shylie/llvm-project
1
0
Fork 0
Code Issues Pull Requests Actions 6 Packages Projects Releases Wiki Activity
llvm-project/llvm/test/Analysis/DivergenceAnalysis/AMDGPU/llvm.amdgcn.buffer.atomic.ll
Sameer Sahasrabuddhe 11bf7da64a [NewPM] Introduce (GPU)DivergenceAnalysis in the new pass manager 
The GPUDivergenceAnalysis is now renamed to just "DivergenceAnalysis"
since there is no conflict with LegacyDivergenceAnalysis. In the
legacy PM, this analysis can only be used through the legacy DA
serving as a wrapper. It is now made available as a pass in the new
PM, and has no relation with the legacy DA.

The new DA currently cannot handle irreducible control flow; its
presence can cause the analysis to run indefinitely. The analysis is
now modified to detect this and report all instructions in the
function as divergent. This is super conservative, but allows the
analysis to be used without hanging the compiler.

Reviewed By: aeubanks

Differential Revision: https://reviews.llvm.org/D96615
2021-02-16 10:26:45 +05:30

305 lines
14 KiB
LLVM
Raw Blame History

;RUN: opt -mtriple=amdgcn-mesa-mesa3d -enable-new-pm=0 -analyze -divergence -use-gpu-divergence-analysis %s | FileCheck %s
; RUN: opt -mtriple amdgcn-mesa-mesa3d -passes='print<divergence>' -disable-output %s 2>&1 | FileCheck %s
;CHECK: DIVERGENT: %orig = call i32 @llvm.amdgcn.buffer.atomic.swap.i32(
define float @buffer_atomic_swap(<4 x i32> inreg %rsrc, i32 inreg %data) #0 {
main_body:
%orig = call i32 @llvm.amdgcn.buffer.atomic.swap.i32(i32 %data, <4 x i32> %rsrc, i32 0, i32 0, i1 0)
%r = bitcast i32 %orig to float
ret float %r
}
;CHECK: DIVERGENT: %orig = call i32 @llvm.amdgcn.buffer.atomic.add.i32(
define float @buffer_atomic_add(<4 x i32> inreg %rsrc, i32 inreg %data) #0 {
main_body:
%orig = call i32 @llvm.amdgcn.buffer.atomic.add.i32(i32 %data, <4 x i32> %rsrc, i32 0, i32 0, i1 0)
%r = bitcast i32 %orig to float
ret float %r
}
;CHECK: DIVERGENT: %orig = call i32 @llvm.amdgcn.buffer.atomic.sub.i32(
define float @buffer_atomic_sub(<4 x i32> inreg %rsrc, i32 inreg %data) #0 {
main_body:
%orig = call i32 @llvm.amdgcn.buffer.atomic.sub.i32(i32 %data, <4 x i32> %rsrc, i32 0, i32 0, i1 0)
%r = bitcast i32 %orig to float
ret float %r
}
;CHECK: DIVERGENT: %orig = call i32 @llvm.amdgcn.buffer.atomic.smin.i32(
define float @buffer_atomic_smin(<4 x i32> inreg %rsrc, i32 inreg %data) #0 {
main_body:
%orig = call i32 @llvm.amdgcn.buffer.atomic.smin.i32(i32 %data, <4 x i32> %rsrc, i32 0, i32 0, i1 0)
%r = bitcast i32 %orig to float
ret float %r
}
;CHECK: DIVERGENT: %orig = call i32 @llvm.amdgcn.buffer.atomic.umin.i32(
define float @buffer_atomic_umin(<4 x i32> inreg %rsrc, i32 inreg %data) #0 {
main_body:
%orig = call i32 @llvm.amdgcn.buffer.atomic.umin.i32(i32 %data, <4 x i32> %rsrc, i32 0, i32 0, i1 0)
%r = bitcast i32 %orig to float
ret float %r
}
;CHECK: DIVERGENT: %orig = call i32 @llvm.amdgcn.buffer.atomic.smax.i32(
define float @buffer_atomic_smax(<4 x i32> inreg %rsrc, i32 inreg %data) #0 {
main_body:
