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/early-if-convert.ll

455 lines
12 KiB
LLVM
Raw Normal View History

[AMDGPU] Switch scalarize global loads ON by default Differential revision: https://reviews.llvm.org/D34407 llvm-svn: 307097
2017-07-05 01:32:00 +08:00
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=verde -amdgpu-early-ifcvt=1 -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
AMDGPU: Implement early ifcvt target hooks. Leave early ifcvt disabled for now since there are some shader-db regressions. This causes some immediate improvements, but could be better. The cost checking that the pass does is based on critical path length for out of order CPUs which we do not want so it skips out on many cases we want. llvm-svn: 293016
2017-01-25 12:25:02 +08:00
; XUN: llc -march=amdgcn -mcpu=tonga -amdgpu-early-ifcvt=1 -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
; FIXME: This leaves behind a now unnecessary and with exec
; GCN-LABEL: {{^}}test_vccnz_ifcvt_triangle:
; GCN: buffer_load_dword [[VAL:v[0-9]+]]
; GCN: v_cmp_neq_f32_e32 vcc, 1.0, [[VAL]]
; GCN: v_add_f32_e32 [[ADD:v[0-9]+]], [[VAL]], [[VAL]]
; GCN: v_cndmask_b32_e32 [[RESULT:v[0-9]+]], [[ADD]], [[VAL]], vcc
; GCN: buffer_store_dword [[RESULT]]
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_vccnz_ifcvt_triangle(float addrspace(1)* %out, float addrspace(1)* %in) #0 {
AMDGPU: Implement early ifcvt target hooks. Leave early ifcvt disabled for now since there are some shader-db regressions. This causes some immediate improvements, but could be better. The cost checking that the pass does is based on critical path length for out of order CPUs which we do not want so it skips out on many cases we want. llvm-svn: 293016
2017-01-25 12:25:02 +08:00
entry:
%v = load float, float addrspace(1)* %in
%cc = fcmp oeq float %v, 1.000000e+00
br i1 %cc, label %if, label %endif
if:
%u = fadd float %v, %v
br label %endif
endif:
%r = phi float [ %v, %entry ], [ %u, %if ]
store float %r, float addrspace(1)* %out
ret void
}
; GCN-LABEL: {{^}}test_vccnz_ifcvt_diamond:
; GCN: buffer_load_dword [[VAL:v[0-9]+]]
; GCN: v_cmp_neq_f32_e32 vcc, 1.0, [[VAL]]
; GCN-DAG: v_add_f32_e32 [[ADD:v[0-9]+]], [[VAL]], [[VAL]]
; GCN-DAG: v_mul_f32_e32 [[MUL:v[0-9]+]], [[VAL]], [[VAL]]
; GCN: v_cndmask_b32_e32 [[RESULT:v[0-9]+]], [[ADD]], [[MUL]], vcc
; GCN: buffer_store_dword [[RESULT]]
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_vccnz_ifcvt_diamond(float addrspace(1)* %out, float addrspace(1)* %in) #0 {
AMDGPU: Implement early ifcvt target hooks. Leave early ifcvt disabled for now since there are some shader-db regressions. This causes some immediate improvements, but could be better. The cost checking that the pass does is based on critical path length for out of order CPUs which we do not want so it skips out on many cases we want. llvm-svn: 293016
2017-01-25 12:25:02 +08:00
entry:
%v = load float, float addrspace(1)* %in
%cc = fcmp oeq float %v, 1.000000e+00
br i1 %cc, label %if, label %else
if:
%u0 = fadd float %v, %v
br label %endif
else:
%u1 = fmul float %v, %v
br label %endif
endif:
%r = phi float [ %u0, %if ], [ %u1, %else ]
store float %r, float addrspace(1)* %out
ret void
}
; GCN-LABEL: {{^}}test_vccnz_ifcvt_triangle_vcc_clobber:
; GCN: ; clobber vcc
; GCN: v_cmp_neq_f32_e64 [[CMP:s\[[0-9]+:[0-9]+\]]], s{{[0-9]+}}, 1.0
