maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/AMDGPU/skip-if-dead.ll

391 lines
10 KiB
LLVM
Raw Normal View History

AMDGPU: Fix verifier error with kill intrinsic Don't create a terminator in the middle of the block. We should probably get rid of this intrinsic. llvm-svn: 275203
2016-07-13 03:01:23 +08:00
; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck %s
; CHECK-LABEL: {{^}}test_kill_depth_0_imm_pos:
; CHECK-NEXT: ; BB#0:
; CHECK-NEXT: s_endpgm
define amdgpu_ps void @test_kill_depth_0_imm_pos() #0 {
call void @llvm.AMDGPU.kill(float 0.0)
ret void
}
; CHECK-LABEL: {{^}}test_kill_depth_0_imm_neg:
; CHECK-NEXT: ; BB#0:
; CHECK-NEXT: s_mov_b64 exec, 0
AMDGPU: Follow up to r275203 I meant to squash this into it. llvm-svn: 275220
2016-07-13 05:41:32 +08:00
; CHECK-NEXT: ; BB#1:
AMDGPU: Fix verifier error with kill intrinsic Don't create a terminator in the middle of the block. We should probably get rid of this intrinsic. llvm-svn: 275203
2016-07-13 03:01:23 +08:00
; CHECK-NEXT: s_endpgm
define amdgpu_ps void @test_kill_depth_0_imm_neg() #0 {
call void @llvm.AMDGPU.kill(float -0.0)
ret void
}
AMDGPU: Follow up to r275203 I meant to squash this into it. llvm-svn: 275220
2016-07-13 05:41:32 +08:00
; FIXME: Ideally only one would be emitted
; CHECK-LABEL: {{^}}test_kill_depth_0_imm_neg_x2:
; CHECK-NEXT: ; BB#0:
; CHECK-NEXT: s_mov_b64 exec, 0
; CHECK-NEXT: ; BB#1:
; CHECK-NEXT: s_mov_b64 exec, 0
; CHECK-NEXT: ; BB#2:
; CHECK-NEXT: s_endpgm
define amdgpu_ps void @test_kill_depth_0_imm_neg_x2() #0 {
call void @llvm.AMDGPU.kill(float -0.0)
call void @llvm.AMDGPU.kill(float -1.0)
ret void
}
AMDGPU: Fix verifier error with kill intrinsic Don't create a terminator in the middle of the block. We should probably get rid of this intrinsic. llvm-svn: 275203
2016-07-13 03:01:23 +08:00
; CHECK-LABEL: {{^}}test_kill_depth_var:
; CHECK-NEXT: ; BB#0:
; CHECK-NEXT: v_cmpx_le_f32_e32 vcc, 0, v0
AMDGPU: Follow up to r275203 I meant to squash this into it. llvm-svn: 275220
2016-07-13 05:41:32 +08:00
; CHECK-NEXT: ; BB#1:
AMDGPU: Fix verifier error with kill intrinsic Don't create a terminator in the middle of the block. We should probably get rid of this intrinsic. llvm-svn: 275203
2016-07-13 03:01:23 +08:00
; CHECK-NEXT: s_endpgm
define amdgpu_ps void @test_kill_depth_var(float %x) #0 {
call void @llvm.AMDGPU.kill(float %x)
ret void
}
AMDGPU: Follow up to r275203 I meant to squash this into it. llvm-svn: 275220
2016-07-13 05:41:32 +08:00
; FIXME: Ideally only one would be emitted
; CHECK-LABEL: {{^}}test_kill_depth_var_x2_same:
; CHECK-NEXT: ; BB#0:
; CHECK-NEXT: v_cmpx_le_f32_e32 vcc, 0, v0
; CHECK-NEXT: ; BB#1:
; CHECK-NEXT: v_cmpx_le_f32_e32 vcc, 0, v0
; CHECK-NEXT: ; BB#2:
; CHECK-NEXT: s_endpgm
define amdgpu_ps void @test_kill_depth_var_x2_same(float %x) #0 {
call void @llvm.AMDGPU.kill(float %x)
call void @llvm.AMDGPU.kill(float %x)
ret void
}
; CHECK-LABEL: {{^}}test_kill_depth_var_x2:
; CHECK-NEXT: ; BB#0:
; CHECK-NEXT: v_cmpx_le_f32_e32 vcc, 0, v0
; CHECK-NEXT: ; BB#1:
; CHECK-NEXT: v_cmpx_le_f32_e32 vcc, 0, v1
