forked from OSchip/llvm-project
166 lines
8.4 KiB
LLVM
166 lines
8.4 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -global-isel -O0 -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1031 -verify-machineinstrs -o - %s | FileCheck %s
|
|
|
|
; Make sure the waterfall loop does not fail the verifier after regalloc fast
|
|
define <4 x float> @waterfall_loop(<8 x i32> %vgpr_srd) {
|
|
; CHECK-LABEL: waterfall_loop:
|
|
; CHECK: ; %bb.0: ; %bb
|
|
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; CHECK-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; CHECK-NEXT: s_or_saveexec_b32 s4, -1
|
|
; CHECK-NEXT: buffer_store_dword v15, off, s[0:3], s32 offset:76 ; 4-byte Folded Spill
|
|
; CHECK-NEXT: s_mov_b32 exec_lo, s4
|
|
; CHECK-NEXT: v_mov_b32_e32 v14, v1
|
|
; CHECK-NEXT: v_mov_b32_e32 v13, v2
|
|
; CHECK-NEXT: v_mov_b32_e32 v12, v3
|
|
; CHECK-NEXT: v_mov_b32_e32 v11, v4
|
|
; CHECK-NEXT: v_mov_b32_e32 v10, v5
|
|
; CHECK-NEXT: v_mov_b32_e32 v9, v6
|
|
; CHECK-NEXT: v_mov_b32_e32 v8, v7
|
|
; CHECK-NEXT: ; kill: def $vgpr0 killed $vgpr0 def $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7 killed $exec
|
|
; CHECK-NEXT: v_mov_b32_e32 v1, v14
|
|
; CHECK-NEXT: v_mov_b32_e32 v2, v13
|
|
; CHECK-NEXT: v_mov_b32_e32 v3, v12
|
|
; CHECK-NEXT: v_mov_b32_e32 v4, v11
|
|
; CHECK-NEXT: v_mov_b32_e32 v5, v10
|
|
; CHECK-NEXT: v_mov_b32_e32 v6, v9
|
|
; CHECK-NEXT: v_mov_b32_e32 v7, v8
|
|
; CHECK-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:40 ; 4-byte Folded Spill
|
|
; CHECK-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:44 ; 4-byte Folded Spill
|
|
; CHECK-NEXT: buffer_store_dword v2, off, s[0:3], s32 offset:48 ; 4-byte Folded Spill
|
|
; CHECK-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:52 ; 4-byte Folded Spill
|
|
; CHECK-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:56 ; 4-byte Folded Spill
|
|
; CHECK-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:60 ; 4-byte Folded Spill
|
|
; CHECK-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:64 ; 4-byte Folded Spill
|
|
; CHECK-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:68 ; 4-byte Folded Spill
|
|
; CHECK-NEXT: v_writelane_b32 v15, s30, 0
|
|
; CHECK-NEXT: v_writelane_b32 v15, s31, 1
|
|
; CHECK-NEXT: s_mov_b32 s8, 0
|
|
; CHECK-NEXT: s_mov_b32 s4, s8
|
|
; CHECK-NEXT: s_mov_b32 s5, s8
|
|
; CHECK-NEXT: s_mov_b32 s6, s8
|
|
; CHECK-NEXT: s_mov_b32 s7, s8
|
|
; CHECK-NEXT: v_writelane_b32 v15, s4, 2
|
|
; CHECK-NEXT: v_writelane_b32 v15, s5, 3
|
|
; CHECK-NEXT: v_writelane_b32 v15, s6, 4
|
|
; CHECK-NEXT: v_writelane_b32 v15, s7, 5
|
|
; CHECK-NEXT: s_mov_b32 s6, 0
|
|
; CHECK-NEXT: s_mov_b32 s4, s6
|
|
; CHECK-NEXT: s_mov_b32 s5, s6
|
|
; CHECK-NEXT: v_mov_b32_e32 v9, s5
|
|
; CHECK-NEXT: v_mov_b32_e32 v8, s4
|
|
; CHECK-NEXT: buffer_store_dword v8, off, s[0:3], s32 offset:32 ; 4-byte Folded Spill
|
|
; CHECK-NEXT: buffer_store_dword v9, off, s[0:3], s32 offset:36 ; 4-byte Folded Spill
|
|
