ; GCN-GISEL-NEXT: global_store_b128 v[38:39], v[10:13], off |
| ; GCN-GISEL-NEXT: s_wait_loadcnt 0xc |
| ; GCN-GISEL-NEXT: global_store_b128 v[38:39], v[14:17], off offset:16 |
| ; GCN-GISEL-NEXT: s_wait_loadcnt 0xb |
| ; GCN-GISEL-NEXT: global_store_b128 v[38:39], v[18:21], off offset:64 |
| ; GCN-GISEL-NEXT: s_wait_loadcnt 0xa |
| ; GCN-GISEL-NEXT: global_store_b128 v[38:39], v[22:25], off offset:80 |
| ; GCN-GISEL-NEXT: s_wait_loadcnt 0x9 |
| ; GCN-GISEL-NEXT: global_store_b128 v[38:39], v[26:29], off offset:96 |
| ; GCN-GISEL-NEXT: s_wait_loadcnt 0x8 |
| ; GCN-GISEL-NEXT: global_store_b128 v[38:39], v[30:33], off offset:112 |
| ; GCN-GISEL-NEXT: s_wait_loadcnt 0x7 |
| ; GCN-GISEL-NEXT: global_store_b128 v[38:39], v[34:37], off offset:128 |
| ; GCN-GISEL-NEXT: s_wait_loadcnt 0x6 |
| ; GCN-GISEL-NEXT: global_store_b128 v[38:39], v[48:51], off offset:144 |
| ; GCN-GISEL-NEXT: s_wait_loadcnt 0x5 |
| ; GCN-GISEL-NEXT: global_store_b128 v[38:39], v[52:55], off offset:160 |
| ; GCN-GISEL-NEXT: s_wait_loadcnt 0x4 |
| ; GCN-GISEL-NEXT: global_store_b128 v[38:39], v[64:67], off offset:176 |
| ; GCN-GISEL-NEXT: s_wait_loadcnt 0x3 |
| ; GCN-GISEL-NEXT: global_store_b128 v[38:39], v[68:71], off offset:192 |
| ; GCN-GISEL-NEXT: s_wait_loadcnt 0x2 |
| ; GCN-GISEL-NEXT: global_store_b128 v[38:39], v[80:83], off offset:208 |
| ; GCN-GISEL-NEXT: s_wait_loadcnt 0x1 |
| ; GCN-GISEL-NEXT: global_store_b128 v[38:39], v[84:87], off offset:224 |
| ; GCN-GISEL-NEXT: s_wait_loadcnt 0x0 |
| ; GCN-GISEL-NEXT: global_store_b128 v[38:39], v[96:99], off offset:240 |
| ; GCN-GISEL-NEXT: s_wait_xcnt 0x10 |
| ; GCN-GISEL-NEXT: v_mov_b32_e32 v0, v16 |
| ; GCN-GISEL-NEXT: s_set_pc_i64 s[30:31] |
| %vec = load <64 x i32>, ptr addrspace(1) %ptr |
| store <64 x i32> %vec, ptr addrspace(1) %out, align 4 |
| %elt = extractelement <64 x i32> %vec, i32 6 |
| ret i32 %elt |
| } |
| |
| define i64 @test_v16i64_load_store(ptr addrspace(1) %ptr_a, ptr addrspace(1) %ptr_b, ptr addrspace(1) %out) { |
| ; GCN-SDAG-LABEL: test_v16i64_load_store: |
| ; GCN-SDAG: ; %bb.0: |
| ; GCN-SDAG-NEXT: s_wait_loadcnt_dscnt 0x0 |
| ; GCN-SDAG-NEXT: s_wait_kmcnt 0x0 |
| ; GCN-SDAG-NEXT: s_clause 0x7 |
| ; GCN-SDAG-NEXT: global_load_b128 v[6:9], v[0:1], off offset:112 |
| ; GCN-SDAG-NEXT: global_load_b128 v[10:13], v[0:1], off offset:96 |
| ; GCN-SDAG-NEXT: global_load_b128 v[14:17], v[0:1], off offset:80 |