%orig = call i32 @llvm.amdgcn.buffer.atomic.smax.i32(i32 %data, <4 x i32> %rsrc, i32 0, i32 0, i1 0)
%r = bitcast i32 %orig to float
ret float %r
}
;CHECK: DIVERGENT: %orig = call i32 @llvm.amdgcn.buffer.atomic.umax.i32(
define float @buffer_atomic_umax(<4 x i32> inreg %rsrc, i32 inreg %data) #0 {
main_body:
%orig = call i32 @llvm.amdgcn.buffer.atomic.umax.i32(i32 %data, <4 x i32> %rsrc, i32 0, i32 0, i1 0)
%r = bitcast i32 %orig to float
ret float %r
}
;CHECK: DIVERGENT: %orig = call i32 @llvm.amdgcn.buffer.atomic.and.i32(
define float @buffer_atomic_and(<4 x i32> inreg %rsrc, i32 inreg %data) #0 {
main_body:
%orig = call i32 @llvm.amdgcn.buffer.atomic.and.i32(i32 %data, <4 x i32> %rsrc, i32 0, i32 0, i1 0)
%r = bitcast i32 %orig to float
ret float %r
}
;CHECK: DIVERGENT: %orig = call i32 @llvm.amdgcn.buffer.atomic.or.i32(
define float @buffer_atomic_or(<4 x i32> inreg %rsrc, i32 inreg %data) #0 {
main_body:
%orig = call i32 @llvm.amdgcn.buffer.atomic.or.i32(i32 %data, <4 x i32> %rsrc, i32 0, i32 0, i1 0)
%r = bitcast i32 %orig to float
ret float %r
}
;CHECK: DIVERGENT: %orig = call i32 @llvm.amdgcn.buffer.atomic.xor.i32(
define float @buffer_atomic_xor(<4 x i32> inreg %rsrc, i32 inreg %data) #0 {
main_body:
%orig = call i32 @llvm.amdgcn.buffer.atomic.xor.i32(i32 %data, <4 x i32> %rsrc, i32 0, i32 0, i1 0)
%r = bitcast i32 %orig to float
ret float %r
}
;CHECK: DIVERGENT: %orig = call i32 @llvm.amdgcn.buffer.atomic.cmpswap(
define float @buffer_atomic_cmpswap(<4 x i32> inreg %rsrc, i32 inreg %data, i32 inreg %cmp) #0 {
main_body:
%orig = call i32 @llvm.amdgcn.buffer.atomic.cmpswap(i32 %data, i32 %cmp, <4 x i32> %rsrc, i32 0, i32 0, i1 0)
%r = bitcast i32 %orig to float
ret float %r
}
;CHECK: DIVERGENT: %orig = call i32 @llvm.amdgcn.raw.buffer.atomic.swap.i32(
define float @raw_buffer_atomic_swap(<4 x i32> inreg %rsrc, i32 inreg %data) #0 {
main_body:
%orig = call i32 @llvm.amdgcn.raw.buffer.atomic.swap.i32(i32 %data, <4 x i32> %rsrc, i32 0, i32 0, i32 0)
%r = bitcast i32 %orig to float
ret float %r
}
;CHECK: DIVERGENT: %orig = call i32 @llvm.amdgcn.raw.buffer.atomic.add.i32(
define float @raw_buffer_atomic_add(<4 x i32> inreg %rsrc, i32 inreg %data) #0 {
main_body:
%orig = call i32 @llvm.amdgcn.raw.buffer.atomic.add.i32(i32 %data, <4 x i32> %rsrc, i32 0, i32 0, i32 0)
%r = bitcast i32 %orig to float
ret float %r
}
;CHECK: DIVERGENT: %orig = call i32 @llvm.amdgcn.raw.buffer.atomic.sub.i32(
define float @raw_buffer_atomic_sub(<4 x i32> inreg %rsrc, i32 inreg %data) #0 {
main_body:
%orig = call i32 @llvm.amdgcn.raw.buffer.atomic.sub.i32(i32 %data, <4 x i32> %rsrc, i32 0, i32 0, i32 0)
%r = bitcast i32 %orig to float
ret float %r
}
;CHECK: DIVERGENT: %orig = call i32 @llvm.amdgcn.raw.buffer.atomic.smin.i32(
define float @raw_buffer_atomic_smin(<4 x i32> inreg %rsrc, i32 inreg %data) #0 {
main_body:
%orig = call i32 @llvm.amdgcn.raw.buffer.atomic.smin.i32(i32 %data, <4 x i32> %rsrc, i32 0, i32 0, i32 0)
%r = bitcast i32 %orig to float
ret float %r
