RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-02-01 13:11:39 +01:00
Code Issues Projects Releases Wiki Activity
llvm-mirror/test/CodeGen/AMDGPU/amdgcn-ieee.ll
Matt Arsenault ddf10ac5a7 AMDGPU: Remove dx10-clamp from subtarget features 
Since this can be set with s_setreg*, it should not be a subtarget
property. Set a default based on the calling convention, and Introduce
a new amdgpu-dx10-clamp attribute to override this if desired.

Also introduce a new amdgpu-ieee attribute to match.

The values need to match to allow inlining. I think it is OK for the
caller's dx10-clamp attribute to override the callee, but there
doesn't appear to be the infrastructure to do this currently without
definining the attribute in the generic Attributes.td.

Eventually the calling convention lowering will need to insert a mode
switch somewhere for these.

llvm-svn: 357302
2019-03-29 19:14:54 +00:00

189 lines
7.6 KiB
LLVM
Raw Blame History

; RUN: llc -mtriple=amdgcn-mesa-mesa3d -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
; GCN-LABEL: {{^}}kernel_ieee_mode_default:
; GCN: {{buffer|global|flat}}_load_dword [[VAL0:v[0-9]+]]
; GCN-NEXT: {{buffer|global|flat}}_load_dword [[VAL1:v[0-9]+]]
; GCN-DAG: v_mul_f32_e32 [[QUIET0:v[0-9]+]], 1.0, [[VAL0]]
; GCN-DAG: v_mul_f32_e32 [[QUIET1:v[0-9]+]], 1.0, [[VAL1]]
; GCN: v_min_f32_e32 [[MIN:v[0-9]+]], [[QUIET0]], [[QUIET1]]
; GCN-NOT: v_mul_f32
define amdgpu_kernel void @kernel_ieee_mode_default() #0 {
%val0 = load volatile float, float addrspace(1)* undef
%val1 = load volatile float, float addrspace(1)* undef
%min = call float @llvm.minnum.f32(float %val0, float %val1)
store volatile float %min, float addrspace(1)* undef
ret void
}
; GCN-LABEL: {{^}}kernel_ieee_mode_on:
; GCN: {{buffer|global|flat}}_load_dword [[VAL0:v[0-9]+]]
; GCN-NEXT: {{buffer|global|flat}}_load_dword [[VAL1:v[0-9]+]]
; GCN-DAG: v_mul_f32_e32 [[QUIET0:v[0-9]+]], 1.0, [[VAL0]]
; GCN-DAG: v_mul_f32_e32 [[QUIET1:v[0-9]+]], 1.0, [[VAL1]]
; GCN: v_min_f32_e32 [[MIN:v[0-9]+]], [[QUIET0]], [[QUIET1]]
; GCN-NOT: v_mul_f32
define amdgpu_kernel void @kernel_ieee_mode_on() #1 {
%val0 = load volatile float, float addrspace(1)* undef
%val1 = load volatile float, float addrspace(1)* undef
%min = call float @llvm.minnum.f32(float %val0, float %val1)
store volatile float %min, float addrspace(1)* undef
ret void
}
; GCN-LABEL: {{^}}kernel_ieee_mode_off:
; GCN: {{buffer|global|flat}}_load_dword [[VAL0:v[0-9]+]]
; GCN-NEXT: {{buffer|global|flat}}_load_dword [[VAL1:v[0-9]+]]
; GCN-NOT: [[VAL0]]
; GCN-NOT: [[VAL1]]
; GCN: v_min_f32_e32 [[MIN:v[0-9]+]], [[VAL0]], [[VAL1]]
; GCN-NOT: v_mul_f32
define amdgpu_kernel void @kernel_ieee_mode_off() #2 {
%val0 = load volatile float, float addrspace(1)* undef
%val1 = load volatile float, float addrspace(1)* undef
%min = call float @llvm.minnum.f32(float %val0, float %val1)
