mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-27 13:30:05 +00:00
1f996fa36b
This is equivalent to the AMDGPUTargetMachine now, but it is the starting point for separating R600 and GCN functionality into separate targets. It is recommened that users start using the gcn triple for GCN-based GPUs, because using the r600 triple for these GPUs will be deprecated in the future. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@225277 91177308-0d34-0410-b5e6-96231b3b80d8
98 lines
3.1 KiB
LLVM
98 lines
3.1 KiB
LLVM
; RUN: llc -march=amdgcn -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
|
|
|
|
declare i32 @llvm.r600.read.tidig.x() nounwind readnone
|
|
|
|
declare double @fabs(double) readnone
|
|
declare double @llvm.fabs.f64(double) readnone
|
|
declare <2 x double> @llvm.fabs.v2f64(<2 x double>) readnone
|
|
declare <4 x double> @llvm.fabs.v4f64(<4 x double>) readnone
|
|
|
|
; FUNC-LABEL: {{^}}v_fabs_f64:
|
|
; SI: v_and_b32
|
|
; SI: s_endpgm
|
|
define void @v_fabs_f64(double addrspace(1)* %out, double addrspace(1)* %in) {
|
|
%tid = call i32 @llvm.r600.read.tidig.x() nounwind readnone
|
|
%tidext = sext i32 %tid to i64
|
|
%gep = getelementptr double addrspace(1)* %in, i64 %tidext
|
|
%val = load double addrspace(1)* %gep, align 8
|
|
%fabs = call double @llvm.fabs.f64(double %val)
|
|
store double %fabs, double addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}fabs_f64:
|
|
; SI: v_and_b32
|
|
; SI-NOT: v_and_b32
|
|
; SI: s_endpgm
|
|
define void @fabs_f64(double addrspace(1)* %out, double %in) {
|
|
%fabs = call double @llvm.fabs.f64(double %in)
|
|
store double %fabs, double addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}fabs_v2f64:
|
|
; SI: v_and_b32
|
|
; SI: v_and_b32
|
|
; SI: s_endpgm
|
|
define void @fabs_v2f64(<2 x double> addrspace(1)* %out, <2 x double> %in) {
|
|
%fabs = call <2 x double> @llvm.fabs.v2f64(<2 x double> %in)
|
|
store <2 x double> %fabs, <2 x double> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}fabs_v4f64:
|
|
; SI: v_and_b32
|
|
; SI: v_and_b32
|
|
; SI: v_and_b32
|
|
; SI: v_and_b32
|
|
; SI: s_endpgm
|
|
define void @fabs_v4f64(<4 x double> addrspace(1)* %out, <4 x double> %in) {
|
|
%fabs = call <4 x double> @llvm.fabs.v4f64(<4 x double> %in)
|
|
store <4 x double> %fabs, <4 x double> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; SI-LABEL: {{^}}fabs_fold_f64:
|
|
; SI: s_load_dwordx2 [[ABS_VALUE:s\[[0-9]+:[0-9]+\]]], {{s\[[0-9]+:[0-9]+\]}}, 0xb
|
|
; SI-NOT: and
|
|
; SI: v_mul_f64 {{v\[[0-9]+:[0-9]+\]}}, |[[ABS_VALUE]]|, {{v\[[0-9]+:[0-9]+\]}}
|
|
; SI: s_endpgm
|
|
define void @fabs_fold_f64(double addrspace(1)* %out, double %in0, double %in1) {
|
|
%fabs = call double @llvm.fabs.f64(double %in0)
|
|
%fmul = fmul double %fabs, %in1
|
|
store double %fmul, double addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; SI-LABEL: {{^}}fabs_fn_fold_f64:
|
|
; SI: s_load_dwordx2 [[ABS_VALUE:s\[[0-9]+:[0-9]+\]]], {{s\[[0-9]+:[0-9]+\]}}, 0xb
|
|
; SI-NOT: and
|
|
; SI: v_mul_f64 {{v\[[0-9]+:[0-9]+\]}}, |[[ABS_VALUE]]|, {{v\[[0-9]+:[0-9]+\]}}
|
|
; SI: s_endpgm
|
|
define void @fabs_fn_fold_f64(double addrspace(1)* %out, double %in0, double %in1) {
|
|
%fabs = call double @fabs(double %in0)
|
|
%fmul = fmul double %fabs, %in1
|
|
store double %fmul, double addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}fabs_free_f64:
|
|
; SI: v_and_b32
|
|
; SI: s_endpgm
|
|
define void @fabs_free_f64(double addrspace(1)* %out, i64 %in) {
|
|
%bc= bitcast i64 %in to double
|
|
%fabs = call double @llvm.fabs.f64(double %bc)
|
|
store double %fabs, double addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}fabs_fn_free_f64:
|
|
; SI: v_and_b32
|
|
; SI: s_endpgm
|
|
define void @fabs_fn_free_f64(double addrspace(1)* %out, i64 %in) {
|
|
%bc= bitcast i64 %in to double
|
|
%fabs = call double @fabs(double %bc)
|
|
store double %fabs, double addrspace(1)* %out
|
|
ret void
|
|
}
|