d09d834bb9
``` /// \returns Minimum number of VGPRs that meets given number of waves per /// execution unit requirement supported by the subtarget. unsigned getMinNumVGPRs(unsigned WavesPerEU) const; /// \returns Maximum number of VGPRs that meets given number of waves per /// execution unit requirement supported by the subtarget. unsigned getMaxNumVGPRs(unsigned WavesPerEU) const; /// Return the maximum number of waves per SIMD for kernels using \p VGPRs /// VGPRs unsigned getOccupancyWithNumVGPRs(unsigned VGPRs) const; ``` While working on RP tracking issues I noticed that getMinNumVGPRs return incorrect values: the problem is large VGPR granule sizes on GFX10+ architectures. Some of the occupancies aren't reachable because require the same amount of VGPR granules as others. For example 19 waves occupancy on gfx1010 require the same amount of granules as 20 waves so the resultng occupancy would be 20. SGPRs have the same issue and even have inconsistency between getMaxNumSGPRs and getOccupancyWithNumSGPRs. It will be addressed in the next patch. Legend: # MinVGPR and MaxVGPR are values returned by getMinNumVGPRs and getMaxNumVGPRs for a given Occ. # (ONumber) is the value returned by getOccupancyWithNumVGPRs for a given MinVGPR or MaxVGPR. # R means range problem: MinVGPR should be less than MaxVGPR and both should refer to the same occupancy. Unit test output without the fix: ``` ./build/unittests/Target/AMDGPU/AMDGPUTests --gtest_filter=AMDGPU.TestVGPRLimitsPerOccupancy --print-cpu-reg-limits gfx90a gfx940: Occ MinVGPR MaxVGPR 8 0 (O8) 64 (O8) 7 65 (O7) 72 (O7) 6 73 (O6) 80 (O6) 5 81 (O5) 96 (O5) 4 97 (O4) 128 (O4) 3 129 (O3) 168 (O3) 2 169 (O2) 256 (O2) 1 257 (O1) 512 (O1) gfx600 gfx600 gfx601 gfx601 gfx601 gfx602 gfx602 gfx602 gfx700 gfx700 gfx701 gfx701 gfx702 gfx703 gfx703 gfx703 gfx704 gfx704 gfx705 gfx801 gfx801 gfx802 gfx802 gfx802 gfx803 gfx803 gfx803 gfx803 gfx805 gfx805 gfx810 gfx810 gfx900 gfx902 gfx904 gfx906 gfx908 gfx909 gfx90c: Occ MinVGPR MaxVGPR 10 0 (O10) 24 (O10) 9 25 (O9) 28 (O9) 8 29 (O8) 32 (O8) 7 33 (O7) 36 (O7) 6 37 (O6) 40 (O6) 5 41 (O5) 48 (O5) 4 49 (O4) 64 (O4) 3 65 (O3) 84 (O3) 2 85 (O2) 128 (O2) 1 129 (O1) 256 (O1) gfx1030w64 gfx1031w64 gfx1032w64 gfx1033w64 gfx1034w64 gfx1035w64 gfx1036w64 gfx1102w64 gfx1103w64: Occ MinVGPR MaxVGPR 16 0 (O16) 32 (O16) 15 33 (O12) R 32 (O16) 14 33 (O12) R 32 (O16) 13 33 (O12) R 32 (O16) 12 33 (O12) 40 (O12) 11 41 (O10) R 40 (O12) 10 41 (O10) 48 (O10) 9 49 (O9) 56 (O9) 8 57 (O8) 64 (O8) 7 65 (O7) 72 (O7) 6 73 (O6) 80 (O6) 5 81 (O5) 96 (O5) 4 97 (O4) 128 (O4) 3 129 (O3) 168 (O3) 2 169 (O2) 256 (O2) 1 256 (O2) R 256 (O2) gfx1100w64 gfx1101w64: Occ MinVGPR MaxVGPR 16 0 (O16) 48 (O16) 15 49 (O12) R 48 (O16) 14 49 (O12) R 48 (O16) 13 49 (O12) R 48 (O16) 12 49 (O12) 60 (O12) 11 61 (O10) R 60 (O12) 10 61 (O10) 