}
;CHECK: DIVERGENT: %orig = call i32 @llvm.amdgcn.raw.buffer.atomic.umin.i32(
define float @raw_buffer_atomic_umin(<4 x i32> inreg %rsrc, i32 inreg %data) #0 {
main_body:
%orig = call i32 @llvm.amdgcn.raw.buffer.atomic.umin.i32(i32 %data, <4 x i32> %rsrc, i32 0, i32 0, i32 0)
%r = bitcast i32 %orig to float
ret float %r
}
;CHECK: DIVERGENT: %orig = call i32 @llvm.amdgcn.raw.buffer.atomic.smax.i32(
define float @raw_buffer_atomic_smax(<4 x i32> inreg %rsrc, i32 inreg %data) #0 {
main_body:
%orig = call i32 @llvm.amdgcn.raw.buffer.atomic.smax.i32(i32 %data, <4 x i32> %rsrc, i32 0, i32 0, i32 0)
%r = bitcast i32 %orig to float
ret float %r
}
;CHECK: DIVERGENT: %orig = call i32 @llvm.amdgcn.raw.buffer.atomic.umax.i32(
define float @raw_buffer_atomic_umax(<4 x i32> inreg %rsrc, i32 inreg %data) #0 {
main_body:
%orig = call i32 @llvm.amdgcn.raw.buffer.atomic.umax.i32(i32 %data, <4 x i32> %rsrc, i32 0, i32 0, i32 0)
%r = bitcast i32 %orig to float
ret float %r
}
;CHECK: DIVERGENT: %orig = call i32 @llvm.amdgcn.raw.buffer.atomic.and.i32(
define float @raw_buffer_atomic_and(<4 x i32> inreg %rsrc, i32 inreg %data) #0 {
main_body:
%orig = call i32 @llvm.amdgcn.raw.buffer.atomic.and.i32(i32 %data, <4 x i32> %rsrc, i32 0, i32 0, i32 0)
%r = bitcast i32 %orig to float
ret float %r
}
;CHECK: DIVERGENT: %orig = call i32 @llvm.amdgcn.raw.buffer.atomic.or.i32(
define float @raw_buffer_atomic_or(<4 x i32> inreg %rsrc, i32 inreg %data) #0 {
main_body:
%orig = call i32 @llvm.amdgcn.raw.buffer.atomic.or.i32(i32 %data, <4 x i32> %rsrc, i32 0, i32 0, i32 0)
%r = bitcast i32 %orig to float
ret float %r
}
;CHECK: DIVERGENT: %orig = call i32 @llvm.amdgcn.raw.buffer.atomic.xor.i32(
define float @raw_buffer_atomic_xor(<4 x i32> inreg %rsrc, i32 inreg %data) #0 {
main_body:
%orig = call i32 @llvm.amdgcn.raw.buffer.atomic.xor.i32(i32 %data, <4 x i32> %rsrc, i32 0, i32 0, i32 0)
%r = bitcast i32 %orig to float
ret float %r
}
;CHECK: DIVERGENT: %orig = call i32 @llvm.amdgcn.raw.buffer.atomic.cmpswap.i32(
define float @raw_buffer_atomic_cmpswap(<4 x i32> inreg %rsrc, i32 inreg %data, i32 inreg %cmp) #0 {
main_body:
%orig = call i32 @llvm.amdgcn.raw.buffer.atomic.cmpswap.i32(i32 %data, i32 %cmp, <4 x i32> %rsrc, i32 0, i32 0, i32 0)
%r = bitcast i32 %orig to float
ret float %r
}
;CHECK: DIVERGENT: %orig = call i32 @llvm.amdgcn.struct.buffer.atomic.swap.i32(
define float @struct_buffer_atomic_swap(<4 x i32> inreg %rsrc, i32 inreg %data) #0 {
main_body:
%orig = call i32 @llvm.amdgcn.struct.buffer.atomic.swap.i32(i32 %data, <4 x i32> %rsrc, i32 0, i32 0, i32 0, i32 0)
%r = bitcast i32 %orig to float
ret float %r
}
;CHECK: DIVERGENT: %orig = call i32 @llvm.amdgcn.struct.buffer.atomic.add.i32(
define float @struct_buffer_atomic_add(<4 x i32> inreg %rsrc, i32 inreg %data) #0 {
main_body:
%orig = call i32 @llvm.amdgcn.struct.buffer.atomic.add.i32(i32 %data, <4 x i32> %rsrc, i32 0, i32 0, i32 0, i32 0)
%r = bitcast i32 %orig to float
ret float %r
}