store volatile float %min, float addrspace(1)* undef
ret void
}
; GCN-LABEL: {{^}}func_ieee_mode_default:
; GCN: {{buffer|global|flat}}_load_dword [[VAL0:v[0-9]+]]
; GCN-NEXT: {{buffer|global|flat}}_load_dword [[VAL1:v[0-9]+]]
; GCN-DAG: v_mul_f32_e32 [[QUIET0:v[0-9]+]], 1.0, [[VAL0]]
; GCN-DAG: v_mul_f32_e32 [[QUIET1:v[0-9]+]], 1.0, [[VAL1]]
; GCN: v_min_f32_e32 [[MIN:v[0-9]+]], [[QUIET0]], [[QUIET1]]
; GCN-NOT: v_mul_f32
define void @func_ieee_mode_default() #0 {
%val0 = load volatile float, float addrspace(1)* undef
%val1 = load volatile float, float addrspace(1)* undef
%min = call float @llvm.minnum.f32(float %val0, float %val1)
store volatile float %min, float addrspace(1)* undef
ret void
}
; GCN-LABEL: {{^}}func_ieee_mode_on:
; GCN: {{buffer|global|flat}}_load_dword [[VAL0:v[0-9]+]]
; GCN-NEXT: {{buffer|global|flat}}_load_dword [[VAL1:v[0-9]+]]
; GCN-DAG: v_mul_f32_e32 [[QUIET0:v[0-9]+]], 1.0, [[VAL0]]
; GCN-DAG: v_mul_f32_e32 [[QUIET1:v[0-9]+]], 1.0, [[VAL1]]
; GCN: v_min_f32_e32 [[MIN:v[0-9]+]], [[QUIET0]], [[QUIET1]]
; GCN-NOT: v_mul_f32
define void @func_ieee_mode_on() #1 {
%val0 = load volatile float, float addrspace(1)* undef
%val1 = load volatile float, float addrspace(1)* undef
%min = call float @llvm.minnum.f32(float %val0, float %val1)
store volatile float %min, float addrspace(1)* undef
ret void
}
; GCN-LABEL: {{^}}func_ieee_mode_off:
; GCN: {{buffer|global|flat}}_load_dword [[VAL0:v[0-9]+]]
; GCN-NEXT: {{buffer|global|flat}}_load_dword [[VAL1:v[0-9]+]]
; GCN-NOT: [[VAL0]]
; GCN-NOT: [[VAL1]]
; GCN: v_min_f32_e32 [[MIN:v[0-9]+]], [[VAL0]], [[VAL1]]
; GCN-NOT: v_mul_f32
define void @func_ieee_mode_off() #2 {
%val0 = load volatile float, float addrspace(1)* undef
%val1 = load volatile float, float addrspace(1)* undef
%min = call float @llvm.minnum.f32(float %val0, float %val1)
store volatile float %min, float addrspace(1)* undef
ret void
}
; GCN-LABEL: {{^}}cs_ieee_mode_default:
; GCN: {{buffer|global|flat}}_load_dword [[VAL0:v[0-9]+]]
; GCN-NEXT: {{buffer|global|flat}}_load_dword [[VAL1:v[0-9]+]]
; GCN-DAG: v_mul_f32_e32 [[QUIET0:v[0-9]+]], 1.0, [[VAL0]]
; GCN-DAG: v_mul_f32_e32 [[QUIET1:v[0-9]+]], 1.0, [[VAL1]]
; GCN: v_min_f32_e32 [[MIN:v[0-9]+]], [[QUIET0]], [[QUIET1]]
; GCN-NOT: v_mul_f32
define amdgpu_cs void @cs_ieee_mode_default() #0 {
%val0 = load volatile float, float addrspace(1)* undef
%val1 = load volatile float, float addrspace(1)* undef
%min = call float @llvm.minnum.f32(float %val0, float %val1)
store volatile float %min, float addrspace(1)* undef
ret void
}
; GCN-LABEL: {{^}}cs_ieee_mode_on:
; GCN: {{buffer|global|flat}}_load_dword [[VAL0:v[0-9]+]]
; GCN-NEXT: {{buffer|global|flat}}_load_dword [[VAL1:v[0-9]+]]
; GCN-DAG: v_mul_f32_e32 [[QUIET0:v[0-9]+]], 1.0, [[VAL0]]
; GCN-DAG: v_mul_f32_e32 [[QUIET1:v[0-9]+]], 1.0, [[VAL1]]
; GCN: v_min_f32_e32 [[MIN:v[0-9]+]], [[QUIET0]], [[QUIET1]]
; GCN-NOT: v_mul_f32
