mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-23 11:13:28 +01:00
cb35142c34
Fix 64-bit copy to SCC by restricting the pattern resulting in such a copy to subtargets supporting 64-bit scalar compare, and mapping the copy to S_CMP_LG_U64. Before introducing the S_CSELECT pattern with explicit SCC (0045786f146e78afee49eee053dc29ebc842fee1), there was no need for handling 64-bit copy to SCC ($scc = COPY sreg_64). The proposed handling to read only the low bits was however based on a false premise that it is only one bit that matters, while in fact the copy source might be a vector of booleans and all bits need to be considered. The practical problem of mapping the 64-bit copy to SCC is that the natural instruction to use (S_CMP_LG_U64) is not available on old hardware. Fix it by restricting the problematic pattern to subtargets supporting the instruction (hasScalarCompareEq64). Differential Revision: https://reviews.llvm.org/D85207
96 lines
3.8 KiB
LLVM
96 lines
3.8 KiB
LLVM
;RUN: llc < %s -march=amdgcn -verify-machineinstrs | FileCheck --check-prefix=SI --check-prefix=FUNC %s
|
|
;RUN: llc < %s -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs | FileCheck --check-prefix=VI --check-prefix=FUNC %s
|
|
;RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck --check-prefix=EG --check-prefix=FUNC %s
|
|
|
|
; FUNC-LABEL: {{^}}test_select_v2i32:
|
|
|
|
; EG-DAG: CNDE_INT {{\** *}}T{{[0-9]+\.[XYZW], PV\.[XYZW], T[0-9]+\.[XYZW]}}, KC0[3].Z
|
|
; EG-DAG: CNDE_INT {{\** *}}T{{[0-9]+\.[XYZW], PV\.[XYZW], T[0-9]+\.[XYZW]}}, KC0[3].Y
|
|
|
|
; VI: s_cmp_gt_i32
|
|
; VI: s_cselect_b32
|
|
; VI: s_cmp_gt_i32
|
|
; VI: s_cselect_b32
|
|
|
|
; SI: v_cmp_gt_i32_e32 vcc
|
|
; SI: v_cndmask_b32_e32
|
|
; SI: v_cmp_gt_i32_e32 vcc
|
|
; SI: v_cndmask_b32_e32
|
|
|
|
define amdgpu_kernel void @test_select_v2i32(<2 x i32> addrspace(1)* %out, <2 x i32> addrspace(1)* %in0, <2 x i32> addrspace(1)* %in1, <2 x i32> %val) {
|
|
entry:
|
|
%load0 = load <2 x i32>, <2 x i32> addrspace(1)* %in0
|
|
%load1 = load <2 x i32>, <2 x i32> addrspace(1)* %in1
|
|
%cmp = icmp sgt <2 x i32> %load0, %load1
|
|
%result = select <2 x i1> %cmp, <2 x i32> %val, <2 x i32> %load0
|
|
store <2 x i32> %result, <2 x i32> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}test_select_v2f32:
|
|
|
|
; EG: CNDE_INT {{\** *}}T{{[0-9]+\.[XYZW], PV\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
; EG: CNDE_INT {{\** *}}T{{[0-9]+\.[XYZW], PV\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
|
|
; SI: v_cmp_neq_f32_e32 vcc
|
|
; SI: v_cndmask_b32_e32
|
|
; SI: v_cmp_neq_f32_e32 vcc
|
|
; SI: v_cndmask_b32_e32
|
|
|
|
define amdgpu_kernel void @test_select_v2f32(<2 x float> addrspace(1)* %out, <2 x float> addrspace(1)* %in0, <2 x float> addrspace(1)* %in1) {
|
|
entry:
|
|
%0 = load <2 x float>, <2 x float> addrspace(1)* %in0
|
|
%1 = load <2 x float>, <2 x float> addrspace(1)* %in1
|
|
%cmp = fcmp une <2 x float> %0, %1
|
|
%result = select <2 x i1> %cmp, <2 x float> %0, <2 x float> %1
|
|
store <2 x float> %result, <2 x float> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
;FUNC-LABEL: {{^}}test_select_v4i32:
|
|
|
|
; EG-DAG: CNDE_INT {{\** *}}T{{[0-9]+\.[XYZW], PV\.[XYZW], T[0-9]+\.[XYZW]}}, KC0[4].X
|
|
; EG-DAG: CNDE_INT {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}, KC0[3].W
|
|
; EG-DAG: CNDE_INT {{\** *}}T{{[0-9]+\.[XYZW], PV\.[XYZW], T[0-9]+\.[XYZW]}}, KC0[3].Z
|
|
; EG-DAG: CNDE_INT {{\** *}}T{{[0-9]+\.[XYZW], PV\.[XYZW], T[0-9]+\.[XYZW]}}, KC0[3].Y
|
|
|
|
; VI: s_cselect_b32
|
|
; VI: s_cselect_b32
|
|
; VI: s_cselect_b32
|
|
; VI: s_cselect_b32
|
|
|
|
; SI: v_cndmask_b32_e32
|
|
; SI: v_cndmask_b32_e32
|
|
; SI: v_cndmask_b32_e32
|
|
; SI: v_cndmask_b32_e32
|
|
|
|
define amdgpu_kernel void @test_select_v4i32(<4 x i32> addrspace(1)* %out, <4 x i32> addrspace(1)* %in0, <4 x i32> addrspace(1)* %in1, <4 x i32> %val) {
|
|
entry:
|
|
%load0 = load <4 x i32>, <4 x i32> addrspace(1)* %in0
|
|
%load1 = load <4 x i32>, <4 x i32> addrspace(1)* %in1
|
|
%cmp = icmp sgt <4 x i32> %load0, %load1
|
|
%result = select <4 x i1> %cmp, <4 x i32> %val, <4 x i32> %load0
|
|
store <4 x i32> %result, <4 x i32> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
;FUNC-LABEL: {{^}}test_select_v4f32:
|
|
;EG: CNDE_INT {{\** *}}T{{[0-9]+\.[XYZW], PV\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
;EG: CNDE_INT {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
;EG: CNDE_INT {{\** *}}T{{[0-9]+\.[XYZW], PV\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
;EG: CNDE_INT {{\** *}}T{{[0-9]+\.[XYZW], PV\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
|
|
; SI: v_cndmask_b32_e32
|
|
; SI: v_cndmask_b32_e32
|
|
; SI: v_cndmask_b32_e32
|
|
; SI: v_cndmask_b32_e32
|
|
define amdgpu_kernel void @test_select_v4f32(<4 x float> addrspace(1)* %out, <4 x float> addrspace(1)* %in0, <4 x float> addrspace(1)* %in1) {
|
|
entry:
|
|
%0 = load <4 x float>, <4 x float> addrspace(1)* %in0
|
|
%1 = load <4 x float>, <4 x float> addrspace(1)* %in1
|
|
%cmp = fcmp une <4 x float> %0, %1
|
|
%result = select <4 x i1> %cmp, <4 x float> %0, <4 x float> %1
|
|
store <4 x float> %result, <4 x float> addrspace(1)* %out
|
|
ret void
|
|
}
|