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/trunc-store-f64-to-f16.ll

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

56 lines
2.2 KiB
LLVM
Raw Normal View History

AMDGPU: Implement expansion of f16 = FP_TO_FP16 f64 I wanted to implement this as a target independent expansion, however when targets say they want to expand FP_TO_FP16 what they actually want is the unsafe math expansion when possible and expansion to a libcall in all other cases. The only way to make this work as a target independent would be to add logic to target's TargetLowering construction to mark theses nodes as Expand when LegalizeDAG can use the unsafe expansion and mark them as LibCall when it cannot. I think this would be possible, but I think it would be too fragile and complex as it would require targets to keep their expansion logic up to date with the code in LegalizeDAG. Reviewers: bogner, ab, t.p.northover, arsenm Subscribers: wdng, llvm-commits, nhaehnle Differential Revision: https://reviews.llvm.org/D25999 llvm-svn: 285704
2016-11-02 00:31:48 +08:00
; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
R600/SI: Fix some cases for load / store of half Mostly argument loads were producing broken zextloads from an FP type. llvm-svn: 239049
2015-06-05 00:00:27 +08:00
; GCN-LABEL: {{^}}global_truncstore_f64_to_f16:
; GCN: s_endpgm
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 @global_truncstore_f64_to_f16(half addrspace(1)* %out, double addrspace(1)* %in) #0 {
R600/SI: Fix some cases for load / store of half Mostly argument loads were producing broken zextloads from an FP type. llvm-svn: 239049
2015-06-05 00:00:27 +08:00
%val = load double, double addrspace(1)* %in
%cvt = fptrunc double %val to half
store half %cvt, half addrspace(1)* %out
ret void
}
; GCN-LABEL: {{^}}global_truncstore_v2f64_to_v2f16:
; GCN: s_endpgm
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 @global_truncstore_v2f64_to_v2f16(<2 x half> addrspace(1)* %out, <2 x double> addrspace(1)* %in) #0 {
R600/SI: Fix some cases for load / store of half Mostly argument loads were producing broken zextloads from an FP type. llvm-svn: 239049
2015-06-05 00:00:27 +08:00
%val = load <2 x double>, <2 x double> addrspace(1)* %in
%cvt = fptrunc <2 x double> %val to <2 x half>
store <2 x half> %cvt, <2 x half> addrspace(1)* %out
ret void
}
; GCN-LABEL: {{^}}global_truncstore_v3f64_to_v3f16:
; GCN: s_endpgm
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 @global_truncstore_v3f64_to_v3f16(<3 x half> addrspace(1)* %out, <3 x double> addrspace(1)* %in) #0 {
R600/SI: Fix some cases for load / store of half Mostly argument loads were producing broken zextloads from an FP type. llvm-svn: 239049
2015-06-05 00:00:27 +08:00
%val = load <3 x double>, <3 x double> addrspace(1)* %in
%cvt = fptrunc <3 x double> %val to <3 x half>
store <3 x half> %cvt, <3 x half> addrspace(1)* %out
ret void
}
; GCN-LABEL: {{^}}global_truncstore_v4f64_to_v4f16:
; GCN: s_endpgm
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 @global_truncstore_v4f64_to_v4f16(<4 x half> addrspace(1)* %out, <4 x double> addrspace(1)* %in) #0 {
R600/SI: Fix some cases for load / store of half Mostly argument loads were producing broken zextloads from an FP type. llvm-svn: 239049
2015-06-05 00:00:27 +08:00
%val = load <4 x double>, <4 x double> addrspace(1)* %in
%cvt = fptrunc <4 x double> %val to <4 x half>
store <4 x half> %cvt, <4 x half> addrspace(1)* %out
ret void
}
; GCN-LABEL: {{^}}global_truncstore_v8f64_to_v8f16:
; GCN: s_endpgm
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 @global_truncstore_v8f64_to_v8f16(<8 x half> addrspace(1)* %out, <8 x double> addrspace(1)* %in) #0 {
R600/SI: Fix some cases for load / store of half Mostly argument loads were producing broken zextloads from an FP type. llvm-svn: 239049
2015-06-05 00:00:27 +08:00
%val = load <8 x double>, <8 x double> addrspace(1)* %in
%cvt = fptrunc <8 x double> %val to <8 x half>
store <8 x half> %cvt, <8 x half> addrspace(1)* %out
ret void
}
; GCN-LABEL: {{^}}global_truncstore_v16f64_to_v16f16:
; GCN: s_endpgm
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 @global_truncstore_v16f64_to_v16f16(<16 x half> addrspace(1)* %out, <16 x double> addrspace(1)* %in) #0 {
R600/SI: Fix some cases for load / store of half Mostly argument loads were producing broken zextloads from an FP type. llvm-svn: 239049
2015-06-05 00:00:27 +08:00
%val = load <16 x double>, <16 x double> addrspace(1)* %in
%cvt = fptrunc <16 x double> %val to <16 x half>
store <16 x half> %cvt, <16 x half> addrspace(1)* %out
ret void
}