; GCN: v_add_i32_e32 v{{[0-9]+}}, vcc
; GCN: s_mov_b64 vcc, [[CMP]]
; GCN: v_cndmask_b32_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}, vcc
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_vccnz_ifcvt_triangle_vcc_clobber(i32 addrspace(1)* %out, i32 addrspace(1)* %in, float %k) #0 {
AMDGPU: Implement early ifcvt target hooks. Leave early ifcvt disabled for now since there are some shader-db regressions. This causes some immediate improvements, but could be better. The cost checking that the pass does is based on critical path length for out of order CPUs which we do not want so it skips out on many cases we want. llvm-svn: 293016
2017-01-25 12:25:02 +08:00
entry:
%v = load i32, i32 addrspace(1)* %in
%cc = fcmp oeq float %k, 1.000000e+00
br i1 %cc, label %if, label %endif
if:
call void asm "; clobber $0", "~{VCC}"() #0
%u = add i32 %v, %v
br label %endif
endif:
%r = phi i32 [ %v, %entry ], [ %u, %if ]
store i32 %r, i32 addrspace(1)* %out
ret void
}
; Longest chain of cheap instructions to convert
; GCN-LABEL: {{^}}test_vccnz_ifcvt_triangle_max_cheap:
; GCN: v_mul_f32
; GCN: v_mul_f32
; GCN: v_mul_f32
; GCN: v_mul_f32
; GCN: v_mul_f32
; GCN: v_mul_f32
; GCN: v_mul_f32
; GCN: v_mul_f32
; GCN: v_mul_f32
; GCN: v_cndmask_b32_e32
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_vccnz_ifcvt_triangle_max_cheap(float addrspace(1)* %out, float addrspace(1)* %in) #0 {
AMDGPU: Implement early ifcvt target hooks. Leave early ifcvt disabled for now since there are some shader-db regressions. This causes some immediate improvements, but could be better. The cost checking that the pass does is based on critical path length for out of order CPUs which we do not want so it skips out on many cases we want. llvm-svn: 293016
2017-01-25 12:25:02 +08:00
entry:
%v = load float, float addrspace(1)* %in
%cc = fcmp oeq float %v, 1.000000e+00
br i1 %cc, label %if, label %endif
if:
%u.0 = fmul float %v, %v
%u.1 = fmul float %v, %u.0
%u.2 = fmul float %v, %u.1
%u.3 = fmul float %v, %u.2
%u.4 = fmul float %v, %u.3
%u.5 = fmul float %v, %u.4
%u.6 = fmul float %v, %u.5
%u.7 = fmul float %v, %u.6
%u.8 = fmul float %v, %u.7
br label %endif
endif:
%r = phi float [ %v, %entry ], [ %u.8, %if ]
store float %r, float addrspace(1)* %out
ret void
}
; Short chain of cheap instructions to not convert
; GCN-LABEL: {{^}}test_vccnz_ifcvt_triangle_min_expensive:
; GCN: s_cbranch_vccnz [[ENDIF:BB[0-9]+_[0-9]+]]
; GCN: v_mul_f32
; GCN: v_mul_f32
; GCN: v_mul_f32
; GCN: v_mul_f32
; GCN: v_mul_f32
; GCN: v_mul_f32
; GCN: v_mul_f32
; GCN: v_mul_f32
; GCN: v_mul_f32
; GCN: v_mul_f32
; GCN: [[ENDIF]]:
; GCN: buffer_store_dword
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_vccnz_ifcvt_triangle_min_expensive(float addrspace(1)* %out, float addrspace(1)* %in) #0 {
AMDGPU: Implement early ifcvt target hooks. Leave early ifcvt disabled for now since there are some shader-db regressions. This causes some immediate improvements, but could be better. The cost checking that the pass does is based on critical path length for out of order CPUs which we do not want so it skips out on many cases we want. llvm-svn: 293016
2017-01-25 12:25:02 +08:00
entry:
%v = load float, float addrspace(1)* %in
%cc = fcmp oeq float %v, 1.000000e+00
br i1 %cc, label %if, label %endif
if:
%u.0 = fmul float %v, %v
%u.1 = fmul float %v, %u.0
