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-icmp.ll

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

68 lines
3.5 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
AMDGPU: Add an option -disable-promote-alloca-to-lds Add this option for debugging and providing workaround. By default it is off so no behavior change in backend. Differential Revision: https://reviews.llvm.org/D54158 llvm-svn: 346267
2018-11-07 05:28:17 +08:00
; RUN: opt -S -mtriple=amdgcn-unknown-amdhsa -mcpu=kaveri -amdgpu-promote-alloca -disable-promote-alloca-to-lds< %s | FileCheck -check-prefix=NOLDS %s
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
; This normally would be fixed by instcombine to be compare to the GEP
; indices
AMDGPU: Add an option -disable-promote-alloca-to-lds Add this option for debugging and providing workaround. By default it is off so no behavior change in backend. Differential Revision: https://reviews.llvm.org/D54158 llvm-svn: 346267
2018-11-07 05:28:17 +08:00
; NOLDS-NOT: addrspace(3)
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: @lds_promoted_alloca_icmp_same_derived_pointer(
; CHECK: [[ARRAYGEP:%[0-9]+]] = getelementptr inbounds [256 x [16 x i32]], [256 x [16 x i32]] addrspace(3)* @lds_promoted_alloca_icmp_same_derived_pointer.alloca, i32 0, i32 %{{[0-9]+}}
; CHECK: %ptr0 = getelementptr inbounds [16 x i32], [16 x i32] addrspace(3)* [[ARRAYGEP]], i32 0, i32 %a
; CHECK: %ptr1 = getelementptr inbounds [16 x i32], [16 x i32] addrspace(3)* [[ARRAYGEP]], i32 0, i32 %b
; CHECK: %cmp = icmp eq i32 addrspace(3)* %ptr0, %ptr1
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 @lds_promoted_alloca_icmp_same_derived_pointer(i32 addrspace(1)* %out, 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
%alloca = alloca [16 x i32], align 4
%ptr0 = getelementptr inbounds [16 x i32], [16 x i32]* %alloca, i32 0, i32 %a
%ptr1 = getelementptr inbounds [16 x i32], [16 x i32]* %alloca, i32 0, i32 %b
%cmp = icmp eq i32* %ptr0, %ptr1
%zext = zext i1 %cmp to i32
store volatile i32 %zext, i32 addrspace(1)* %out
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: @lds_promoted_alloca_icmp_null_rhs(
; CHECK: [[ARRAYGEP:%[0-9]+]] = getelementptr inbounds [256 x [16 x i32]], [256 x [16 x i32]] addrspace(3)* @lds_promoted_alloca_icmp_null_rhs.alloca, i32 0, i32 %{{[0-9]+}}
; CHECK: %ptr0 = getelementptr inbounds [16 x i32], [16 x i32] addrspace(3)* [[ARRAYGEP]], i32 0, i32 %a
; CHECK: %cmp = icmp eq i32 addrspace(3)* %ptr0, null
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 @lds_promoted_alloca_icmp_null_rhs(i32 addrspace(1)* %out, 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
%alloca = alloca [16 x i32], align 4
%ptr0 = getelementptr inbounds [16 x i32], [16 x i32]* %alloca, i32 0, i32 %a
%cmp = icmp eq i32* %ptr0, null
%zext = zext i1 %cmp to i32
store volatile i32 %zext, i32 addrspace(1)* %out
ret void
}
; CHECK-LABEL: @lds_promoted_alloca_icmp_null_lhs(
; CHECK: [[ARRAYGEP:%[0-9]+]] = getelementptr inbounds [256 x [16 x i32]], [256 x [16 x i32]] addrspace(3)* @lds_promoted_alloca_icmp_null_lhs.alloca, i32 0, i32 %{{[0-9]+}}
; CHECK: %ptr0 = getelementptr inbounds [16 x i32], [16 x i32] addrspace(3)* [[ARRAYGEP]], i32 0, i32 %a
; CHECK: %cmp = icmp eq i32 addrspace(3)* null, %ptr0
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 @lds_promoted_alloca_icmp_null_lhs(i32 addrspace(1)* %out, 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
%alloca = alloca [16 x i32], align 4
%ptr0 = getelementptr inbounds [16 x i32], [16 x i32]* %alloca, i32 0, i32 %a
%cmp = icmp eq i32* null, %ptr0
%zext = zext i1 %cmp to i32
store volatile i32 %zext, i32 addrspace(1)* %out
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: @lds_promoted_alloca_icmp_unknown_ptr(
; CHECK: %alloca = alloca [16 x i32], align 4
; CHECK: %ptr0 = getelementptr inbounds [16 x i32], [16 x i32]* %alloca, i32 0, i32 %a
; CHECK: %ptr1 = call i32* @get_unknown_pointer()
; CHECK: %cmp = icmp eq i32* %ptr0, %ptr1
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 @lds_promoted_alloca_icmp_unknown_ptr(i32 addrspace(1)* %out, 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
%alloca = alloca [16 x i32], align 4
%ptr0 = getelementptr inbounds [16 x i32], [16 x i32]* %alloca, i32 0, i32 %a
%ptr1 = call i32* @get_unknown_pointer()
%cmp = icmp eq i32* %ptr0, %ptr1
%zext = zext i1 %cmp to i32
store volatile i32 %zext, i32 addrspace(1)* %out
ret void
}
declare i32* @get_unknown_pointer() #0
AMDGPU: Switch backend default max workgroup size to 1024 Previously this would default to 256, not the maximum supported size of 1024. Using a maximum lower than the hardware maximum requires language runtimes to enforce this limit for correctness, which no language has correctly done. Switch the default to the conservatively correct maximum, and force frontends to opt-in to the more optimal 256 default maximum. I don't really understand why the changes in occupancy-levels.ll increased the computed occupancy, which I expected to decrease. I'm not sure if these tests should be forcing the old maximum.
2019-08-28 00:34:40 +08:00
attributes #0 = { nounwind "amdgpu-waves-per-eu"="1,1" "amdgpu-flat-work-group-size"="1,256" }