| ; GCN-SDAG-NEXT: global_load_b128 v[18:21], v[0:1], off offset:48 |
| ; GCN-SDAG-NEXT: global_load_b128 v[22:25], v[0:1], off offset:32 |
| ; GCN-SDAG-NEXT: global_load_b128 v[26:29], v[0:1], off offset:16 |
| ; GCN-SDAG-NEXT: global_load_b128 v[30:33], v[0:1], off |
| ; GCN-SDAG-NEXT: global_load_b128 v[0:3], v[0:1], off offset:64 |
| ; GCN-SDAG-NEXT: v_mov_b64_e32 v[36:37], 0x70 |
| ; GCN-SDAG-NEXT: v_mov_b64_e32 v[48:49], 48 |
| ; GCN-SDAG-NEXT: v_mov_b64_e32 v[38:39], 0x60 |
| ; GCN-SDAG-NEXT: v_mov_b64_e32 v[50:51], 32 |
| ; GCN-SDAG-NEXT: v_mov_b64_e32 v[64:65], 16 |
| ; GCN-SDAG-NEXT: v_mov_b64_e32 v[66:67], 0 |
| ; GCN-SDAG-NEXT: v_mov_b64_e32 v[52:53], 0x50 |
| ; GCN-SDAG-NEXT: v_mov_b64_e32 v[54:55], 64 |
| ; GCN-SDAG-NEXT: v_dual_mov_b32 v34, 0xc8 :: v_dual_mov_b32 v35, 0 |
| ; GCN-SDAG-NEXT: s_wait_loadcnt 0x7 |
| ; GCN-SDAG-NEXT: global_store_b128 v[36:37], v[6:9], off |
| ; GCN-SDAG-NEXT: s_wait_loadcnt 0x6 |
| ; GCN-SDAG-NEXT: global_store_b128 v[38:39], v[10:13], off |
| ; GCN-SDAG-NEXT: s_wait_loadcnt 0x5 |
| ; GCN-SDAG-NEXT: s_wait_xcnt 0x1 |
| ; GCN-SDAG-NEXT: v_dual_mov_b32 v36, v16 :: v_dual_mov_b32 v37, v17 |
| ; GCN-SDAG-NEXT: s_wait_xcnt 0x0 |
| ; GCN-SDAG-NEXT: v_add_nc_u64_e32 v[12:13], v[12:13], v[12:13] |
| ; GCN-SDAG-NEXT: v_add_nc_u64_e32 v[10:11], v[10:11], v[10:11] |
| ; GCN-SDAG-NEXT: s_wait_loadcnt 0x4 |
| ; GCN-SDAG-NEXT: global_store_b128 v[48:49], v[18:21], off |
| ; GCN-SDAG-NEXT: s_wait_loadcnt 0x3 |
| ; GCN-SDAG-NEXT: global_store_b128 v[50:51], v[22:25], off |
| ; GCN-SDAG-NEXT: s_wait_loadcnt 0x2 |
| ; GCN-SDAG-NEXT: global_store_b128 v[64:65], v[26:29], off |
| ; GCN-SDAG-NEXT: s_wait_loadcnt 0x1 |
| ; GCN-SDAG-NEXT: global_store_b128 v[66:67], v[30:33], off |
| ; GCN-SDAG-NEXT: s_wait_xcnt 0x0 |
| ; GCN-SDAG-NEXT: v_add_nc_u64_e32 v[32:33], v[32:33], v[32:33] |
| ; GCN-SDAG-NEXT: v_add_nc_u64_e32 v[8:9], v[8:9], v[8:9] |
| ; GCN-SDAG-NEXT: v_add_nc_u64_e32 v[6:7], v[6:7], v[6:7] |
| ; GCN-SDAG-NEXT: s_wait_loadcnt 0x0 |
| ; GCN-SDAG-NEXT: v_add_nc_u64_e32 v[50:51], v[2:3], v[2:3] |
| ; GCN-SDAG-NEXT: v_add_nc_u64_e32 v[48:49], v[0:1], v[0:1] |
| ; GCN-SDAG-NEXT: v_add_nc_u64_e32 v[16:17], v[16:17], v[16:17] |
| ; GCN-SDAG-NEXT: v_add_nc_u64_e32 v[14:15], 0xc8, v[14:15] |
| ; GCN-SDAG-NEXT: v_add_nc_u64_e32 v[24:25], 0x64, v[24:25] |
| ; GCN-SDAG-NEXT: v_add_nc_u64_e32 v[22:23], v[22:23], v[22:23] |