%u.2 = fmul float %v, %u.1
%u.3 = fmul float %v, %u.2
%u.4 = fmul float %v, %u.3
%u.5 = fmul float %v, %u.4
%u.6 = fmul float %v, %u.5
%u.7 = fmul float %v, %u.6
%u.8 = fmul float %v, %u.7
%u.9 = fmul float %v, %u.8
br label %endif
endif:
%r = phi float [ %v, %entry ], [ %u.9, %if ]
store float %r, float addrspace(1)* %out
ret void
}
; Should still branch over fdiv expansion
; GCN-LABEL: {{^}}test_vccnz_ifcvt_triangle_expensive:
; GCN: v_cmp_neq_f32_e32
; GCN: s_cbranch_vccnz [[ENDIF:BB[0-9]+_[0-9]+]]
; GCN: v_div_scale_f32
; GCN: [[ENDIF]]:
; GCN: buffer_store_dword
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_vccnz_ifcvt_triangle_expensive(float addrspace(1)* %out, float addrspace(1)* %in) #0 {
AMDGPU: Implement early ifcvt target hooks. Leave early ifcvt disabled for now since there are some shader-db regressions. This causes some immediate improvements, but could be better. The cost checking that the pass does is based on critical path length for out of order CPUs which we do not want so it skips out on many cases we want. llvm-svn: 293016
2017-01-25 12:25:02 +08:00
entry:
%v = load float, float addrspace(1)* %in
%cc = fcmp oeq float %v, 1.000000e+00
br i1 %cc, label %if, label %endif
if:
%u = fdiv float %v, %v
br label %endif
endif:
%r = phi float [ %v, %entry ], [ %u, %if ]
store float %r, float addrspace(1)* %out
ret void
}
; vcc branch with SGPR inputs
; GCN-LABEL: {{^}}test_vccnz_sgpr_ifcvt_triangle:
; GCN: v_cmp_neq_f32_e64
; GCN: s_cbranch_vccnz [[ENDIF:BB[0-9]+_[0-9]+]]
; GCN: s_add_i32
; GCN: [[ENDIF]]:
; GCN: buffer_store_dword
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_vccnz_sgpr_ifcvt_triangle(i32 addrspace(1)* %out, i32 addrspace(2)* %in, float %cnd) #0 {
AMDGPU: Implement early ifcvt target hooks. Leave early ifcvt disabled for now since there are some shader-db regressions. This causes some immediate improvements, but could be better. The cost checking that the pass does is based on critical path length for out of order CPUs which we do not want so it skips out on many cases we want. llvm-svn: 293016
2017-01-25 12:25:02 +08:00
entry:
%v = load i32, i32 addrspace(2)* %in
%cc = fcmp oeq float %cnd, 1.000000e+00
br i1 %cc, label %if, label %endif
if:
%u = add i32 %v, %v
br label %endif
endif:
%r = phi i32 [ %v, %entry ], [ %u, %if ]
store i32 %r, i32 addrspace(1)* %out
ret void
}
; GCN-LABEL: {{^}}test_vccnz_ifcvt_triangle_constant_load:
; GCN: v_cndmask_b32
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_vccnz_ifcvt_triangle_constant_load(float addrspace(1)* %out, float addrspace(2)* %in) #0 {
AMDGPU: Implement early ifcvt target hooks. Leave early ifcvt disabled for now since there are some shader-db regressions. This causes some immediate improvements, but could be better. The cost checking that the pass does is based on critical path length for out of order CPUs which we do not want so it skips out on many cases we want. llvm-svn: 293016
2017-01-25 12:25:02 +08:00
entry:
%v = load float, float addrspace(2)* %in
%cc = fcmp oeq float %v, 1.000000e+00
br i1 %cc, label %if, label %endif
if:
%u = fadd float %v, %v
br label %endif
endif:
%r = phi float [ %v, %entry ], [ %u, %if ]
store float %r, float addrspace(1)* %out
ret void
}
; Due to broken cost heuristic, this is not if converted like
; test_vccnz_ifcvt_triangle_constant_load even though it should be.
