a5cbd2ab0b
…133242)" This reverts commit 130080fab11cde5efcb338b77f5c3b31097df6e6 because it causes issues in testcases similar to coalescer_remat.ll [1], i.e. when we use a VGPR tuple but only write to its lower parts. The high VGPRs would then not be included in the vgpr_count, and accessing them would be an out of bounds violation. [1] https://github.com/llvm/llvm-project/blob/main/llvm/test/CodeGen/AMDGPU/coalescer_remat.ll
30 lines
1.5 KiB
LLVM
30 lines
1.5 KiB
LLVM
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx90a -mattr=-xnack < %s | FileCheck --check-prefixes=ASM %s
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx90a -mattr=-xnack --filetype=obj < %s | llvm-objdump -s -j .rodata - | FileCheck --check-prefixes=OBJ %s
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx90a -mattr=-xnack --filetype=obj < %s | llvm-readelf --notes - | FileCheck --check-prefixes=ELF %s
|
|
|
|
; TODO: Update to check for granulated sgpr count directive once one is added.
|
|
|
|
define amdgpu_kernel void @kern() #0 {
|
|
; ASM-LABEL: kern:
|
|
; ASM: .amdhsa_next_free_sgpr 5
|
|
; ASM: .amdhsa_reserve_xnack_mask 0
|
|
|
|
; Verify that an extra SGPR block is not reserved with XNACK "off" tid setting.
|
|
; OBJ: Contents of section .rodata:
|
|
; OBJ-NEXT: 0000 00000000 00000000 00000000 00000000 ................
|
|
; OBJ-NEXT: 0010 00000000 00000000 00000000 00000000 ................
|
|
; OBJ-NEXT: 0020 00000000 00000000 00000000 00000000 ................
|
|
; OBJ-NEXT: 0030 0000af00 8c000000 21000000 00000000 ........!.......
|
|
|
|
; ELF: AMDGPU Metadata
|
|
; ELF: .sgpr_count: 5
|
|
entry:
|
|
tail call void asm sideeffect "", "~{s[0:4]}"()
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" }
|
|
|
|
!llvm.module.flags = !{!0}
|
|
!0 = !{i32 1, !"amdhsa_code_object_version", i32 400}
|