; CHECK-NEXT: v_mov_b32_e32 v9, v1
|
|
; CHECK-NEXT: v_mov_b32_e32 v8, v0
|
|
; CHECK-NEXT: buffer_store_dword v8, off, s[0:3], s32 offset:24 ; 4-byte Folded Spill
|
|
; CHECK-NEXT: buffer_store_dword v9, off, s[0:3], s32 offset:28 ; 4-byte Folded Spill
|
|
; CHECK-NEXT: v_mov_b32_e32 v9, v3
|
|
; CHECK-NEXT: v_mov_b32_e32 v8, v2
|
|
; CHECK-NEXT: buffer_store_dword v8, off, s[0:3], s32 offset:16 ; 4-byte Folded Spill
|
|
; CHECK-NEXT: buffer_store_dword v9, off, s[0:3], s32 offset:20 ; 4-byte Folded Spill
|
|
; CHECK-NEXT: v_mov_b32_e32 v9, v5
|
|
; CHECK-NEXT: v_mov_b32_e32 v8, v4
|
|
; CHECK-NEXT: buffer_store_dword v8, off, s[0:3], s32 offset:8 ; 4-byte Folded Spill
|
|
; CHECK-NEXT: buffer_store_dword v9, off, s[0:3], s32 offset:12 ; 4-byte Folded Spill
|
|
; CHECK-NEXT: v_mov_b32_e32 v0, v6
|
|
; CHECK-NEXT: v_mov_b32_e32 v1, v7
|
|
; CHECK-NEXT: buffer_store_dword v0, off, s[0:3], s32 ; 4-byte Folded Spill
|
|
; CHECK-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:4 ; 4-byte Folded Spill
|
|
; CHECK-NEXT: s_mov_b32 s4, exec_lo
|
|
; CHECK-NEXT: v_writelane_b32 v15, s4, 6
|
|
; CHECK-NEXT: .LBB0_1: ; =>This Inner Loop Header: Depth=1
|
|
; CHECK-NEXT: buffer_load_dword v0, off, s[0:3], s32 offset:32 ; 4-byte Folded Reload
|
|
; CHECK-NEXT: buffer_load_dword v1, off, s[0:3], s32 offset:36 ; 4-byte Folded Reload
|
|
; CHECK-NEXT: v_readlane_b32 s16, v15, 2
|
|
; CHECK-NEXT: v_readlane_b32 s17, v15, 3
|
|
; CHECK-NEXT: v_readlane_b32 s18, v15, 4
|
|
; CHECK-NEXT: v_readlane_b32 s19, v15, 5
|
|
; CHECK-NEXT: buffer_load_dword v2, off, s[0:3], s32 ; 4-byte Folded Reload
|
|
; CHECK-NEXT: buffer_load_dword v3, off, s[0:3], s32 offset:4 ; 4-byte Folded Reload
|
|
; CHECK-NEXT: buffer_load_dword v4, off, s[0:3], s32 offset:8 ; 4-byte Folded Reload
|
|
; CHECK-NEXT: buffer_load_dword v5, off, s[0:3], s32 offset:12 ; 4-byte Folded Reload
|
|
; CHECK-NEXT: buffer_load_dword v6, off, s[0:3], s32 offset:16 ; 4-byte Folded Reload
|
|
; CHECK-NEXT: buffer_load_dword v7, off, s[0:3], s32 offset:20 ; 4-byte Folded Reload
|
|
; CHECK-NEXT: buffer_load_dword v8, off, s[0:3], s32 offset:24 ; 4-byte Folded Reload
|
|
; CHECK-NEXT: buffer_load_dword v9, off, s[0:3], s32 offset:28 ; 4-byte Folded Reload
|
|
; CHECK-NEXT: s_waitcnt vmcnt(0)
|
|
; CHECK-NEXT: v_readfirstlane_b32 s8, v8
|
|
; CHECK-NEXT: v_readfirstlane_b32 s23, v9
|
|
; CHECK-NEXT: s_mov_b32 s4, s8
|
|
; CHECK-NEXT: s_mov_b32 s5, s23
|
|
; CHECK-NEXT: v_writelane_b32 v15, s4, 7
|
|
; CHECK-NEXT: v_writelane_b32 v15, s5, 8
|
|
; CHECK-NEXT: v_cmp_eq_u64_e64 s5, s[4:5], v[8:9]
|
|
; CHECK-NEXT: v_readfirstlane_b32 s22, v6
|
|
; CHECK-NEXT: v_readfirstlane_b32 s21, v7
|
|
; CHECK-NEXT: s_mov_b32 s6, s22
|
|
; CHECK-NEXT: s_mov_b32 s7, s21
|
|
; CHECK-NEXT: v_writelane_b32 v15, s6, 9
|
|
; CHECK-NEXT: v_writelane_b32 v15, s7, 10
|
|
; CHECK-NEXT: v_cmp_eq_u64_e64 s4, s[6:7], v[6:7]
|
|
; CHECK-NEXT: s_and_b32 s5, s4, s5
|
|
; CHECK-NEXT: v_readfirstlane_b32 s20, v4
|
|
