mirror of
https://github.com/Gericom/teak-llvm.git
synced 2025-06-22 04:55:50 -04:00
e53a9d96e6
The current implementation of skip insertion (SIInsertSkip) makes it a mandatory pass required for correctness. Initially, the idea was to have an optional pass. This patch inserts the s_cbranch_execz upfront during SILowerControlFlow to skip over the sections of code when no lanes are active. Later, SIRemoveShortExecBranches removes the skips for short branches, unless there is a sideeffect and the skip branch is really necessary. This new pass will replace the handling of skip insertion in the existing SIInsertSkip Pass. Differential revision: https://reviews.llvm.org/D68092
67 lines
1.6 KiB
LLVM
67 lines
1.6 KiB
LLVM
; RUN: llc -march=amdgcn -mcpu=verde < %s | FileCheck %s
|
|
|
|
; Test a simple uniform loop that lives inside non-uniform control flow.
|
|
|
|
; CHECK-LABEL: {{^}}test1:
|
|
; CHECK: v_cmp_ne_u32_e32 vcc, 0
|
|
; CHECK: s_and_saveexec_b64
|
|
; CHECK-NEXT: s_cbranch_execz BB{{[0-9]+_[0-9]+}}
|
|
|
|
; CHECK: [[LOOP_BODY_LABEL:BB[0-9]+_[0-9]+]]: ; %loop_body
|
|
; CHECK: s_cbranch_scc0 [[LOOP_BODY_LABEL]]
|
|
|
|
; CHECK: s_endpgm
|
|
define amdgpu_ps void @test1(<8 x i32> inreg %rsrc, <2 x i32> %addr.base, i32 %y, i32 %p) {
|
|
main_body:
|
|
%cc = icmp eq i32 %p, 0
|
|
br i1 %cc, label %out, label %loop_body
|
|
|
|
loop_body:
|
|
%counter = phi i32 [ 0, %main_body ], [ %incr, %loop_body ]
|
|
|
|
; Prevent the loop from being optimized out
|
|
call void asm sideeffect "", "" ()
|
|
|
|
%incr = add i32 %counter, 1
|
|
%lc = icmp sge i32 %incr, 1000
|
|
br i1 %lc, label %out, label %loop_body
|
|
|
|
out:
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: {{^}}test2:
|
|
; CHECK: s_and_saveexec_b64
|
|
; CHECK-NEXT: s_cbranch_execz
|
|
define amdgpu_kernel void @test2(i32 addrspace(1)* %out, i32 %a, i32 %b) {
|
|
main_body:
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x() #1
|
|
%cc = icmp eq i32 %tid, 0
|
|
br i1 %cc, label %done1, label %if
|
|
|
|
if:
|
|
%cmp = icmp eq i32 %a, 0
|
|
br i1 %cmp, label %done0, label %loop_body
|
|
|
|
loop_body:
|
|
%counter = phi i32 [ 0, %if ], [0, %done0], [ %incr, %loop_body ]
|
|
|
|
; Prevent the loop from being optimized out
|
|
call void asm sideeffect "", "" ()
|
|
|
|
%incr = add i32 %counter, 1
|
|
%lc = icmp sge i32 %incr, 1000
|
|
br i1 %lc, label %done1, label %loop_body
|
|
|
|
done0:
|
|
%cmp0 = icmp eq i32 %b, 0
|
|
br i1 %cmp0, label %done1, label %loop_body
|
|
|
|
done1:
|
|
ret void
|
|
}
|
|
|
|
declare i32 @llvm.amdgcn.workitem.id.x() #1
|
|
|
|
attributes #1 = { nounwind readonly }
|