5c714cbdd8
We were assuming a much larger possible per-wave visible stack
allocation than is possible:
faa3ae5138/src/core/runtime/amd_gpu_agent.cpp (L70)
Based on this, we can assume the high 15 bits of a frame index or sret
are 0. The frame index value is the per-lane offset, so the maximum
frame index value is MAX_WAVE_SCRATCH / wavesize.
Remove the corresponding subtarget feature and option that made
this configurable.
llvm-svn: 361541
43 lines
1.6 KiB
LLVM
43 lines
1.6 KiB
LLVM
; RUN: llc -mtriple=amdgcn-amd-amdhsa -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN %s
|
|
|
|
; GCN-LABEL: {{^}}scratch_buffer_known_high_masklo16:
|
|
; GCN: v_mov_b32_e32 [[FI:v[0-9]+]], 4
|
|
; GCN: v_and_b32_e32 [[MASKED:v[0-9]+]], 0xfffc, [[FI]]
|
|
; GCN: flat_store_dword v{{\[[0-9]+:[0-9]+\]}}, [[MASKED]]
|
|
define amdgpu_kernel void @scratch_buffer_known_high_masklo16() #0 {
|
|
%alloca = alloca i32, align 4, addrspace(5)
|
|
store volatile i32 0, i32 addrspace(5)* %alloca
|
|
%toint = ptrtoint i32 addrspace(5)* %alloca to i32
|
|
%masked = and i32 %toint, 65535
|
|
store volatile i32 %masked, i32 addrspace(1)* undef
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}scratch_buffer_known_high_masklo17:
|
|
; GCN: v_mov_b32_e32 [[FI:v[0-9]+]], 4
|
|
; GCN-NOT: [[FI]]
|
|
; GCN: flat_store_dword v{{\[[0-9]+:[0-9]+\]}}, [[FI]]
|
|
define amdgpu_kernel void @scratch_buffer_known_high_masklo17() #0 {
|
|
%alloca = alloca i32, align 4, addrspace(5)
|
|
store volatile i32 0, i32 addrspace(5)* %alloca
|
|
%toint = ptrtoint i32 addrspace(5)* %alloca to i32
|
|
%masked = and i32 %toint, 131071
|
|
store volatile i32 %masked, i32 addrspace(1)* undef
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}scratch_buffer_known_high_mask18:
|
|
; GCN: v_mov_b32_e32 [[FI:v[0-9]+]], 4
|
|
; GCN-NOT: [[FI]]
|
|
; GCN: flat_store_dword v{{\[[0-9]+:[0-9]+\]}}, [[FI]]
|
|
define amdgpu_kernel void @scratch_buffer_known_high_mask18() #0 {
|
|
%alloca = alloca i32, align 4, addrspace(5)
|
|
store volatile i32 0, i32 addrspace(5)* %alloca
|
|
%toint = ptrtoint i32 addrspace(5)* %alloca to i32
|
|
%masked = and i32 %toint, 262143
|
|
store volatile i32 %masked, i32 addrspace(1)* undef
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { nounwind }
|