; CHECK-NEXT: v_readfirstlane_b32 s7, v5
|
|
; CHECK-NEXT: s_mov_b32 s10, s20
|
|
; CHECK-NEXT: s_mov_b32 s11, s7
|
|
; CHECK-NEXT: v_writelane_b32 v15, s10, 11
|
|
; CHECK-NEXT: v_writelane_b32 v15, s11, 12
|
|
; CHECK-NEXT: v_cmp_eq_u64_e64 s4, s[10:11], v[4:5]
|
|
; CHECK-NEXT: s_and_b32 s9, s4, s5
|
|
; CHECK-NEXT: v_readfirstlane_b32 s6, v2
|
|
; CHECK-NEXT: v_readfirstlane_b32 s5, v3
|
|
; CHECK-NEXT: s_mov_b32 s10, s6
|
|
; CHECK-NEXT: s_mov_b32 s11, s5
|
|
; CHECK-NEXT: v_writelane_b32 v15, s10, 13
|
|
; CHECK-NEXT: v_writelane_b32 v15, s11, 14
|
|
; CHECK-NEXT: v_cmp_eq_u64_e64 s4, s[10:11], v[2:3]
|
|
; CHECK-NEXT: s_and_b32 s4, s4, s9
|
|
; CHECK-NEXT: ; kill: def $sgpr8 killed $sgpr8 def $sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15
|
|
; CHECK-NEXT: s_mov_b32 s9, s23
|
|
; CHECK-NEXT: s_mov_b32 s10, s22
|
|
; CHECK-NEXT: s_mov_b32 s11, s21
|
|
; CHECK-NEXT: s_mov_b32 s12, s20
|
|
; CHECK-NEXT: s_mov_b32 s13, s7
|
|
; CHECK-NEXT: s_mov_b32 s14, s6
|
|
; CHECK-NEXT: s_mov_b32 s15, s5
|
|
; CHECK-NEXT: v_writelane_b32 v15, s8, 15
|
|
; CHECK-NEXT: v_writelane_b32 v15, s9, 16
|
|
; CHECK-NEXT: v_writelane_b32 v15, s10, 17
|
|
; CHECK-NEXT: v_writelane_b32 v15, s11, 18
|
|
; CHECK-NEXT: v_writelane_b32 v15, s12, 19
|
|
; CHECK-NEXT: v_writelane_b32 v15, s13, 20
|
|
; CHECK-NEXT: v_writelane_b32 v15, s14, 21
|
|
; CHECK-NEXT: v_writelane_b32 v15, s15, 22
|
|
; CHECK-NEXT: s_and_saveexec_b32 s4, s4
|
|
; CHECK-NEXT: image_sample v0, v[0:1], s[8:15], s[16:19] dmask:0x1 dim:SQ_RSRC_IMG_2D
|
|
; CHECK-NEXT: s_waitcnt vmcnt(0)
|
|
; CHECK-NEXT: buffer_store_dword v0, off, s[0:3], s32 offset:72 ; 4-byte Folded Spill
|
|
; CHECK-NEXT: s_xor_b32 exec_lo, exec_lo, s4
|
|
; CHECK-NEXT: s_cbranch_execnz .LBB0_1
|
|
; CHECK-NEXT: ; %bb.2:
|
|
; CHECK-NEXT: v_readlane_b32 s4, v15, 6
|
|
; CHECK-NEXT: s_mov_b32 exec_lo, s4
|
|
; CHECK-NEXT: ; %bb.3:
|
|
; CHECK-NEXT: v_readlane_b32 s4, v15, 0
|
|
; CHECK-NEXT: v_readlane_b32 s5, v15, 1
|
|
; CHECK-NEXT: buffer_load_dword v0, off, s[0:3], s32 offset:72 ; 4-byte Folded Reload
|
|
; CHECK-NEXT: ; implicit-def: $sgpr6
|
|
; CHECK-NEXT: v_mov_b32_e32 v1, s6
|
|
; CHECK-NEXT: v_mov_b32_e32 v2, s6
|
|
; CHECK-NEXT: v_mov_b32_e32 v3, s6
|
|
; CHECK-NEXT: s_or_saveexec_b32 s6, -1
|
|
; CHECK-NEXT: buffer_load_dword v15, off, s[0:3], s32 offset:76 ; 4-byte Folded Reload
|
|
; CHECK-NEXT: s_mov_b32 exec_lo, s6
|
|
; CHECK-NEXT: s_waitcnt vmcnt(0)
|
|
; CHECK-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; CHECK-NEXT: s_setpc_b64 s[4:5]
|
|
bb:
|
|
%ret = tail call <4 x float> @llvm.amdgcn.image.sample.2d.v4f32.f32(i32 1, float 0.000000e+00, float 0.000000e+00, <8 x i32> %vgpr_srd, <4 x i32> zeroinitializer, i1 false, i32 0, i32 0)
|
|
ret <4 x float> %ret
|
|
}
|
|
|
|
declare <4 x float> @llvm.amdgcn.image.sample.2d.v4f32.f32(i32 immarg, float, float, <8 x i32>, <4 x i32>, i1 immarg, i32 immarg, i32 immarg) #0
|
|
|
|
attributes #0 = { nounwind readonly willreturn }
|