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/lower-mem-intrinsics.ll

130 lines
5.8 KiB
LLVM
Raw Normal View History

AMDGPU: Add pass to expand memcpy/memmove/memset llvm-svn: 294635
2017-02-10 06:00:42 +08:00
; RUN: opt -S -amdgpu-lower-intrinsics %s | FileCheck -check-prefix=OPT %s
Extend memcpy expansion in Transform/Utils to handle wider operand types. Adds loop expansions for known-size and unknown-sized memcpy calls, allowing the target to provide the operand types through TTI callbacks. The default values for the TTI callbacks use int8 operand types and matches the existing behaviour if they aren't overridden by the target. Differential revision: https://reviews.llvm.org/D32536 llvm-svn: 307346
2017-07-07 10:00:06 +08:00
; RUN: opt -S -amdgpu-lower-intrinsics -use-wide-memcpy-loop-lowering=true %s | FileCheck -check-prefix=WOPT %s
AMDGPU: Add pass to expand memcpy/memmove/memset llvm-svn: 294635
2017-02-10 06:00:42 +08:00
declare void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* nocapture, i8 addrspace(1)* nocapture readonly, i64, i32, i1) #1
declare void @llvm.memcpy.p1i8.p3i8.i32(i8 addrspace(1)* nocapture, i8 addrspace(3)* nocapture readonly, i32, i32, i1) #1
declare void @llvm.memmove.p1i8.p1i8.i64(i8 addrspace(1)* nocapture, i8 addrspace(1)* nocapture readonly, i64, i32, i1) #1
declare void @llvm.memset.p1i8.i64(i8 addrspace(1)* nocapture, i8, i64, i32, i1) #1
; Test the upper bound for sizes to leave
; OPT-LABEL: @max_size_small_static_memcpy_caller0(
; OPT: call void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* %dst, i8 addrspace(1)* %src, i64 1024, i32 1, i1 false)
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 @max_size_small_static_memcpy_caller0(i8 addrspace(1)* %dst, i8 addrspace(1)* %src) #0 {
AMDGPU: Add pass to expand memcpy/memmove/memset llvm-svn: 294635
2017-02-10 06:00:42 +08:00
call void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* %dst, i8 addrspace(1)* %src, i64 1024, i32 1, i1 false)
ret void
}
; Smallest static size which will be expanded
; OPT-LABEL: @min_size_large_static_memcpy_caller0(
; OPT-NOT: call
; OPT: getelementptr
; OPT-NEXT: load i8
; OPT: getelementptr
; OPT-NEXT: store i8
Extend memcpy expansion in Transform/Utils to handle wider operand types. Adds loop expansions for known-size and unknown-sized memcpy calls, allowing the target to provide the operand types through TTI callbacks. The default values for the TTI callbacks use int8 operand types and matches the existing behaviour if they aren't overridden by the target. Differential revision: https://reviews.llvm.org/D32536 llvm-svn: 307346
2017-07-07 10:00:06 +08:00
; WOPT-LABEL: @min_size_large_static_memcpy_caller0(
; WOPT-NOT: call
; WOPT: br label %load-store-loop
; WOPT: [[T1:%[0-9]+]] = getelementptr inbounds i8, i8 addrspace(1)* %src, i64 %loop-index
; WOPT-NEXT: [[T2:%[0-9]+]] = load i8, i8 addrspace(1)* [[T1]]
; WOPT-NEXT: [[T3:%[0-9]+]] = getelementptr inbounds i8, i8 addrspace(1)* %dst, i64 %loop-index
; WOPT-NEXT: store i8 [[T2]], i8 addrspace(1)* [[T3]]
; WOPT-NEXT: [[T4:%[0-9]+]] = add i64 %loop-index, 1
; WOPT-NEXT: [[T5:%[0-9]+]] = icmp ult i64 [[T4]], 1025
; WOPT-NEXT: br i1 [[T5]], label %load-store-loop, label %memcpy-split
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 @min_size_large_static_memcpy_caller0(i8 addrspace(1)* %dst, i8 addrspace(1)* %src) #0 {
AMDGPU: Add pass to expand memcpy/memmove/memset llvm-svn: 294635
2017-02-10 06:00:42 +08:00
call void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* %dst, i8 addrspace(1)* %src, i64 1025, i32 1, i1 false)
ret void
}
; OPT-LABEL: @max_size_small_static_memmove_caller0(
; OPT: call void @llvm.memmove.p1i8.p1i8.i64(i8 addrspace(1)* %dst, i8 addrspace(1)* %src, i64 1024, i32 1, i1 false)
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 @max_size_small_static_memmove_caller0(i8 addrspace(1)* %dst, i8 addrspace(1)* %src) #0 {
AMDGPU: Add pass to expand memcpy/memmove/memset llvm-svn: 294635
2017-02-10 06:00:42 +08:00
call void @llvm.memmove.p1i8.p1i8.i64(i8 addrspace(1)* %dst, i8 addrspace(1)* %src, i64 1024, i32 1, i1 false)
ret void
}
; OPT-LABEL: @min_size_large_static_memmove_caller0(
; OPT-NOT: call
; OPT: getelementptr
; OPT-NEXT: load i8
; OPT: getelementptr
; OPT-NEXT: store i8