;CHECK: DIVERGENT: %orig = call i32 @llvm.amdgcn.struct.buffer.atomic.sub.i32(
define float @struct_buffer_atomic_sub(<4 x i32> inreg %rsrc, i32 inreg %data) #0 {
main_body:
%orig = call i32 @llvm.amdgcn.struct.buffer.atomic.sub.i32(i32 %data, <4 x i32> %rsrc, i32 0, i32 0, i32 0, i32 0)
%r = bitcast i32 %orig to float
ret float %r
}
;CHECK: DIVERGENT: %orig = call i32 @llvm.amdgcn.struct.buffer.atomic.smin.i32(
define float @struct_buffer_atomic_smin(<4 x i32> inreg %rsrc, i32 inreg %data) #0 {
main_body:
%orig = call i32 @llvm.amdgcn.struct.buffer.atomic.smin.i32(i32 %data, <4 x i32> %rsrc, i32 0, i32 0, i32 0, i32 0)
%r = bitcast i32 %orig to float
ret float %r
}
;CHECK: DIVERGENT: %orig = call i32 @llvm.amdgcn.struct.buffer.atomic.umin.i32(
define float @struct_buffer_atomic_umin(<4 x i32> inreg %rsrc, i32 inreg %data) #0 {
main_body:
%orig = call i32 @llvm.amdgcn.struct.buffer.atomic.umin.i32(i32 %data, <4 x i32> %rsrc, i32 0, i32 0, i32 0, i32 0)
%r = bitcast i32 %orig to float
ret float %r
}
;CHECK: DIVERGENT: %orig = call i32 @llvm.amdgcn.struct.buffer.atomic.smax.i32(
define float @struct_buffer_atomic_smax(<4 x i32> inreg %rsrc, i32 inreg %data) #0 {
main_body:
%orig = call i32 @llvm.amdgcn.struct.buffer.atomic.smax.i32(i32 %data, <4 x i32> %rsrc, i32 0, i32 0, i32 0, i32 0)
%r = bitcast i32 %orig to float
ret float %r
}
;CHECK: DIVERGENT: %orig = call i32 @llvm.amdgcn.struct.buffer.atomic.umax.i32(
define float @struct_buffer_atomic_umax(<4 x i32> inreg %rsrc, i32 inreg %data) #0 {
main_body:
%orig = call i32 @llvm.amdgcn.struct.buffer.atomic.umax.i32(i32 %data, <4 x i32> %rsrc, i32 0, i32 0, i32 0, i32 0)
%r = bitcast i32 %orig to float
ret float %r
}
;CHECK: DIVERGENT: %orig = call i32 @llvm.amdgcn.struct.buffer.atomic.and.i32(
define float @struct_buffer_atomic_and(<4 x i32> inreg %rsrc, i32 inreg %data) #0 {
main_body:
%orig = call i32 @llvm.amdgcn.struct.buffer.atomic.and.i32(i32 %data, <4 x i32> %rsrc, i32 0, i32 0, i32 0, i32 0)
%r = bitcast i32 %orig to float
ret float %r
}
;CHECK: DIVERGENT: %orig = call i32 @llvm.amdgcn.struct.buffer.atomic.or.i32(
define float @struct_buffer_atomic_or(<4 x i32> inreg %rsrc, i32 inreg %data) #0 {
main_body:
%orig = call i32 @llvm.amdgcn.struct.buffer.atomic.or.i32(i32 %data, <4 x i32> %rsrc, i32 0, i32 0, i32 0, i32 0)
%r = bitcast i32 %orig to float
ret float %r
}
;CHECK: DIVERGENT: %orig = call i32 @llvm.amdgcn.struct.buffer.atomic.xor.i32(
define float @struct_buffer_atomic_xor(<4 x i32> inreg %rsrc, i32 inreg %data) #0 {
main_body:
%orig = call i32 @llvm.amdgcn.struct.buffer.atomic.xor.i32(i32 %data, <4 x i32> %rsrc, i32 0, i32 0, i32 0, i32 0)
%r = bitcast i32 %orig to float
ret float %r
}
;CHECK: DIVERGENT: %orig = call i32 @llvm.amdgcn.struct.buffer.atomic.cmpswap.i32(
define float @struct_buffer_atomic_cmpswap(<4 x i32> inreg %rsrc, i32 inreg %data, i32 inreg %cmp) #0 {
main_body:
%orig = call i32 @llvm.amdgcn.struct.buffer.atomic.cmpswap.i32(i32 %data, i32 %cmp, <4 x i32> %rsrc, i32 0, i32 0, i32 0, i32 0)
