ffa6d2afa4
This optmization produces incorrect results when the vector element type is not byte-sized. Related to D78568.
19 lines
804 B
LLVM
19 lines
804 B
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa < %s | FileCheck %s
|
|
|
|
; FIXME: Incorrect codegen during an optimization of load + extractelement when
|
|
; the vector element type is not byte-sized: this test loads from %idx-many
|
|
; bytes from address %ptr, instead of that many bits.
|
|
define i1 @extractloadi1(<8 x i1> *%ptr, i32 %idx) {
|
|
; CHECK-LABEL: extractloadi1:
|
|
; CHECK: ; %bb.0:
|
|
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; CHECK-NEXT: v_mad_u64_u32 v[0:1], s[4:5], v2, 1, v[0:1]
|
|
; CHECK-NEXT: flat_load_ubyte v0, v[0:1]
|
|
; CHECK-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; CHECK-NEXT: s_setpc_b64 s[30:31]
|
|
%val = load <8 x i1>, <8 x i1> *%ptr
|
|
%ret = extractelement <8 x i1> %val, i32 %idx
|
|
ret i1 %ret
|
|
}
|