| ; GCN-SDAG-NEXT: v_add_nc_u64_e32 v[28:29], v[28:29], v[28:29] |
| ; GCN-SDAG-NEXT: v_add_nc_u64_e32 v[26:27], v[26:27], v[26:27] |
| ; GCN-SDAG-NEXT: v_add_nc_u64_e32 v[30:31], v[30:31], v[30:31] |
| ; GCN-SDAG-NEXT: v_add_nc_u64_e32 v[20:21], v[20:21], v[20:21] |
| ; GCN-SDAG-NEXT: v_add_nc_u64_e32 v[18:19], v[18:19], v[18:19] |
| ; GCN-SDAG-NEXT: s_clause 0x1 |
| ; GCN-SDAG-NEXT: global_store_b128 v[52:53], v[34:37], off |
| ; GCN-SDAG-NEXT: global_store_b128 v[54:55], v[0:3], off |
| ; GCN-SDAG-NEXT: s_clause 0x7 |
| ; GCN-SDAG-NEXT: global_store_b128 v[4:5], v[10:13], off offset:96 |
| ; GCN-SDAG-NEXT: global_store_b128 v[4:5], v[6:9], off offset:112 |
| ; GCN-SDAG-NEXT: global_store_b128 v[4:5], v[48:51], off offset:64 |
| ; GCN-SDAG-NEXT: global_store_b128 v[4:5], v[14:17], off offset:80 |
| ; GCN-SDAG-NEXT: global_store_b128 v[4:5], v[22:25], off offset:32 |
| ; GCN-SDAG-NEXT: global_store_b128 v[4:5], v[18:21], off offset:48 |
| ; GCN-SDAG-NEXT: global_store_b128 v[4:5], v[30:33], off |
| ; GCN-SDAG-NEXT: global_store_b128 v[4:5], v[26:29], off offset:16 |
| ; GCN-SDAG-NEXT: s_wait_xcnt 0x8 |
| ; GCN-SDAG-NEXT: v_dual_mov_b32 v0, v32 :: v_dual_mov_b32 v1, v33 |
| ; GCN-SDAG-NEXT: s_set_pc_i64 s[30:31] |
| ; |
| ; GCN-GISEL-LABEL: test_v16i64_load_store: |
| ; GCN-GISEL: ; %bb.0: |
| ; GCN-GISEL-NEXT: s_wait_loadcnt_dscnt 0x0 |
| ; GCN-GISEL-NEXT: s_wait_kmcnt 0x0 |
| ; GCN-GISEL-NEXT: s_clause 0x7 |
| ; GCN-GISEL-NEXT: global_load_b128 v[6:9], v[0:1], off offset:80 |
| ; GCN-GISEL-NEXT: global_load_b128 v[10:13], v[0:1], off |
| ; GCN-GISEL-NEXT: global_load_b128 v[14:17], v[0:1], off offset:16 |
| ; GCN-GISEL-NEXT: global_load_b128 v[18:21], v[0:1], off offset:32 |
| ; GCN-GISEL-NEXT: global_load_b128 v[22:25], v[0:1], off offset:48 |
| ; GCN-GISEL-NEXT: global_load_b128 v[26:29], v[0:1], off offset:96 |
| ; GCN-GISEL-NEXT: global_load_b128 v[30:33], v[0:1], off offset:112 |
| ; GCN-GISEL-NEXT: global_load_b128 v[0:3], v[0:1], off offset:64 |
| ; GCN-GISEL-NEXT: v_mov_b64_e32 v[38:39], 0 |
| ; GCN-GISEL-NEXT: v_mov_b64_e32 v[48:49], 16 |
| ; GCN-GISEL-NEXT: v_mov_b64_e32 v[50:51], 32 |
| ; GCN-GISEL-NEXT: v_mov_b64_e32 v[52:53], 48 |
| ; GCN-GISEL-NEXT: v_mov_b64_e32 v[66:67], 0x60 |
| ; GCN-GISEL-NEXT: v_mov_b64_e32 v[68:69], 0x70 |
| ; GCN-GISEL-NEXT: v_mov_b64_e32 v[54:55], 64 |
