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/promote-alloca-to-lds-phi.ll

205 lines
6.7 KiB
LLVM
Raw Normal View History

AMDGPU: Fix breaking IR on instructions with multiple pointer operands The promote alloca pass would attempt to promote an alloca with a select, icmp, or phi user, even though the other operand was from a non-promotable source, producing a select on two different pointer types. Only do this if we know that both operands derive from the same alloca. In the future we should be able to relax this to an alloca which will also be promoted. llvm-svn: 269265
2016-05-12 09:58:58 +08:00
; RUN: opt -S -mtriple=amdgcn-unknown-amdhsa -mcpu=kaveri -amdgpu-promote-alloca < %s | FileCheck %s
; CHECK-LABEL: @branch_ptr_var_same_alloca(
; CHECK: getelementptr inbounds [256 x [64 x i32]], [256 x [64 x i32]] addrspace(3)* @branch_ptr_var_same_alloca.alloca, i32 0, i32 %{{[0-9]+}}
; CHECK: if:
; CHECK: %arrayidx0 = getelementptr inbounds [64 x i32], [64 x i32] addrspace(3)* %{{[0-9]+}}, i32 0, i32 %a
; CHECK: else:
; CHECK: %arrayidx1 = getelementptr inbounds [64 x i32], [64 x i32] addrspace(3)* %15, i32 0, i32 %b
; CHECK: endif:
; CHECK: %phi.ptr = phi i32 addrspace(3)* [ %arrayidx0, %if ], [ %arrayidx1, %else ]
; CHECK: store i32 0, i32 addrspace(3)* %phi.ptr, align 4
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 @branch_ptr_var_same_alloca(i32 %a, i32 %b) #0 {
AMDGPU: Fix breaking IR on instructions with multiple pointer operands The promote alloca pass would attempt to promote an alloca with a select, icmp, or phi user, even though the other operand was from a non-promotable source, producing a select on two different pointer types. Only do this if we know that both operands derive from the same alloca. In the future we should be able to relax this to an alloca which will also be promoted. llvm-svn: 269265
2016-05-12 09:58:58 +08:00
entry:
%alloca = alloca [64 x i32], align 4
br i1 undef, label %if, label %else
if:
%arrayidx0 = getelementptr inbounds [64 x i32], [64 x i32]* %alloca, i32 0, i32 %a
br label %endif
else:
%arrayidx1 = getelementptr inbounds [64 x i32], [64 x i32]* %alloca, i32 0, i32 %b
br label %endif
endif:
%phi.ptr = phi i32* [ %arrayidx0, %if ], [ %arrayidx1, %else ]
store i32 0, i32* %phi.ptr, align 4
ret void
}
AMDGPU: Handle alloca promoting with null operands If the second pointer in a multi-pointer instruction is a constant, we can replace the type. llvm-svn: 269945
2016-05-18 23:57:21 +08:00
; CHECK-LABEL: @branch_ptr_phi_alloca_null_0(
; CHECK: %phi.ptr = phi i32 addrspace(3)* [ %arrayidx0, %if ], [ null, %entry ]
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 @branch_ptr_phi_alloca_null_0(i32 %a, i32 %b) #0 {
AMDGPU: Handle alloca promoting with null operands If the second pointer in a multi-pointer instruction is a constant, we can replace the type. llvm-svn: 269945
2016-05-18 23:57:21 +08:00
entry:
%alloca = alloca [64 x i32], align 4
br i1 undef, label %if, label %endif
if:
%arrayidx0 = getelementptr inbounds [64 x i32], [64 x i32]* %alloca, i32 0, i32 %a
br label %endif
endif:
%phi.ptr = phi i32* [ %arrayidx0, %if ], [ null, %entry ]
store i32 0, i32* %phi.ptr, align 4
ret void
}
; CHECK-LABEL: @branch_ptr_phi_alloca_null_1(
; CHECK: %phi.ptr = phi i32 addrspace(3)* [ null, %entry ], [ %arrayidx0, %if ]
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 @branch_ptr_phi_alloca_null_1(i32 %a, i32 %b) #0 {
AMDGPU: Handle alloca promoting with null operands If the second pointer in a multi-pointer instruction is a constant, we can replace the type. llvm-svn: 269945
2016-05-18 23:57:21 +08:00
entry:
%alloca = alloca [64 x i32], align 4
br i1 undef, label %if, label %endif
if:
%arrayidx0 = getelementptr inbounds [64 x i32], [64 x i32]* %alloca, i32 0, i32 %a
br label %endif
endif:
%phi.ptr = phi i32* [ null, %entry ], [ %arrayidx0, %if ]
store i32 0, i32* %phi.ptr, align 4
ret void
}
AMDGPU: Fix breaking IR on instructions with multiple pointer operands The promote alloca pass would attempt to promote an alloca with a select, icmp, or phi user, even though the other operand was from a non-promotable source, producing a select on two different pointer types. Only do this if we know that both operands derive from the same alloca. In the future we should be able to relax this to an alloca which will also be promoted. llvm-svn: 269265
2016-05-12 09:58:58 +08:00
; CHECK-LABEL: @one_phi_value(
; CHECK: getelementptr inbounds [256 x [64 x i32]], [256 x [64 x i32]] addrspace(3)* @one_phi_value.alloca, i32 0, i32 %14
; CHECK: %arrayidx0 = getelementptr inbounds [64 x i32], [64 x i32] addrspace(3)* %{{[0-9]+}}, i32 0, i32 %a
; CHECK: br label %exit
; CHECK: %phi.ptr = phi i32 addrspace(3)* [ %arrayidx0, %entry ]
; CHECK: store i32 0, i32 addrspace(3)* %phi.ptr, align 4
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 @one_phi_value(i32 %a) #0 {
AMDGPU: Fix breaking IR on instructions with multiple pointer operands The promote alloca pass would attempt to promote an alloca with a select, icmp, or phi user, even though the other operand was from a non-promotable source, producing a select on two different pointer types. Only do this if we know that both operands derive from the same alloca. In the future we should be able to relax this to an alloca which will also be promoted. llvm-svn: 269265
2016-05-12 09:58:58 +08:00
entry:
%alloca = alloca [64 x i32], align 4
%arrayidx0 = getelementptr inbounds [64 x i32], [64 x i32]* %alloca, i32 0, i32 %a
br label %exit
exit:
%phi.ptr = phi i32* [ %arrayidx0, %entry ]
store i32 0, i32* %phi.ptr, align 4
ret void
}
; CHECK-LABEL: @branch_ptr_alloca_unknown_obj(
; CHECK: %alloca = alloca [64 x i32], align 4
; CHECK: if:
; CHECK: %arrayidx0 = getelementptr inbounds [64 x i32], [64 x i32]* %alloca, i32 0, i32 %a
; CHECK: else:
; CHECK: %arrayidx1 = call i32* @get_unknown_pointer()
; CHECK: endif:
; CHECK: %phi.ptr = phi i32* [ %arrayidx0, %if ], [ %arrayidx1, %else ]
; CHECK: store i32 0, i32* %phi.ptr, align 4
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 @branch_ptr_alloca_unknown_obj(i32 %a, i32 %b) #0 {
AMDGPU: Fix breaking IR on instructions with multiple pointer operands The promote alloca pass would attempt to promote an alloca with a select, icmp, or phi user, even though the other operand was from a non-promotable source, producing a select on two different pointer types. Only do this if we know that both operands derive from the same alloca. In the future we should be able to relax this to an alloca which will also be promoted. llvm-svn: 269265
2016-05-12 09:58:58 +08:00
entry:
%alloca = alloca [64 x i32], align 4
br i1 undef, label %if, label %else
if:
%arrayidx0 = getelementptr inbounds [64 x i32], [64 x i32]* %alloca, i32 0, i32 %a
br label %endif
else:
%arrayidx1 = call i32* @get_unknown_pointer()
br label %endif
endif:
%phi.ptr = phi i32* [ %arrayidx0, %if ], [ %arrayidx1, %else ]
store i32 0, i32* %phi.ptr, align 4
ret void
}
; kernel void ptr_induction_var_same_alloca(void)
; {
; int alloca[64];
; int i = 0;
; #pragma nounroll
; for (int* p = &alloca[2], *e = &alloca[48]; p != e; ++p, ++i)
; {
; *p = i;
; }
; }
; FIXME: This should be promotable. We need to use
; GetUnderlyingObjects when looking at the icmp user.