; CHECK-NEXT: ; BB#2:
; CHECK-NEXT: s_endpgm
define amdgpu_ps void @test_kill_depth_var_x2(float %x, float %y) #0 {
call void @llvm.AMDGPU.kill(float %x)
call void @llvm.AMDGPU.kill(float %y)
ret void
}
; CHECK-LABEL: {{^}}test_kill_depth_var_x2_instructions:
; CHECK-NEXT: ; BB#0:
; CHECK-NEXT: v_cmpx_le_f32_e32 vcc, 0, v0
; CHECK-NEXT: ; BB#1:
; CHECK: v_mov_b32_e64 v7, -1
; CHECK: v_cmpx_le_f32_e32 vcc, 0, v7
; CHECK-NEXT: ; BB#2:
; CHECK-NEXT: s_endpgm
define amdgpu_ps void @test_kill_depth_var_x2_instructions(float %x) #0 {
call void @llvm.AMDGPU.kill(float %x)
%y = call float asm sideeffect "v_mov_b32_e64 v7, -1", "={VGPR7}"()
call void @llvm.AMDGPU.kill(float %y)
ret void
}
AMDGPU: Fix verifier error with kill intrinsic Don't create a terminator in the middle of the block. We should probably get rid of this intrinsic. llvm-svn: 275203
2016-07-13 03:01:23 +08:00
; FIXME: why does the skip depend on the asm length in the same block?
; CHECK-LABEL: {{^}}test_kill_control_flow:
AMDGPU: Use unsigned compare for eq/ne For some reason there are both of these available, except for scalar 64-bit compares which only has u64. I'm not sure why there are both (I'm guessing it's for the one bit inputs we don't use), but for consistency always using the unsigned one. llvm-svn: 282832
2016-09-30 09:50:20 +08:00
; CHECK: s_cmp_lg_u32 s{{[0-9]+}}, 0
AMDGPU: Fix verifier error with kill intrinsic Don't create a terminator in the middle of the block. We should probably get rid of this intrinsic. llvm-svn: 275203
2016-07-13 03:01:23 +08:00
; CHECK: s_cbranch_scc1 [[RETURN_BB:BB[0-9]+_[0-9]+]]
AMDGPU: Follow up to r275203 I meant to squash this into it. llvm-svn: 275220
2016-07-13 05:41:32 +08:00
; CHECK-NEXT: ; BB#1:
; CHECK: v_mov_b32_e64 v7, -1
AMDGPU: Fix verifier error with kill intrinsic Don't create a terminator in the middle of the block. We should probably get rid of this intrinsic. llvm-svn: 275203
2016-07-13 03:01:23 +08:00
; CHECK: v_nop_e64
; CHECK: v_nop_e64
; CHECK: v_nop_e64
; CHECK: v_nop_e64
; CHECK: v_nop_e64
; CHECK: v_nop_e64
; CHECK: v_nop_e64
; CHECK: v_nop_e64
; CHECK: v_nop_e64
; CHECK: v_nop_e64
AMDGPU: Follow up to r275203 I meant to squash this into it. llvm-svn: 275220
2016-07-13 05:41:32 +08:00
; CHECK: v_cmpx_le_f32_e32 vcc, 0, v7
; CHECK-NEXT: s_cbranch_execnz [[SPLIT_BB:BB[0-9]+_[0-9]+]]
BranchRelaxation: Support expanding unconditional branches AMDGPU needs to expand unconditional branches in a new block with an indirect branch. llvm-svn: 283464
2016-10-07 00:20:41 +08:00
; CHECK-NEXT: ; BB#2:
AMDGPU: Fix verifier error with kill intrinsic Don't create a terminator in the middle of the block. We should probably get rid of this intrinsic. llvm-svn: 275203
2016-07-13 03:01:23 +08:00
; CHECK-NEXT: exp 0, 9, 0, 1, 1, v0, v0, v0, v0
; CHECK-NEXT: s_endpgm
; CHECK-NEXT: {{^}}[[SPLIT_BB]]:
; CHECK-NEXT: s_endpgm
define amdgpu_ps void @test_kill_control_flow(i32 inreg %arg) #0 {
entry:
%cmp = icmp eq i32 %arg, 0
br i1 %cmp, label %bb, label %exit
bb:
%var = call float asm sideeffect "