%r = bitcast i32 %orig to float
ret float %r
}
declare i32 @llvm.amdgcn.buffer.atomic.swap.i32(i32, <4 x i32>, i32, i32, i1) #0
declare i32 @llvm.amdgcn.buffer.atomic.add.i32(i32, <4 x i32>, i32, i32, i1) #0
declare i32 @llvm.amdgcn.buffer.atomic.sub.i32(i32, <4 x i32>, i32, i32, i1) #0
declare i32 @llvm.amdgcn.buffer.atomic.smin.i32(i32, <4 x i32>, i32, i32, i1) #0
declare i32 @llvm.amdgcn.buffer.atomic.umin.i32(i32, <4 x i32>, i32, i32, i1) #0
declare i32 @llvm.amdgcn.buffer.atomic.smax.i32(i32, <4 x i32>, i32, i32, i1) #0
declare i32 @llvm.amdgcn.buffer.atomic.umax.i32(i32, <4 x i32>, i32, i32, i1) #0
declare i32 @llvm.amdgcn.buffer.atomic.and.i32(i32, <4 x i32>, i32, i32, i1) #0
declare i32 @llvm.amdgcn.buffer.atomic.or.i32(i32, <4 x i32>, i32, i32, i1) #0
declare i32 @llvm.amdgcn.buffer.atomic.xor.i32(i32, <4 x i32>, i32, i32, i1) #0
declare i32 @llvm.amdgcn.buffer.atomic.cmpswap(i32, i32, <4 x i32>, i32, i32, i1) #0
declare i32 @llvm.amdgcn.raw.buffer.atomic.swap.i32(i32, <4 x i32>, i32, i32, i32) #0
declare i32 @llvm.amdgcn.raw.buffer.atomic.add.i32(i32, <4 x i32>, i32, i32, i32) #0
declare i32 @llvm.amdgcn.raw.buffer.atomic.sub.i32(i32, <4 x i32>, i32, i32, i32) #0
declare i32 @llvm.amdgcn.raw.buffer.atomic.smin.i32(i32, <4 x i32>, i32, i32, i32) #0
declare i32 @llvm.amdgcn.raw.buffer.atomic.umin.i32(i32, <4 x i32>, i32, i32, i32) #0
declare i32 @llvm.amdgcn.raw.buffer.atomic.smax.i32(i32, <4 x i32>, i32, i32, i32) #0
declare i32 @llvm.amdgcn.raw.buffer.atomic.umax.i32(i32, <4 x i32>, i32, i32, i32) #0
declare i32 @llvm.amdgcn.raw.buffer.atomic.and.i32(i32, <4 x i32>, i32, i32, i32) #0
declare i32 @llvm.amdgcn.raw.buffer.atomic.or.i32(i32, <4 x i32>, i32, i32, i32) #0
declare i32 @llvm.amdgcn.raw.buffer.atomic.xor.i32(i32, <4 x i32>, i32, i32, i32) #0
declare i32 @llvm.amdgcn.raw.buffer.atomic.cmpswap.i32(i32, i32, <4 x i32>, i32, i32, i32) #0
declare i32 @llvm.amdgcn.struct.buffer.atomic.swap.i32(i32, <4 x i32>, i32, i32, i32, i32) #0
declare i32 @llvm.amdgcn.struct.buffer.atomic.add.i32(i32, <4 x i32>, i32, i32, i32, i32) #0
declare i32 @llvm.amdgcn.struct.buffer.atomic.sub.i32(i32, <4 x i32>, i32, i32, i32, i32) #0
declare i32 @llvm.amdgcn.struct.buffer.atomic.smin.i32(i32, <4 x i32>, i32, i32, i32, i32) #0
declare i32 @llvm.amdgcn.struct.buffer.atomic.umin.i32(i32, <4 x i32>, i32, i32, i32, i32) #0
declare i32 @llvm.amdgcn.struct.buffer.atomic.smax.i32(i32, <4 x i32>, i32, i32, i32, i32) #0
declare i32 @llvm.amdgcn.struct.buffer.atomic.umax.i32(i32, <4 x i32>, i32, i32, i32, i32) #0
declare i32 @llvm.amdgcn.struct.buffer.atomic.and.i32(i32, <4 x i32>, i32, i32, i32, i32) #0
declare i32 @llvm.amdgcn.struct.buffer.atomic.or.i32(i32, <4 x i32>, i32, i32, i32, i32) #0
declare i32 @llvm.amdgcn.struct.buffer.atomic.xor.i32(i32, <4 x i32>, i32, i32, i32, i32) #0
declare i32 @llvm.amdgcn.struct.buffer.atomic.cmpswap.i32(i32, i32, <4 x i32>, i32, i32, i32, i32) #0
attributes #0 = { nounwind }
Reference in New Issue View Git Blame Copy Permalink