define amdgpu_cs void @cs_ieee_mode_on() #1 {
%val0 = load volatile float, float addrspace(1)* undef
%val1 = load volatile float, float addrspace(1)* undef
%min = call float @llvm.minnum.f32(float %val0, float %val1)
store volatile float %min, float addrspace(1)* undef
ret void
}
; GCN-LABEL: {{^}}cs_ieee_mode_off:
; GCN: {{buffer|global|flat}}_load_dword [[VAL0:v[0-9]+]]
; GCN-NEXT: {{buffer|global|flat}}_load_dword [[VAL1:v[0-9]+]]
; GCN-NOT: [[VAL0]]
; GCN-NOT: [[VAL1]]
; GCN: v_min_f32_e32 [[MIN:v[0-9]+]], [[VAL0]], [[VAL1]]
; GCN-NOT: v_mul_f32
define amdgpu_cs void @cs_ieee_mode_off() #2 {
%val0 = load volatile float, float addrspace(1)* undef
%val1 = load volatile float, float addrspace(1)* undef
%min = call float @llvm.minnum.f32(float %val0, float %val1)
store volatile float %min, float addrspace(1)* undef
ret void
}
; GCN-LABEL: {{^}}ps_ieee_mode_default:
; GCN: {{buffer|global|flat}}_load_dword [[VAL0:v[0-9]+]]
; GCN-NEXT: {{buffer|global|flat}}_load_dword [[VAL1:v[0-9]+]]
; GCN-NOT: [[VAL0]]
; GCN-NOT: [[VAL1]]
; GCN: v_min_f32_e32 [[MIN:v[0-9]+]], [[VAL0]], [[VAL1]]
; GCN-NOT: v_mul_f32
define amdgpu_ps void @ps_ieee_mode_default() #0 {
%val0 = load volatile float, float addrspace(1)* undef
%val1 = load volatile float, float addrspace(1)* undef
%min = call float @llvm.minnum.f32(float %val0, float %val1)
store volatile float %min, float addrspace(1)* undef
ret void
}
; GCN-LABEL: {{^}}ps_ieee_mode_on:
; GCN: {{buffer|global|flat}}_load_dword [[VAL0:v[0-9]+]]
; GCN-NEXT: {{buffer|global|flat}}_load_dword [[VAL1:v[0-9]+]]
; GCN-DAG: v_mul_f32_e32 [[QUIET0:v[0-9]+]], 1.0, [[VAL0]]
; GCN-DAG: v_mul_f32_e32 [[QUIET1:v[0-9]+]], 1.0, [[VAL1]]
; GCN: v_min_f32_e32 [[MIN:v[0-9]+]], [[QUIET0]], [[QUIET1]]
; GCN-NOT: v_mul_f32
define amdgpu_ps void @ps_ieee_mode_on() #1 {
%val0 = load volatile float, float addrspace(1)* undef
%val1 = load volatile float, float addrspace(1)* undef
%min = call float @llvm.minnum.f32(float %val0, float %val1)
store volatile float %min, float addrspace(1)* undef
ret void
}
; GCN-LABEL: {{^}}ps_ieee_mode_off:
; GCN: {{buffer|global|flat}}_load_dword [[VAL0:v[0-9]+]]
; GCN-NEXT: {{buffer|global|flat}}_load_dword [[VAL1:v[0-9]+]]
; GCN-NOT: [[VAL0]]
; GCN-NOT: [[VAL1]]
; GCN: v_min_f32_e32 [[MIN:v[0-9]+]], [[VAL0]], [[VAL1]]
; GCN-NOT: v_mul_f32
define amdgpu_ps void @ps_ieee_mode_off() #2 {
%val0 = load volatile float, float addrspace(1)* undef
%val1 = load volatile float, float addrspace(1)* undef
%min = call float @llvm.minnum.f32(float %val0, float %val1)
store volatile float %min, float addrspace(1)* undef
ret void
}
declare float @llvm.minnum.f32(float, float) #3
attributes #0 = { nounwind }
attributes #1 = { nounwind "amdgpu-ieee"="true" }
attributes #2 = { nounwind "amdgpu-ieee"="false" }
attributes #3 = { nounwind readnone speculatable }
Reference in New Issue View Git Blame Copy Permalink