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 @min_size_large_static_memmove_caller0(i8 addrspace(1)* %dst, i8 addrspace(1)* %src) #0 {
AMDGPU: Add pass to expand memcpy/memmove/memset llvm-svn: 294635
2017-02-10 06:00:42 +08:00
call void @llvm.memmove.p1i8.p1i8.i64(i8 addrspace(1)* %dst, i8 addrspace(1)* %src, i64 1025, i32 1, i1 false)
ret void
}
; OPT-LABEL: @max_size_small_static_memset_caller0(
; OPT: call void @llvm.memset.p1i8.i64(i8 addrspace(1)* %dst, i8 %val, i64 1024, i32 1, i1 false)
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 @max_size_small_static_memset_caller0(i8 addrspace(1)* %dst, i8 %val) #0 {
AMDGPU: Add pass to expand memcpy/memmove/memset llvm-svn: 294635
2017-02-10 06:00:42 +08:00
call void @llvm.memset.p1i8.i64(i8 addrspace(1)* %dst, i8 %val, i64 1024, i32 1, i1 false)
ret void
}
; OPT-LABEL: @min_size_large_static_memset_caller0(
; OPT-NOT: call
; OPT: getelementptr
; OPT: store i8
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 @min_size_large_static_memset_caller0(i8 addrspace(1)* %dst, i8 %val) #0 {
AMDGPU: Add pass to expand memcpy/memmove/memset llvm-svn: 294635
2017-02-10 06:00:42 +08:00
call void @llvm.memset.p1i8.i64(i8 addrspace(1)* %dst, i8 %val, i64 1025, i32 1, i1 false)
ret void
}
; OPT-LABEL: @variable_memcpy_caller0(
; OPT-NOT: call
; OPT: phi
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 @variable_memcpy_caller0(i8 addrspace(1)* %dst, i8 addrspace(1)* %src, i64 %n) #0 {
AMDGPU: Add pass to expand memcpy/memmove/memset llvm-svn: 294635
2017-02-10 06:00:42 +08:00
call void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* %dst, i8 addrspace(1)* %src, i64 %n, i32 1, i1 false)
ret void
}
; OPT-LABEL: @variable_memcpy_caller1(
; OPT-NOT: call
; OPT: phi
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 @variable_memcpy_caller1(i8 addrspace(1)* %dst, i8 addrspace(1)* %src, i64 %n) #0 {
AMDGPU: Add pass to expand memcpy/memmove/memset llvm-svn: 294635
2017-02-10 06:00:42 +08:00
call void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* %dst, i8 addrspace(1)* %src, i64 %n, i32 1, i1 false)
ret void
}
; OPT-LABEL: @memcpy_multi_use_one_function(
; OPT-NOT: call
; OPT: phi
; OPT-NOT: call
; OPT: phi
; OPT-NOT: 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 @memcpy_multi_use_one_function(i8 addrspace(1)* %dst0, i8 addrspace(1)* %dst1, i8 addrspace(1)* %src, i64 %n, i64 %m) #0 {
AMDGPU: Add pass to expand memcpy/memmove/memset llvm-svn: 294635
2017-02-10 06:00:42 +08:00
call void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* %dst0, i8 addrspace(1)* %src, i64 %n, i32 1, i1 false)
call void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* %dst1, i8 addrspace(1)* %src, i64 %m, i32 1, i1 false)
ret void
}
; OPT-LABEL: @memcpy_alt_type(
; OPT: phi
; OPT: getelementptr inbounds i8, i8 addrspace(3)*
; OPT: load i8, i8 addrspace(3)*
; OPT: getelementptr inbounds i8, i8 addrspace(1)*
; OPT: store i8
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 @memcpy_alt_type(i8 addrspace(1)* %dst, i8 addrspace(3)* %src, i32 %n) #0 {
AMDGPU: Add pass to expand memcpy/memmove/memset llvm-svn: 294635
2017-02-10 06:00:42 +08:00
call void @llvm.memcpy.p1i8.p3i8.i32(i8 addrspace(1)* %dst, i8 addrspace(3)* %src, i32 %n, i32 1, i1 false)
ret void
}
; One of the uses in the function should be expanded, the other left alone.
; OPT-LABEL: @memcpy_multi_use_one_function_keep_small(
; OPT: getelementptr inbounds i8, i8 addrspace(1)*
; OPT: load i8, i8 addrspace(1)*
; OPT: getelementptr inbounds i8, i8 addrspace(1)*
; OPT: store i8
; OPT: call void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* %dst1, i8 addrspace(1)* %src, i64 102, i32 1, i1 false)
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 @memcpy_multi_use_one_function_keep_small(i8 addrspace(1)* %dst0, i8 addrspace(1)* %dst1, i8 addrspace(1)* %src, i64 %n) #0 {
AMDGPU: Add pass to expand memcpy/memmove/memset llvm-svn: 294635
2017-02-10 06:00:42 +08:00
call void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* %dst0, i8 addrspace(1)* %src, i64 %n, i32 1, i1 false)
call void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* %dst1, i8 addrspace(1)* %src, i64 102, i32 1, i1 false)
ret void
}
attributes #0 = { nounwind }
attributes #1 = { argmemonly nounwind }