| ; GCN-GISEL-NEXT: v_mov_b64_e32 v[34:35], 0xc8 |
| ; GCN-GISEL-NEXT: v_mov_b64_e32 v[64:65], 0x50 |
| ; GCN-GISEL-NEXT: s_wait_loadcnt 0x6 |
| ; GCN-GISEL-NEXT: global_store_b128 v[38:39], v[10:13], off |
| ; GCN-GISEL-NEXT: s_wait_loadcnt 0x5 |
| ; GCN-GISEL-NEXT: global_store_b128 v[48:49], v[14:17], off |
| ; GCN-GISEL-NEXT: s_wait_loadcnt 0x4 |
| ; GCN-GISEL-NEXT: global_store_b128 v[50:51], v[18:21], off |
| ; GCN-GISEL-NEXT: s_wait_loadcnt 0x3 |
| ; GCN-GISEL-NEXT: global_store_b128 v[52:53], v[22:25], off |
| ; GCN-GISEL-NEXT: s_wait_loadcnt 0x2 |
| ; GCN-GISEL-NEXT: global_store_b128 v[66:67], v[26:29], off |
| ; GCN-GISEL-NEXT: s_wait_loadcnt 0x1 |
| ; GCN-GISEL-NEXT: global_store_b128 v[68:69], v[30:33], off |
| ; GCN-GISEL-NEXT: s_wait_xcnt 0x5 |
| ; GCN-GISEL-NEXT: v_add_nc_u64_e32 v[12:13], v[12:13], v[12:13] |
| ; GCN-GISEL-NEXT: v_mov_b64_e32 v[36:37], v[8:9] |
| ; GCN-GISEL-NEXT: v_add_nc_u64_e32 v[10:11], v[10:11], v[10:11] |
| ; GCN-GISEL-NEXT: s_wait_xcnt 0x4 |
| ; GCN-GISEL-NEXT: v_add_nc_u64_e32 v[14:15], v[14:15], v[14:15] |
| ; GCN-GISEL-NEXT: v_add_nc_u64_e32 v[16:17], v[16:17], v[16:17] |
| ; GCN-GISEL-NEXT: s_wait_xcnt 0x3 |
| ; GCN-GISEL-NEXT: v_add_nc_u64_e32 v[18:19], v[18:19], v[18:19] |
| ; GCN-GISEL-NEXT: v_add_nc_u64_e32 v[20:21], 0x64, v[20:21] |
| ; GCN-GISEL-NEXT: s_wait_xcnt 0x2 |
| ; GCN-GISEL-NEXT: v_add_nc_u64_e32 v[22:23], v[22:23], v[22:23] |
| ; GCN-GISEL-NEXT: v_add_nc_u64_e32 v[24:25], v[24:25], v[24:25] |
| ; GCN-GISEL-NEXT: s_wait_loadcnt 0x0 |
| ; GCN-GISEL-NEXT: v_add_nc_u64_e32 v[48:49], v[0:1], v[0:1] |
| ; GCN-GISEL-NEXT: v_add_nc_u64_e32 v[50:51], v[2:3], v[2:3] |
| ; GCN-GISEL-NEXT: v_add_nc_u64_e32 v[6:7], 0xc8, v[6:7] |
| ; GCN-GISEL-NEXT: v_add_nc_u64_e32 v[8:9], v[8:9], v[8:9] |
| ; GCN-GISEL-NEXT: s_wait_xcnt 0x1 |
| ; GCN-GISEL-NEXT: v_add_nc_u64_e32 v[26:27], v[26:27], v[26:27] |
| ; GCN-GISEL-NEXT: v_add_nc_u64_e32 v[28:29], v[28:29], v[28:29] |
| ; GCN-GISEL-NEXT: s_wait_xcnt 0x0 |
| ; GCN-GISEL-NEXT: v_add_nc_u64_e32 v[30:31], v[30:31], v[30:31] |
| ; GCN-GISEL-NEXT: v_add_nc_u64_e32 v[32:33], v[32:33], v[32:33] |
| ; GCN-GISEL-NEXT: s_clause 0x1 |
| ; GCN-GISEL-NEXT: global_store_b128 v[54:55], v[0:3], off |
| ; GCN-GISEL-NEXT: global_store_b128 v[64:65], v[34:37], off |
| ; GCN-GISEL-NEXT: s_clause 0x7 |
| ; GCN-GISEL-NEXT: global_store_b128 v[4:5], v[10:13], off |