72 (O10) 9 73 (O9) 84 (O9) 8 85 (O8) 96 (O8) 7 97 (O7) 108 (O7) 6 109 (O6) 120 (O6) 5 121 (O5) 144 (O5) 4 145 (O4) 192 (O4) 3 193 (O3) 252 (O3) 2 253 (O2) 256 (O2) 1 256 (O2) R 256 (O2) gfx1030w32 gfx1031w32 gfx1032w32 gfx1033w32 gfx1034w32 gfx1035w32 gfx1036w32 gfx1102w32 gfx1103w32: Occ MinVGPR MaxVGPR 16 0 (O16) 64 (O16) 15 65 (O12) R 64 (O16) 14 65 (O12) R 64 (O16) 13 65 (O12) R 64 (O16) 12 65 (O12) 80 (O12) 11 81 (O10) R 80 (O12) 10 81 (O10) 96 (O10) 9 97 (O9) 112 (O9) 8 113 (O8) 128 (O8) 7 129 (O7) 144 (O7) 6 145 (O6) 160 (O6) 5 161 (O5) 192 (O5) 4 193 (O4) 256 (O4) 3 256 (O4) R 256 (O4) 2 256 (O4) R 256 (O4) 1 256 (O4) R 256 (O4) gfx1100w32 gfx1101w32: Occ MinVGPR MaxVGPR 16 0 (O16) 96 (O16) 15 97 (O12) R 96 (O16) 14 97 (O12) R 96 (O16) 13 97 (O12) R 96 (O16) 12 97 (O12) 120 (O12) 11 121 (O10) R 120 (O12) 10 121 (O10) 144 (O10) 9 145 (O9) 168 (O9) 8 169 (O8) 192 (O8) 7 193 (O7) 216 (O7) 6 217 (O6) 240 (O6) 5 241 (O5) 256 (O5) 4 256 (O5) R 256 (O5) 3 256 (O5) R 256 (O5) 2 256 (O5) R 256 (O5) 1 256 (O5) R 256 (O5) gfx1010w64 gfx1011w64 gfx1012w64 gfx1013w64: Occ MinVGPR MaxVGPR 20 0 (O20) 24 (O20) 19 25 (O18) R 24 (O20) 18 25 (O18) 28 (O18) 17 29 (O16) R 28 (O18) 16 29 (O16) 32 (O16) 15 33 (O14) R 32 (O16) 14 33 (O14) 36 (O14) 13 37 (O12) R 36 (O14) 12 37 (O12) 40 (O12) 11 41 (O11) 44 (O11) 10 45 (O10) 48 (O10) 9 49 (O9) 56 (O9) 8 57 (O8) 64 (O8) 7 65 (O7) 72 (O7) 6 73 (O6) 84 (O6) 5 85 (O5) 100 (O5) 4 101 (O4) 128 (O4) 3 129 (O3) 168 (O3) 2 169 (O2) 256 (O2) 1 256 (O2) R 256 (O2) gfx1010w32 gfx1011w32 gfx1012w32 gfx1013w32: Occ MinVGPR MaxVGPR 20 0 (O20) 48 (O20) 19 49 (O18) R 48 (O20) 18 49 (O18) 56 (O18) 17 57 (O16) R 56 (O18) 16 57 (O16) 64 (O16) 15 65 (O14) R 64 (O16) 14 65 (O14) 72 (O14) 13 73 (O12) R 72 (O14) 12 73 (O12) 80 (O12) 11 81 (O11) 88 (O11) 10 89 (O10) 96 (O10) 9 97 (O9) 112 (O9) 8 113 (O8) 128 (O8) 7 129 (O7) 144 (O7) 6 145 (O6) 168 (O6) 5 169 (O5) 200 (O5) 4 201 (O4) 256 (O4) 3 256 (O4) R 256 (O4) 2 256 (O4) R 256 (O4) 1 256 (O4) R 256 (O4) ``` After the fix: ``` gfx90a gfx940: Occ MinVGPR MaxVGPR 8 0 (O8) 64 (O8) 7 65 (O7) 72 (O7) 6 73 (O6) 80 (O6) 5 81 (O5) 96 (O5) 4 97 (O4) 128 (O4) 3 129 (O3) 168 (O3) 2 169 (O2) 256 (O2) 1 257 (O1) 512 (O1) gfx600 gfx600 gfx601 gfx601 gfx601 gfx602 gfx602 gfx602 gfx700 gfx700 gfx701 gfx701 gfx702 gfx703 gfx703 gfx703 gfx704 gfx704 gfx705 gfx801 gfx801 gfx802 gfx802 gfx802 gfx803 gfx803 gfx803 gfx803 gfx805 gfx805 gfx810 gfx810 gfx900 gfx902 gfx904 gfx906 gfx908 gfx909 gfx90c: Occ MinVGPR MaxVGPR 10 0 (O10) 24 (O10) 9 25 (O9) 28 (O9) 8 29 (O8) 32 (O8) 7 33 (O7) 36 (O7) 6 37 (O6) 40 (O6) 5 41 (O5) 48 (O5) 4 49 (O4) 64 (O4) 3 65 (O3) 84 (O3) 2 85 (O2) 128 (O2) 1 129 (O1) 256 (O1) gfx1030w64 gfx1031w64 gfx1032w64 gfx1033w64 gfx1034w64 gfx1035w64 gfx1036w64 gfx1102w64 gfx1103w64: Occ MinVGPR MaxVGPR 16 0 (O16) 