v_mov_b32_e64 v7, -1
v_nop_e64
v_nop_e64
v_nop_e64
v_nop_e64
v_nop_e64
v_nop_e64
v_nop_e64
v_nop_e64
v_nop_e64
v_nop_e64", "={VGPR7}"()
call void @llvm.AMDGPU.kill(float %var)
br label %exit
exit:
ret void
}
; CHECK-LABEL: {{^}}test_kill_control_flow_remainder:
AMDGPU: Use unsigned compare for eq/ne For some reason there are both of these available, except for scalar 64-bit compares which only has u64. I'm not sure why there are both (I'm guessing it's for the one bit inputs we don't use), but for consistency always using the unsigned one. llvm-svn: 282832
2016-09-30 09:50:20 +08:00
; CHECK: s_cmp_lg_u32 s{{[0-9]+}}, 0
ScheduleDAGInstrs: Add condjump deps to addSchedBarrierDeps() addSchedBarrierDeps() is supposed to add use operands to the ExitSU node. The current implementation adds uses for calls/barrier instruction and the MBB live-outs in all other cases. The use operands of conditional jump instructions were missed. Also added code to macrofusion to set the latencies between nodes to zero to avoid problems with the fusing nodes lingering around in the pending list now. Differential Revision: https://reviews.llvm.org/D25140 llvm-svn: 286544
2016-11-11 09:34:21 +08:00
; CHECK-NEXT: v_mov_b32_e32 v{{[0-9]+}}, 0
AMDGPU: Fix verifier error with kill intrinsic Don't create a terminator in the middle of the block. We should probably get rid of this intrinsic. llvm-svn: 275203
2016-07-13 03:01:23 +08:00
; CHECK-NEXT: s_cbranch_scc1 [[RETURN_BB:BB[0-9]+_[0-9]+]]
; CHECK-NEXT: ; BB#1: ; %bb
; CHECK: v_mov_b32_e64 v7, -1
; CHECK: v_nop_e64
; CHECK: v_nop_e64
; CHECK: v_nop_e64
; CHECK: v_nop_e64
; CHECK: v_nop_e64
; CHECK: v_nop_e64
; CHECK: v_nop_e64
; CHECK: v_nop_e64
; CHECK: ;;#ASMEND
; CHECK: v_mov_b32_e64 v8, -1
; CHECK: ;;#ASMEND
AMDGPU: Follow up to r275203 I meant to squash this into it. llvm-svn: 275220
2016-07-13 05:41:32 +08:00
; CHECK: v_cmpx_le_f32_e32 vcc, 0, v7
AMDGPU: Fix verifier error with kill intrinsic Don't create a terminator in the middle of the block. We should probably get rid of this intrinsic. llvm-svn: 275203
2016-07-13 03:01:23 +08:00
; CHECK-NEXT: s_cbranch_execnz [[SPLIT_BB:BB[0-9]+_[0-9]+]]
BranchRelaxation: Support expanding unconditional branches AMDGPU needs to expand unconditional branches in a new block with an indirect branch. llvm-svn: 283464
2016-10-07 00:20:41 +08:00
; CHECK-NEXT: ; BB#2:
AMDGPU: Fix verifier error with kill intrinsic Don't create a terminator in the middle of the block. We should probably get rid of this intrinsic. llvm-svn: 275203
2016-07-13 03:01:23 +08:00
; CHECK-NEXT: exp 0, 9, 0, 1, 1, v0, v0, v0, v0
; CHECK-NEXT: s_endpgm
; CHECK-NEXT: {{^}}[[SPLIT_BB]]:
; CHECK: buffer_store_dword v8
; CHECK: v_mov_b32_e64 v9, -2
; CHECK: {{^}}BB{{[0-9]+_[0-9]+}}:
; CHECK: buffer_store_dword v9
; CHECK-NEXT: s_endpgm
define amdgpu_ps void @test_kill_control_flow_remainder(i32 inreg %arg) #0 {
entry:
%cmp = icmp eq i32 %arg, 0
br i1 %cmp, label %bb, label %exit
bb:
%var = call float asm sideeffect "
v_mov_b32_e64 v7, -1
v_nop_e64
v_nop_e64