| ; GCN-GISEL-NEXT: global_store_b128 v[4:5], v[14:17], off offset:16 |
| ; GCN-GISEL-NEXT: global_store_b128 v[4:5], v[18:21], off offset:32 |
| ; GCN-GISEL-NEXT: global_store_b128 v[4:5], v[22:25], off offset:48 |
| ; GCN-GISEL-NEXT: global_store_b128 v[4:5], v[48:51], off offset:64 |
| ; GCN-GISEL-NEXT: global_store_b128 v[4:5], v[6:9], off offset:80 |
| ; GCN-GISEL-NEXT: global_store_b128 v[4:5], v[26:29], off offset:96 |
| ; GCN-GISEL-NEXT: global_store_b128 v[4:5], v[30:33], off offset:112 |
| ; GCN-GISEL-NEXT: s_wait_xcnt 0x9 |
| ; GCN-GISEL-NEXT: v_dual_mov_b32 v0, v12 :: v_dual_mov_b32 v1, v13 |
| ; GCN-GISEL-NEXT: s_set_pc_i64 s[30:31] |
| %a = load <16 x i64>, ptr addrspace(1) %ptr_a, align 4 |
| %in_a = insertelement <16 x i64> %a, i64 100, i32 5 |
| store <16 x i64> %in_a, ptr addrspace(1) null |
| %b = load <16 x i64>, ptr addrspace(1) %ptr_b, align 4 |
| %in_b = insertelement <16 x i64> %a, i64 200, i32 10 |
| store <16 x i64> %in_b, ptr addrspace(1) null |
| %add = add <16 x i64> %in_a, %in_b |
| store <16 x i64> %add, ptr addrspace(1) %out, align 4 |
| %elt = extractelement <16 x i64> %add, i32 1 |
| ret i64 %elt |
| } |
| |
| define amdgpu_kernel void @test_v7i16_load_store_kernel(ptr addrspace(1) %ptr1, ptr addrspace(1) %ptr2, ptr addrspace(1) %out) { |
| ; GCN-SDAG-LABEL: test_v7i16_load_store_kernel: |
| ; GCN-SDAG: ; %bb.0: |
| ; GCN-SDAG-NEXT: s_load_b128 s[0:3], s[4:5], 0x0 |
| ; GCN-SDAG-NEXT: v_and_b32_e32 v4, 0x3ff, v0 |
| ; GCN-SDAG-NEXT: s_wait_xcnt 0x0 |
| ; GCN-SDAG-NEXT: s_load_b64 s[4:5], s[4:5], 0x10 |
| ; GCN-SDAG-NEXT: v_mov_b64_e32 v[8:9], 12 |
| ; GCN-SDAG-NEXT: v_mov_b64_e32 v[10:11], 8 |
| ; GCN-SDAG-NEXT: v_mov_b64_e32 v[12:13], 0 |
| ; GCN-SDAG-NEXT: s_wait_kmcnt 0x0 |
| ; GCN-SDAG-NEXT: s_clause 0x1 |
| ; GCN-SDAG-NEXT: global_load_b128 v[0:3], v4, s[0:1] scale_offset |
| ; GCN-SDAG-NEXT: global_load_b128 v[4:7], v4, s[2:3] scale_offset |
| ; GCN-SDAG-NEXT: s_wait_loadcnt 0x0 |
| ; GCN-SDAG-NEXT: v_pk_add_u16 v3, v3, v7 |
| ; GCN-SDAG-NEXT: v_pk_add_u16 v2, v2, v6 |
| ; GCN-SDAG-NEXT: v_pk_add_u16 v1, v1, v5 |
| ; GCN-SDAG-NEXT: v_pk_add_u16 v0, v0, v4 |
| ; GCN-SDAG-NEXT: v_mov_b32_e32 v4, 0 |
| ; GCN-SDAG-NEXT: s_clause 0x2 |
| ; GCN-SDAG-NEXT: global_store_b16 v[8:9], v3, off |
| ; GCN-SDAG-NEXT: global_store_b32 v[10:11], v2, off |
| ; GCN-SDAG-NEXT: global_store_b64 v[12:13], v[0:1], off |