; GCN-LABEL: {{^}}test_vccnz_ifcvt_triangle_argload:
; GCN: v_cndmask_b32
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_vccnz_ifcvt_triangle_argload(float addrspace(1)* %out, float %v) #0 {
AMDGPU: Implement early ifcvt target hooks. Leave early ifcvt disabled for now since there are some shader-db regressions. This causes some immediate improvements, but could be better. The cost checking that the pass does is based on critical path length for out of order CPUs which we do not want so it skips out on many cases we want. llvm-svn: 293016
2017-01-25 12:25:02 +08:00
entry:
%cc = fcmp oeq float %v, 1.000000e+00
br i1 %cc, label %if, label %endif
if:
%u = fadd float %v, %v
br label %endif
endif:
%r = phi float [ %v, %entry ], [ %u, %if ]
store float %r, float addrspace(1)* %out
ret void
}
; Scalar branch and scalar inputs
; GCN-LABEL: {{^}}test_scc1_sgpr_ifcvt_triangle:
; GCN: s_load_dword [[VAL:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0x0
; GCN: s_add_i32 [[ADD:s[0-9]+]], [[VAL]], [[VAL]]
; GCN: s_cmp_lg_u32 s{{[0-9]+}}, 1
; GCN-NEXT: s_cselect_b32 [[SELECT:s[0-9]+]], [[ADD]], [[VAL]]
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_scc1_sgpr_ifcvt_triangle(i32 addrspace(2)* %in, i32 %cond) #0 {
AMDGPU: Implement early ifcvt target hooks. Leave early ifcvt disabled for now since there are some shader-db regressions. This causes some immediate improvements, but could be better. The cost checking that the pass does is based on critical path length for out of order CPUs which we do not want so it skips out on many cases we want. llvm-svn: 293016
2017-01-25 12:25:02 +08:00
entry:
%v = load i32, i32 addrspace(2)* %in
%cc = icmp eq i32 %cond, 1
br i1 %cc, label %if, label %endif
if:
%u = add i32 %v, %v
br label %endif
endif:
%r = phi i32 [ %v, %entry ], [ %u, %if ]
call void asm sideeffect "; reg use $0", "s"(i32 %r) #0
ret void
}
; FIXME: Should be able to use VALU compare and select
; Scalar branch but VGPR select operands
; GCN-LABEL: {{^}}test_scc1_vgpr_ifcvt_triangle:
; GCN: s_cmp_lg_u32
; GCN: s_cbranch_scc1 [[ENDIF:BB[0-9]+_[0-9]+]]
; GCN: v_add_f32_e32
; GCN: [[ENDIF]]:
; GCN: buffer_store_dword
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_scc1_vgpr_ifcvt_triangle(float addrspace(1)* %out, float addrspace(1)* %in, i32 %cond) #0 {
AMDGPU: Implement early ifcvt target hooks. Leave early ifcvt disabled for now since there are some shader-db regressions. This causes some immediate improvements, but could be better. The cost checking that the pass does is based on critical path length for out of order CPUs which we do not want so it skips out on many cases we want. llvm-svn: 293016
2017-01-25 12:25:02 +08:00
entry:
%v = load float, float addrspace(1)* %in
%cc = icmp eq i32 %cond, 1
br i1 %cc, label %if, label %endif
if:
%u = fadd float %v, %v
br label %endif
endif:
%r = phi float [ %v, %entry ], [ %u, %if ]
store float %r, float addrspace(1)* %out
ret void
}
; GCN-LABEL: {{^}}test_scc1_sgpr_ifcvt_triangle64:
; GCN: s_add_u32
; GCN: s_addc_u32
; GCN: s_cmp_lg_u32 s{{[0-9]+}}, 1
; GCN-NEXT: s_cselect_b64 s{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_scc1_sgpr_ifcvt_triangle64(i64 addrspace(2)* %in, i32 %cond) #0 {
AMDGPU: Implement early ifcvt target hooks. Leave early ifcvt disabled for now since there are some shader-db regressions. This causes some immediate improvements, but could be better. The cost checking that the pass does is based on critical path length for out of order CPUs which we do not want so it skips out on many cases we want. llvm-svn: 293016