v_nop_e64
v_nop_e64
v_nop_e64
v_nop_e64
v_nop_e64
v_nop_e64
v_nop_e64
v_nop_e64
v_nop_e64", "={VGPR7}"()
%live.across = call float asm sideeffect "v_mov_b32_e64 v8, -1", "={VGPR8}"()
call void @llvm.AMDGPU.kill(float %var)
store volatile float %live.across, float addrspace(1)* undef
%live.out = call float asm sideeffect "v_mov_b32_e64 v9, -2", "={VGPR9}"()
br label %exit
exit:
%phi = phi float [ 0.0, %entry ], [ %live.out, %bb ]
store float %phi, float addrspace(1)* undef
ret void
}
AMDGPU: Follow up to r275203 I meant to squash this into it. llvm-svn: 275220
2016-07-13 05:41:32 +08:00
; CHECK-LABEL: {{^}}test_kill_divergent_loop:
AMDGPU: Use unsigned compare for eq/ne For some reason there are both of these available, except for scalar 64-bit compares which only has u64. I'm not sure why there are both (I'm guessing it's for the one bit inputs we don't use), but for consistency always using the unsigned one. llvm-svn: 282832
2016-09-30 09:50:20 +08:00
; CHECK: v_cmp_eq_u32_e32 vcc, 0, v0
AMDGPU: Follow up to r275203 I meant to squash this into it. llvm-svn: 275220
2016-07-13 05:41:32 +08:00
; CHECK-NEXT: s_and_saveexec_b64 [[SAVEEXEC:s\[[0-9]+:[0-9]+\]]], vcc
; CHECK-NEXT: s_xor_b64 [[SAVEEXEC]], exec, [[SAVEEXEC]]
AMDGPU: Change insertion point of si_mask_branch Insert before the skip branch if one is created. This is a somewhat more natural placement relative to the skip branches, and makes it possible to implement analyzeBranch for skip blocks. The test changes are mostly due to a quirk where the block label is not emitted if there is a terminator that is not also a branch. llvm-svn: 278273
2016-08-11 03:11:42 +08:00
; CHECK-NEXT: ; mask branch [[EXIT:BB[0-9]+_[0-9]+]]
; CHECK-NEXT: s_cbranch_execz [[EXIT]]
; CHECK: {{BB[0-9]+_[0-9]+}}: ; %bb.preheader
; CHECK: s_mov_b32
AMDGPU: Follow up to r275203 I meant to squash this into it. llvm-svn: 275220
2016-07-13 05:41:32 +08:00
; CHECK: [[LOOP_BB:BB[0-9]+_[0-9]+]]:
; CHECK: v_mov_b32_e64 v7, -1
; CHECK: v_nop_e64
; CHECK: v_cmpx_le_f32_e32 vcc, 0, v7
; CHECK-NEXT: ; BB#3:
; CHECK: buffer_load_dword [[LOAD:v[0-9]+]]
AMDGPU: Use unsigned compare for eq/ne For some reason there are both of these available, except for scalar 64-bit compares which only has u64. I'm not sure why there are both (I'm guessing it's for the one bit inputs we don't use), but for consistency always using the unsigned one. llvm-svn: 282832
2016-09-30 09:50:20 +08:00
; CHECK: v_cmp_eq_u32_e32 vcc, 0, [[LOAD]]
AMDGPU: Follow up to r275203 I meant to squash this into it. llvm-svn: 275220
2016-07-13 05:41:32 +08:00
; CHECK-NEXT: s_and_b64 vcc, exec, vcc
; CHECK-NEXT: s_cbranch_vccnz [[LOOP_BB]]
; CHECK-NEXT: {{^}}[[EXIT]]:
; CHECK: s_or_b64 exec, exec, [[SAVEEXEC]]
; CHECK: buffer_store_dword
; CHECK: s_endpgm
define amdgpu_ps void @test_kill_divergent_loop(i32 %arg) #0 {
entry:
%cmp = icmp eq i32 %arg, 0
br i1 %cmp, label %bb, label %exit
bb:
%var = call float asm sideeffect "
v_mov_b32_e64 v7, -1
v_nop_e64
v_nop_e64
v_nop_e64
v_nop_e64
v_nop_e64
v_nop_e64
v_nop_e64
v_nop_e64
v_nop_e64