| ; GCN-SDAG-NEXT: global_store_d16_hi_b16 v4, v2, s[4:5] |
| ; GCN-SDAG-NEXT: s_endpgm |
| ; |
| ; GCN-GISEL-LABEL: test_v7i16_load_store_kernel: |
| ; GCN-GISEL: ; %bb.0: |
| ; GCN-GISEL-NEXT: s_load_b128 s[0:3], s[4:5], 0x0 |
| ; GCN-GISEL-NEXT: v_and_b32_e32 v4, 0x3ff, v0 |
| ; GCN-GISEL-NEXT: s_wait_xcnt 0x0 |
| ; GCN-GISEL-NEXT: s_load_b64 s[4:5], s[4:5], 0x10 |
| ; GCN-GISEL-NEXT: v_mov_b64_e32 v[8:9], 0 |
| ; GCN-GISEL-NEXT: v_mov_b64_e32 v[10:11], 2 |
| ; GCN-GISEL-NEXT: v_mov_b64_e32 v[12:13], 4 |
| ; GCN-GISEL-NEXT: v_mov_b64_e32 v[14:15], 6 |
| ; GCN-GISEL-NEXT: v_mov_b64_e32 v[16:17], 8 |
| ; GCN-GISEL-NEXT: v_mov_b64_e32 v[18:19], 10 |
| ; GCN-GISEL-NEXT: v_mov_b64_e32 v[20:21], 12 |
| ; GCN-GISEL-NEXT: s_wait_kmcnt 0x0 |
| ; GCN-GISEL-NEXT: s_clause 0x1 |
| ; GCN-GISEL-NEXT: global_load_b128 v[0:3], v4, s[0:1] scale_offset |
| ; GCN-GISEL-NEXT: global_load_b128 v[4:7], v4, s[2:3] scale_offset |
| ; GCN-GISEL-NEXT: s_wait_loadcnt 0x0 |
| ; GCN-GISEL-NEXT: v_pk_add_u16 v0, v0, v4 |
| ; GCN-GISEL-NEXT: v_pk_add_u16 v1, v1, v5 |
| ; GCN-GISEL-NEXT: v_pk_add_u16 v2, v2, v6 |
| ; GCN-GISEL-NEXT: v_mov_b32_e32 v4, 0 |
| ; GCN-GISEL-NEXT: v_pk_add_u16 v3, v3, v7 |
| ; GCN-GISEL-NEXT: s_clause 0x6 |
| ; GCN-GISEL-NEXT: global_store_b16 v[8:9], v0, off |
| ; GCN-GISEL-NEXT: global_store_d16_hi_b16 v[10:11], v0, off |
| ; GCN-GISEL-NEXT: global_store_b16 v[12:13], v1, off |
| ; GCN-GISEL-NEXT: global_store_d16_hi_b16 v[14:15], v1, off |
| ; GCN-GISEL-NEXT: global_store_b16 v[16:17], v2, off |
| ; GCN-GISEL-NEXT: global_store_d16_hi_b16 v[18:19], v2, off |
| ; GCN-GISEL-NEXT: global_store_b16 v[20:21], v3, off |
| ; GCN-GISEL-NEXT: global_store_d16_hi_b16 v4, v2, s[4:5] |
| ; GCN-GISEL-NEXT: s_endpgm |
| %tid = call i32 @llvm.amdgcn.workitem.id.x() |
| %gep1 = getelementptr inbounds <7 x i16>, ptr addrspace(1) %ptr1, i32 %tid |
| %gep2 = getelementptr inbounds <7 x i16>, ptr addrspace(1) %ptr2, i32 %tid |
| %vec1 = load <7 x i16>, ptr addrspace(1) %gep1 |
| %insert = insertelement <7 x i16> %vec1, i16 20, i32 4 |
| %vec2 = load <7 x i16>, ptr addrspace(1) %gep2 |
| %add = add <7 x i16> %vec1, %vec2 |
| store <7 x i16> %add, ptr addrspace(1) null |
| %elt = extractelement <7 x i16> %add, i32 5 |
| store i16 %elt, ptr addrspace(1) %out |
| ret void |
| } |
| |
| ;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line: |
| ; GCN: {{.*}} |