[PATCH] D82463: [AMDGPU] Spill more than wavesize CSR SGPRs
Saiyedul Islam via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Fri Jun 26 09:50:10 PDT 2020
saiislam updated this revision to Diff 273760.
saiislam added a comment.
Corrected the test case
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D82463/new/
https://reviews.llvm.org/D82463
Files:
llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp
llvm/test/CodeGen/AMDGPU/spill_more_than_wavesize_csr_sgprs.ll
Index: llvm/test/CodeGen/AMDGPU/spill_more_than_wavesize_csr_sgprs.ll
===================================================================
--- /dev/null
+++ llvm/test/CodeGen/AMDGPU/spill_more_than_wavesize_csr_sgprs.ll
@@ -0,0 +1,43 @@
+; RUN: llc -mtriple amdgcn-amd-amdhsa -mcpu=gfx803 -verify-machineinstrs < %s | FileCheck -enable-var-scope %s
+
+; CHECK-LABEL: {{^}}spill_more_than_wavesize_csr_sgprs:
+; CHECK: v_writelane_b32 v0, s98, 63
+; CHECK-NEXT: v_writelane_b32 v1, s99, 0
+; CHECK: v_readlane_b32 s99, v1, 0
+; CHECK-NEXT: v_readlane_b32 s98, v0, 63
+
+define void @spill_more_than_wavesize_csr_sgprs() {
+ call void asm sideeffect "",
+ "~{s35},~{s36},~{s37},~{s38},~{s39},~{s40},~{s41},~{s42}
+ ,~{s43},~{s44},~{s45},~{s46},~{s47},~{s48},~{s49},~{s50}
+ ,~{s51},~{s52},~{s53},~{s54},~{s55},~{s56},~{s57},~{s58}
+ ,~{s59},~{s60},~{s61},~{s62},~{s63},~{s64},~{s65},~{s66}
+ ,~{s67},~{s68},~{s69},~{s70},~{s71},~{s72},~{s73},~{s74}
+ ,~{s75},~{s76},~{s77},~{s78},~{s79},~{s80},~{s81},~{s82}
+ ,~{s83},~{s84},~{s85},~{s86},~{s87},~{s88},~{s89},~{s90}
+ ,~{s91},~{s92},~{s93},~{s94},~{s95},~{s96},~{s97},~{s98}
+ ,~{s99},~{s100},~{s101},~{s102}"()
+ ret void
+}
+
+; CHECK-LABEL: {{^}}spill_more_than_wavesize_csr_sgprs_with_stack_object:
+; CHECK: v_writelane_b32 v0, s98, 63
+; CHECK-NEXT: v_writelane_b32 v1, s99, 0
+; CHECK: v_readlane_b32 s99, v1, 0
+; CHECK-NEXT: v_readlane_b32 s98, v0, 63
+
+define void @spill_more_than_wavesize_csr_sgprs_with_stack_object() {
+ %alloca = alloca i32, align 4, addrspace(5)
+ store volatile i32 0, i32 addrspace(5)* %alloca
+ call void asm sideeffect "",
+ "~{s35},~{s36},~{s37},~{s38},~{s39},~{s40},~{s41},~{s42}
+ ,~{s43},~{s44},~{s45},~{s46},~{s47},~{s48},~{s49},~{s50}
+ ,~{s51},~{s52},~{s53},~{s54},~{s55},~{s56},~{s57},~{s58}
+ ,~{s59},~{s60},~{s61},~{s62},~{s63},~{s64},~{s65},~{s66}
+ ,~{s67},~{s68},~{s69},~{s70},~{s71},~{s72},~{s73},~{s74}
+ ,~{s75},~{s76},~{s77},~{s78},~{s79},~{s80},~{s81},~{s82}
+ ,~{s83},~{s84},~{s85},~{s86},~{s87},~{s88},~{s89},~{s90}
+ ,~{s91},~{s92},~{s93},~{s94},~{s95},~{s96},~{s97},~{s98}
+ ,~{s99},~{s100},~{s101},~{s102}"()
+ ret void
+}
Index: llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp
===================================================================
--- llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp
+++ llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp
@@ -303,7 +303,16 @@
Register LaneVGPR;
unsigned VGPRIndex = (NumVGPRSpillLanes % WaveSize);
- if (VGPRIndex == 0 && !FuncInfo->VGPRReservedForSGPRSpill) {
+ // Reserve a VGPR (when NumVGPRSpillLanes = 0, WaveSize, 2*WaveSize, ..) and
+ // when one of the two conditions is true:
+ // 1. One reserved VGPR being tracked by VGPRReservedForSGPRSpill is not yet
+ // reserved.
+ // 2. All spill lanes of reserved VGPR(s) are full and another spill lane is
+ // required.
+ if (FuncInfo->VGPRReservedForSGPRSpill && NumVGPRSpillLanes <= WaveSize) {
+ assert(FuncInfo->VGPRReservedForSGPRSpill == SpillVGPRs.back().VGPR);
+ LaneVGPR = FuncInfo->VGPRReservedForSGPRSpill;
+ } else if (VGPRIndex == 0) {
LaneVGPR = TRI->findUnusedRegister(MRI, &AMDGPU::VGPR_32RegClass, MF);
if (LaneVGPR == AMDGPU::NoRegister) {
// We have no VGPRs left for spilling SGPRs. Reset because we will not
-------------- next part --------------
A non-text attachment was scrubbed...
Name: D82463.273760.patch
Type: text/x-patch
Size: 3389 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200626/43ac0e9d/attachment.bin>
More information about the llvm-commits
mailing list