llvm-project/llvm/test/CodeGen/AMDGPU/call-constant.ll
Scott Linder 60b1967c39 [AMDGPU] Add Scratch Wave Offset to Scratch Buffer Descriptor in entry functions
Add the scratch wave offset to the scratch buffer descriptor (SRSrc) in
the entry function prologue. This allows us to removes the scratch wave
offset register from the calling convention ABI.

As part of this change, allow the use of an inline constant zero for the
SOffset of MUBUF instructions accessing the stack in entry functions
when a frame pointer is not requested/required. Entry functions with
calls still need to set up the calling convention ABI stack pointer
register, and reference it in order to address arguments of called
functions. The ABI stack pointer register remains unswizzled, but is now
wave-relative instead of queue-relative.

Non-entry functions also use an inline constant zero SOffset for
wave-relative scratch access, but continue to use the stack and frame
pointers as before. When the stack or frame pointer is converted to a
swizzled offset it is now scaled directly, as the scratch wave offset no
longer needs to be subtracted first.

Update llvm/docs/AMDGPUUsage.rst to reflect these changes to the calling
convention.

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D75138
2020-03-19 15:35:16 -04:00

44 lines
1.1 KiB
LLVM

; RUN: llc -mtriple=amdgcn-amd-amdhsa < %s | FileCheck -check-prefix=GCN %s
; FIXME: Emitting unnecessary flat_scratch setup
; GCN-LABEL: {{^}}test_call_undef:
; GCN: s_mov_b32 flat_scratch_lo, s5
; GCN: s_add_u32 s4, s4, s7
; GCN: s_lshr_b32
; GCN: s_endpgm
define amdgpu_kernel void @test_call_undef() #0 {
%val = call i32 undef(i32 1)
%op = add i32 %val, 1
store volatile i32 %op, i32 addrspace(1)* undef
ret void
}
; GCN-LABEL: {{^}}test_tail_call_undef:
; GCN: s_waitcnt
; GCN-NEXT: .Lfunc_end
define i32 @test_tail_call_undef() #0 {
%call = tail call i32 undef(i32 1)
ret i32 %call
}
; GCN-LABEL: {{^}}test_call_null:
; GCN: s_mov_b32 flat_scratch_lo, s5
; GCN: s_add_u32 s4, s4, s7
; GCN: s_lshr_b32
; GCN: s_endpgm
define amdgpu_kernel void @test_call_null() #0 {
%val = call i32 null(i32 1)
%op = add i32 %val, 1
store volatile i32 %op, i32 addrspace(1)* null
ret void
}
; GCN-LABEL: {{^}}test_tail_call_null:
; GCN: s_waitcnt
; GCN-NEXT: .Lfunc_end
define i32 @test_tail_call_null() #0 {
%call = tail call i32 null(i32 1)
ret i32 %call
}