v_nop_e64", "={VGPR7}"()
call void @llvm.AMDGPU.kill(float %var)
%vgpr = load volatile i32, i32 addrspace(1)* undef
%loop.cond = icmp eq i32 %vgpr, 0
br i1 %loop.cond, label %bb, label %exit
exit:
store volatile i32 8, i32 addrspace(1)* undef
ret void
}
AMDGPU: Fix splitting kill blocks with defs before kill llvm-svn: 275508
2016-07-15 08:58:09 +08:00
; bug 28550
; CHECK-LABEL: {{^}}phi_use_def_before_kill:
; CHECK: v_cndmask_b32_e64 [[PHIREG:v[0-9]+]], 0, -1.0,
; CHECK: v_cmpx_le_f32_e32 vcc, 0,
; CHECK-NEXT: s_cbranch_execnz [[BB4:BB[0-9]+_[0-9]+]]
; CHECK: exp
; CHECK-NEXT: s_endpgm
; CHECK: [[KILLBB:BB[0-9]+_[0-9]+]]:
; CHECK-NEXT: s_cbranch_vccz [[PHIBB:BB[0-9]+_[0-9]+]]
; CHECK: [[PHIBB]]:
; CHECK: v_cmp_eq_f32_e32 vcc, 0, [[PHIREG]]
AMDGPU: Remove unnecessary and on conditional branch The comment explaining why this was necessary is incorrect in its description of v_cmp's behavior for inactive workitems. llvm-svn: 286134
2016-11-08 03:09:33 +08:00
; CHECK-NEXT: s_cbranch_vccz [[ENDBB:BB[0-9]+_[0-9]+]]
AMDGPU: Fix splitting kill blocks with defs before kill llvm-svn: 275508
2016-07-15 08:58:09 +08:00
BranchRelaxation: Support expanding unconditional branches AMDGPU needs to expand unconditional branches in a new block with an indirect branch. llvm-svn: 283464
2016-10-07 00:20:41 +08:00
; CHECK: ; %bb10
AMDGPU: Fix splitting kill blocks with defs before kill llvm-svn: 275508
2016-07-15 08:58:09 +08:00
; CHECK: v_mov_b32_e32 v{{[0-9]+}}, 9
; CHECK: buffer_store_dword
; CHECK: [[ENDBB]]:
; CHECK-NEXT: s_endpgm
define amdgpu_ps void @phi_use_def_before_kill() #0 {
bb:
%tmp = fadd float undef, 1.000000e+00
%tmp1 = fcmp olt float 0.000000e+00, %tmp
%tmp2 = select i1 %tmp1, float -1.000000e+00, float 0.000000e+00
call void @llvm.AMDGPU.kill(float %tmp2)
br i1 undef, label %phibb, label %bb8
phibb:
%tmp5 = phi float [ %tmp2, %bb ], [ 4.0, %bb8 ]
%tmp6 = fcmp oeq float %tmp5, 0.000000e+00
br i1 %tmp6, label %bb10, label %end
bb8:
store volatile i32 8, i32 addrspace(1)* undef
br label %phibb
bb10:
store volatile i32 9, i32 addrspace(1)* undef
br label %end
end:
ret void
}
AMDGPU: Follow up to r275203 I meant to squash this into it. llvm-svn: 275220
2016-07-13 05:41:32 +08:00
AMDGPU: Fix trying to skip from a block with no successors Found while reducing bug 28550 llvm-svn: 275509
2016-07-15 08:58:13 +08:00
; CHECK-LABEL: {{^}}no_skip_no_successors:
AMDGPU: Support commuting with immediate in src0 llvm-svn: 280970
2016-09-09 01:19:29 +08:00
; CHECK: v_cmp_nge_f32
AMDGPU: Remove unnecessary and on conditional branch The comment explaining why this was necessary is incorrect in its description of v_cmp's behavior for inactive workitems. llvm-svn: 286134
2016-11-08 03:09:33 +08:00
; CHECK-NEXT: s_cbranch_vccz [[SKIPKILL:BB[0-9]+_[0-9]+]]
AMDGPU: Fix trying to skip from a block with no successors Found while reducing bug 28550 llvm-svn: 275509
2016-07-15 08:58:13 +08:00
BranchRelaxation: Support expanding unconditional branches AMDGPU needs to expand unconditional branches in a new block with an indirect branch. llvm-svn: 283464