; CHECK-LABEL: @ptr_induction_var_same_alloca(
; CHECK: %alloca = alloca [64 x i32], align 4
; CHECK: phi i32* [ %arrayidx, %entry ], [ %incdec.ptr, %for.body ]
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 @ptr_induction_var_same_alloca() #0 {
AMDGPU: Fix breaking IR on instructions with multiple pointer operands The promote alloca pass would attempt to promote an alloca with a select, icmp, or phi user, even though the other operand was from a non-promotable source, producing a select on two different pointer types. Only do this if we know that both operands derive from the same alloca. In the future we should be able to relax this to an alloca which will also be promoted. llvm-svn: 269265
2016-05-12 09:58:58 +08:00
entry:
%alloca = alloca [64 x i32], align 4
%arrayidx = getelementptr inbounds [64 x i32], [64 x i32]* %alloca, i32 0, i32 2
%arrayidx1 = getelementptr inbounds [64 x i32], [64 x i32]* %alloca, i32 0, i32 48
br label %for.body
for.cond.cleanup: ; preds = %for.body
ret void
for.body: ; preds = %for.body, %entry
%i.09 = phi i32 [ 0, %entry ], [ %inc, %for.body ]
%p.08 = phi i32* [ %arrayidx, %entry ], [ %incdec.ptr, %for.body ]
store i32 %i.09, i32* %p.08, align 4
%incdec.ptr = getelementptr inbounds i32, i32* %p.08, i32 1
%inc = add nuw nsw i32 %i.09, 1
%cmp = icmp eq i32* %incdec.ptr, %arrayidx1
br i1 %cmp, label %for.cond.cleanup, label %for.body
}
; extern int* get_unknown_pointer(void);
; kernel void ptr_induction_var_alloca_unknown(void)
; {
; int alloca[64];
; int i = 0;
;
; for (int* p = &alloca[2], *e = get_unknown_pointer(); p != e; ++p, ++i)
; {
; *p = i;
; }
; }
; CHECK-LABEL: @ptr_induction_var_alloca_unknown(
; CHECK: %alloca = alloca [64 x i32], align 4
; CHECK: %p.08 = phi i32* [ %incdec.ptr, %for.body ], [ %arrayidx, %for.body.preheader ]
; CHECK: %cmp = icmp eq i32* %incdec.ptr, %call
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 @ptr_induction_var_alloca_unknown() #0 {
AMDGPU: Fix breaking IR on instructions with multiple pointer operands The promote alloca pass would attempt to promote an alloca with a select, icmp, or phi user, even though the other operand was from a non-promotable source, producing a select on two different pointer types. Only do this if we know that both operands derive from the same alloca. In the future we should be able to relax this to an alloca which will also be promoted. llvm-svn: 269265
2016-05-12 09:58:58 +08:00
entry:
%alloca = alloca [64 x i32], align 4
%arrayidx = getelementptr inbounds [64 x i32], [64 x i32]* %alloca, i32 0, i32 2
%call = tail call i32* @get_unknown_pointer() #2
%cmp.7 = icmp eq i32* %arrayidx, %call
br i1 %cmp.7, label %for.cond.cleanup, label %for.body.preheader
for.body.preheader: ; preds = %entry
br label %for.body
for.cond.cleanup.loopexit: ; preds = %for.body
br label %for.cond.cleanup
for.cond.cleanup: ; preds = %for.cond.cleanup.loopexit, %entry
ret void
for.body: ; preds = %for.body, %for.body.preheader
%i.09 = phi i32 [ %inc, %for.body ], [ 0, %for.body.preheader ]
%p.08 = phi i32* [ %incdec.ptr, %for.body ], [ %arrayidx, %for.body.preheader ]
store i32 %i.09, i32* %p.08, align 4
%incdec.ptr = getelementptr inbounds i32, i32* %p.08, i32 1
%inc = add nuw nsw i32 %i.09, 1
%cmp = icmp eq i32* %incdec.ptr, %call
br i1 %cmp, label %for.cond.cleanup.loopexit, label %for.body
}
declare i32* @get_unknown_pointer() #0
[AMDGPU] Wave and register controls - Implemented amdgpu-flat-work-group-size attribute - Implemented amdgpu-num-active-waves-per-eu attribute - Implemented amdgpu-num-sgpr attribute - Implemented amdgpu-num-vgpr attribute - Dynamic LDS constraints are in a separate patch Patch by Tom Stellard and Konstantin Zhuravlyov Differential Revision: https://reviews.llvm.org/D21562 llvm-svn: 280747
2016-09-07 04:22:28 +08:00
attributes #0 = { nounwind "amdgpu-waves-per-eu"="1,1" }