2017-01-25 12:25:02 +08:00
entry:
%v = load i64, i64 addrspace(2)* %in
%cc = icmp eq i32 %cond, 1
br i1 %cc, label %if, label %endif
if:
%u = add i64 %v, %v
br label %endif
endif:
%r = phi i64 [ %v, %entry ], [ %u, %if ]
call void asm sideeffect "; reg use $0", "s"(i64 %r) #0
ret void
}
; TODO: Can do s_cselect_b64; s_cselect_b32
; GCN-LABEL: {{^}}test_scc1_sgpr_ifcvt_triangle96:
; GCN: s_add_i32
; GCN: s_add_i32
; GCN: s_add_i32
; GCN: s_add_i32
; GCN: s_cmp_lg_u32 s{{[0-9]+}}, 1
; GCN-NEXT: s_cselect_b64 s{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}
; GCN-NEXT: s_cselect_b64 s{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_scc1_sgpr_ifcvt_triangle96(<3 x i32> addrspace(2)* %in, i32 %cond) #0 {
AMDGPU: Implement early ifcvt target hooks. Leave early ifcvt disabled for now since there are some shader-db regressions. This causes some immediate improvements, but could be better. The cost checking that the pass does is based on critical path length for out of order CPUs which we do not want so it skips out on many cases we want. llvm-svn: 293016
2017-01-25 12:25:02 +08:00
entry:
%v = load <3 x i32>, <3 x i32> addrspace(2)* %in
%cc = icmp eq i32 %cond, 1
br i1 %cc, label %if, label %endif
if:
%u = add <3 x i32> %v, %v
br label %endif
endif:
%r = phi <3 x i32> [ %v, %entry ], [ %u, %if ]
%r.ext = shufflevector <3 x i32> %r, <3 x i32> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
call void asm sideeffect "; reg use $0", "s"(<4 x i32> %r.ext) #0
ret void
}
; GCN-LABEL: {{^}}test_scc1_sgpr_ifcvt_triangle128:
; GCN: s_add_i32
; GCN: s_add_i32
; GCN: s_add_i32
; GCN: s_add_i32
; GCN: s_cmp_lg_u32 s{{[0-9]+}}, 1
; GCN-NEXT: s_cselect_b64 s{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}
; GCN-NEXT: s_cselect_b64 s{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_scc1_sgpr_ifcvt_triangle128(<4 x i32> addrspace(2)* %in, i32 %cond) #0 {
AMDGPU: Implement early ifcvt target hooks. Leave early ifcvt disabled for now since there are some shader-db regressions. This causes some immediate improvements, but could be better. The cost checking that the pass does is based on critical path length for out of order CPUs which we do not want so it skips out on many cases we want. llvm-svn: 293016
2017-01-25 12:25:02 +08:00
entry:
%v = load <4 x i32>, <4 x i32> addrspace(2)* %in
%cc = icmp eq i32 %cond, 1
br i1 %cc, label %if, label %endif
if:
%u = add <4 x i32> %v, %v
br label %endif
endif:
%r = phi <4 x i32> [ %v, %entry ], [ %u, %if ]
call void asm sideeffect "; reg use $0", "s"(<4 x i32> %r) #0
ret void
}
; GCN-LABEL: {{^}}uniform_if_swap_br_targets_scc_constant_select:
; GCN: s_cmp_lg_u32 s{{[0-9]+}}, 0
; GCN: s_cselect_b32 s{{[0-9]+}}, 1, 0{{$}}
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @uniform_if_swap_br_targets_scc_constant_select(i32 %cond, i32 addrspace(1)* %out) {
AMDGPU: Implement early ifcvt target hooks. Leave early ifcvt disabled for now since there are some shader-db regressions. This causes some immediate improvements, but could be better. The cost checking that the pass does is based on critical path length for out of order CPUs which we do not want so it skips out on many cases we want. llvm-svn: 293016
2017-01-25 12:25:02 +08:00
entry:
%cmp0 = icmp eq i32 %cond, 0
br i1 %cmp0, label %else, label %if
if:
br label %done
else:
br label %done
done:
%value = phi i32 [0, %if], [1, %else]
store i32 %value, i32 addrspace(1)* %out
ret void
}
; GCN-LABEL: {{^}}ifcvt_undef_scc:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; GCN: {{^}}; %bb.0:
AMDGPU: Implement early ifcvt target hooks. Leave early ifcvt disabled for now since there are some shader-db regressions. This causes some immediate improvements, but could be better. The cost checking that the pass does is based on critical path length for out of order CPUs which we do not want so it skips out on many cases we want. llvm-svn: 293016
2017-01-25 12:25:02 +08:00
; GCN-NEXT: s_load_dwordx2
; GCN-NEXT: s_cselect_b32 s{{[0-9]+}}, 1, 0
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @ifcvt_undef_scc(i32 %cond, i32 addrspace(1)* %out) {
AMDGPU: Implement early ifcvt target hooks. Leave early ifcvt disabled for now since there are some shader-db regressions. This causes some immediate improvements, but could be better. The cost checking that the pass does is based on critical path length for out of order CPUs which we do not want so it skips out on many cases we want. llvm-svn: 293016
2017-01-25 12:25:02 +08:00
entry:
br i1 undef, label %else, label %if
if:
br label %done
else:
br label %done
done:
%value = phi i32 [0, %if], [1, %else]
store i32 %value, i32 addrspace(1)* %out
ret void
}
; GCN-LABEL: {{^}}test_vccnz_ifcvt_triangle256:
; GCN: v_cmp_neq_f32
; GCN: s_cbranch_vccnz [[ENDIF:BB[0-9]+_[0-9]+]]
; GCN: v_add_i32
; GCN: v_add_i32
; GCN: [[ENDIF]]:
; GCN: buffer_store_dword
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_vccnz_ifcvt_triangle256(<8 x i32> addrspace(1)* %out, <8 x i32> addrspace(1)* %in, float %cnd) #0 {
AMDGPU: Implement early ifcvt target hooks. Leave early ifcvt disabled for now since there are some shader-db regressions. This causes some immediate improvements, but could be better. The cost checking that the pass does is based on critical path length for out of order CPUs which we do not want so it skips out on many cases we want. llvm-svn: 293016
2017-01-25 12:25:02 +08:00
entry:
%v = load <8 x i32>, <8 x i32> addrspace(1)* %in
%cc = fcmp oeq float %cnd, 1.000000e+00
br i1 %cc, label %if, label %endif
if:
%u = add <8 x i32> %v, %v
br label %endif
endif:
%r = phi <8 x i32> [ %v, %entry ], [ %u, %if ]
store <8 x i32> %r, <8 x i32> addrspace(1)* %out
ret void
}
; GCN-LABEL: {{^}}test_vccnz_ifcvt_triangle512:
; GCN: v_cmp_neq_f32
; GCN: s_cbranch_vccnz [[ENDIF:BB[0-9]+_[0-9]+]]
; GCN: v_add_i32
; GCN: v_add_i32
; GCN: [[ENDIF]]:
; GCN: buffer_store_dword
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_vccnz_ifcvt_triangle512(<16 x i32> addrspace(1)* %out, <16 x i32> addrspace(1)* %in, float %cnd) #0 {
AMDGPU: Implement early ifcvt target hooks. Leave early ifcvt disabled for now since there are some shader-db regressions. This causes some immediate improvements, but could be better. The cost checking that the pass does is based on critical path length for out of order CPUs which we do not want so it skips out on many cases we want. llvm-svn: 293016
2017-01-25 12:25:02 +08:00
entry:
%v = load <16 x i32>, <16 x i32> addrspace(1)* %in
%cc = fcmp oeq float %cnd, 1.000000e+00
br i1 %cc, label %if, label %endif
if:
%u = add <16 x i32> %v, %v
br label %endif
endif:
%r = phi <16 x i32> [ %v, %entry ], [ %u, %if ]
store <16 x i32> %r, <16 x i32> addrspace(1)* %out
ret void
}
attributes #0 = { nounwind }