2016-10-07 00:20:41 +08:00
; CHECK: ; %bb6
AMDGPU: Fix trying to skip from a block with no successors Found while reducing bug 28550 llvm-svn: 275509
2016-07-15 08:58:13 +08:00
; CHECK: s_mov_b64 exec, 0
; CHECK: [[SKIPKILL]]:
; CHECK: v_cmp_nge_f32
AMDGPU: Remove unnecessary and on conditional branch The comment explaining why this was necessary is incorrect in its description of v_cmp's behavior for inactive workitems. llvm-svn: 286134
2016-11-08 03:09:33 +08:00
; CHECK-NEXT: s_cbranch_vccz [[UNREACHABLE:BB[0-9]+_[0-9]+]]
AMDGPU: Fix trying to skip from a block with no successors Found while reducing bug 28550 llvm-svn: 275509
2016-07-15 08:58:13 +08:00
; CHECK: [[UNREACHABLE]]:
; CHECK-NEXT: .Lfunc_end{{[0-9]+}}
define amdgpu_ps void @no_skip_no_successors(float inreg %arg, float inreg %arg1) #0 {
bb:
%tmp = fcmp ult float %arg1, 0.000000e+00
%tmp2 = fcmp ult float %arg, 0x3FCF5C2900000000
br i1 %tmp, label %bb6, label %bb3
bb3: ; preds = %bb
br i1 %tmp2, label %bb5, label %bb4
bb4: ; preds = %bb3
br i1 true, label %bb5, label %bb7
bb5: ; preds = %bb4, %bb3
unreachable
bb6: ; preds = %bb
call void @llvm.AMDGPU.kill(float -1.000000e+00)
unreachable
bb7: ; preds = %bb4
ret void
}
AMDGPU: Fix not expanding control flow after some kill blocks Also stop trying to insert skip blocks at end_cf. This was inserting them at the end of the block which doesn't make sense. The skip should be inserted at the beginning of the block right after the end cf. Just remove this for now since no tests seem to stress this and I think this can be handled more generally later. Fixes bug 28550 llvm-svn: 275510
2016-07-15 08:58:15 +08:00
; CHECK-LABEL: {{^}}if_after_kill_block:
; CHECK: ; BB#0:
; CHECK: s_and_saveexec_b64
; CHECK: s_xor_b64
; CHECK-NEXT: mask branch [[BB4:BB[0-9]+_[0-9]+]]
; CHECK: v_cmpx_le_f32_e32 vcc, 0,
; CHECK: [[BB4]]:
; CHECK: s_or_b64 exec, exec
; CHECK: image_sample_c
; CHECK: v_cmp_neq_f32_e32 vcc, 0,
; CHECK: s_and_saveexec_b64 s{{\[[0-9]+:[0-9]+\]}}, vcc
; CHECK: s_xor_b64 s{{\[[0-9]+:[0-9]+\]}}, exec
; CHECK: mask branch [[END:BB[0-9]+_[0-9]+]]
; CHECK-NOT: branch
AMDGPU: Change insertion point of si_mask_branch Insert before the skip branch if one is created. This is a somewhat more natural placement relative to the skip branches, and makes it possible to implement analyzeBranch for skip blocks. The test changes are mostly due to a quirk where the block label is not emitted if there is a terminator that is not also a branch. llvm-svn: 278273
2016-08-11 03:11:42 +08:00
; CHECK: BB{{[0-9]+_[0-9]+}}: ; %bb8
AMDGPU: Fix not expanding control flow after some kill blocks Also stop trying to insert skip blocks at end_cf. This was inserting them at the end of the block which doesn't make sense. The skip should be inserted at the beginning of the block right after the end cf. Just remove this for now since no tests seem to stress this and I think this can be handled more generally later. Fixes bug 28550 llvm-svn: 275510
2016-07-15 08:58:15 +08:00
; CHECK: buffer_store_dword
; CHECK: [[END]]:
; CHECK: s_or_b64 exec, exec
; CHECK: s_endpgm
define amdgpu_ps void @if_after_kill_block(float %arg, float %arg1, <4 x i32> %arg2) #0 {
bb:
%tmp = fcmp ult float %arg1, 0.000000e+00
br i1 %tmp, label %bb3, label %bb4
bb3: ; preds = %bb
call void @llvm.AMDGPU.kill(float %arg)
br label %bb4
bb4: ; preds = %bb3, %bb
%tmp5 = call <4 x float> @llvm.SI.image.sample.c.v4i32(<4 x i32> %arg2, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)
%tmp6 = extractelement <4 x float> %tmp5, i32 0
%tmp7 = fcmp une float %tmp6, 0.000000e+00
br i1 %tmp7, label %bb8, label %bb9
bb8: ; preds = %bb9, %bb4
store volatile i32 9, i32 addrspace(1)* undef
ret void
bb9: ; preds = %bb4
ret void
}
AMDGPU: Fix verifier error with kill intrinsic Don't create a terminator in the middle of the block. We should probably get rid of this intrinsic. llvm-svn: 275203
2016-07-13 03:01:23 +08:00
declare void @llvm.AMDGPU.kill(float) #0
AMDGPU: Fix not expanding control flow after some kill blocks Also stop trying to insert skip blocks at end_cf. This was inserting them at the end of the block which doesn't make sense. The skip should be inserted at the beginning of the block right after the end cf. Just remove this for now since no tests seem to stress this and I think this can be handled more generally later. Fixes bug 28550 llvm-svn: 275510
2016-07-15 08:58:15 +08:00
declare <4 x float> @llvm.SI.image.sample.c.v4i32(<4 x i32>, <8 x i32>, <4 x i32>, i32, i32, i32, i32, i32, i32, i32, i32) #1
AMDGPU: Stay in WQM for non-intrinsic stores Summary: Two types of stores are possible in pixel shaders: stores to memory that are explicitly requested at the API level, and stores that are an implementation detail of register spilling or lowering of arrays. For the first kind of store, we must ensure that helper pixels have no effect and hence WQM must be disabled. The second kind of store must always be executed, because the written value may be loaded again in a way that is relevant for helper pixels as well -- and there are no externally visible effects anyway. This is a candidate for the 3.9 release branch. Reviewers: arsenm, tstellarAMD, mareko Subscribers: arsenm, kzhuravl, llvm-commits Differential Revision: https://reviews.llvm.org/D22675 llvm-svn: 277504
2016-08-03 03:31:14 +08:00
declare void @llvm.amdgcn.buffer.store.f32(float, <4 x i32>, i32, i32, i1, i1) nounwind
AMDGPU: Fix verifier error with kill intrinsic Don't create a terminator in the middle of the block. We should probably get rid of this intrinsic. llvm-svn: 275203
2016-07-13 03:01:23 +08:00
attributes #0 = { nounwind }
AMDGPU: Change insertion point of si_mask_branch Insert before the skip branch if one is created. This is a somewhat more natural placement relative to the skip branches, and makes it possible to implement analyzeBranch for skip blocks. The test changes are mostly due to a quirk where the block label is not emitted if there is a terminator that is not also a branch. llvm-svn: 278273
2016-08-11 03:11:42 +08:00
attributes #1 = { nounwind readnone }