32 (O16) 15 0 (O16) 32 (O16) 14 0 (O16) 32 (O16) 13 0 (O16) 32 (O16) 12 33 (O12) 40 (O12) 11 33 (O12) 40 (O12) 10 41 (O10) 48 (O10) 9 49 (O9) 56 (O9) 8 57 (O8) 64 (O8) 7 65 (O7) 72 (O7) 6 73 (O6) 80 (O6) 5 81 (O5) 96 (O5) 4 97 (O4) 128 (O4) 3 129 (O3) 168 (O3) 2 169 (O2) 256 (O2) 1 169 (O2) 256 (O2) gfx1100w64 gfx1101w64: Occ MinVGPR MaxVGPR 16 0 (O16) 48 (O16) 15 0 (O16) 48 (O16) 14 0 (O16) 48 (O16) 13 0 (O16) 48 (O16) 12 49 (O12) 60 (O12) 11 49 (O12) 60 (O12) 10 61 (O10) 72 (O10) 9 73 (O9) 84 (O9) 8 85 (O8) 96 (O8) 7 97 (O7) 108 (O7) 6 109 (O6) 120 (O6) 5 121 (O5) 144 (O5) 4 145 (O4) 192 (O4) 3 193 (O3) 252 (O3) 2 253 (O2) 256 (O2) 1 253 (O2) 256 (O2) gfx1030w32 gfx1031w32 gfx1032w32 gfx1033w32 gfx1034w32 gfx1035w32 gfx1036w32 gfx1102w32 gfx1103w32: Occ MinVGPR MaxVGPR 16 0 (O16) 64 (O16) 15 0 (O16) 64 (O16) 14 0 (O16) 64 (O16) 13 0 (O16) 64 (O16) 12 65 (O12) 80 (O12) 11 65 (O12) 80 (O12) 10 81 (O10) 96 (O10) 9 97 (O9) 112 (O9) 8 113 (O8) 128 (O8) 7 129 (O7) 144 (O7) 6 145 (O6) 160 (O6) 5 161 (O5) 192 (O5) 4 193 (O4) 256 (O4) 3 193 (O4) 256 (O4) 2 193 (O4) 256 (O4) 1 193 (O4) 256 (O4) gfx1100w32 gfx1101w32: Occ MinVGPR MaxVGPR 16 0 (O16) 96 (O16) 15 0 (O16) 96 (O16) 14 0 (O16) 96 (O16) 13 0 (O16) 96 (O16) 12 97 (O12) 120 (O12) 11 97 (O12) 120 (O12) 10 121 (O10) 144 (O10) 9 145 (O9) 168 (O9) 8 169 (O8) 192 (O8) 7 193 (O7) 216 (O7) 6 217 (O6) 240 (O6) 5 241 (O5) 256 (O5) 4 241 (O5) 256 (O5) 3 241 (O5) 256 (O5) 2 241 (O5) 256 (O5) 1 241 (O5) 256 (O5) gfx1010w64 gfx1011w64 gfx1012w64 gfx1013w64: Occ MinVGPR MaxVGPR 20 0 (O20) 24 (O20) 19 0 (O20) 24 (O20) 18 25 (O18) 28 (O18) 17 25 (O18) 28 (O18) 16 29 (O16) 32 (O16) 15 29 (O16) 32 (O16) 14 33 (O14) 36 (O14) 13 33 (O14) 36 (O14) 12 37 (O12) 40 (O12) 11 41 (O11) 44 (O11) 10 45 (O10) 48 (O10) 9 49 (O9) 56 (O9) 8 57 (O8) 64 (O8) 7 65 (O7) 72 (O7) 6 73 (O6) 84 (O6) 5 85 (O5) 100 (O5) 4 101 (O4) 128 (O4) 3 129 (O3) 168 (O3) 2 169 (O2) 256 (O2) 1 169 (O2) 256 (O2) gfx1010w32 gfx1011w32 gfx1012w32 gfx1013w32: Occ MinVGPR MaxVGPR 20 0 (O20) 48 (O20) 19 0 (O20) 48 (O20) 18 49 (O18) 56 (O18) 17 49 (O18) 56 (O18) 16 57 (O16) 64 (O16) 15 57 (O16) 64 (O16) 14 65 (O14) 72 (O14) 13 65 (O14) 72 (O14) 12 73 (O12) 80 (O12) 11 81 (O11) 88 (O11) 10 89 (O10) 96 (O10) 9 97 (O9) 112 (O9) 8 113 (O8) 128 (O8) 7 129 (O7) 144 (O7) 6 145 (O6) 168 (O6) 5 169 (O5) 200 (O5) 4 201 (O4) 256 (O4) 3 201 (O4) 256 (O4) 2 201 (O4) 256 (O4) 1 201 (O4) 256 (O4) ``` Reviewed By: #amdgpu, arsenm Differential Revision: https://reviews.llvm.org/D138443
60 lines
2.2 KiB
C++
60 lines
2.2 KiB
C++
//===- llvm/unittests/Target/AMDGPU/DwarfRegMappings.cpp ------------------===//
|
|
//
|
|
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
|
|
// See https://llvm.org/LICENSE.txt for license information.
|
|
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include "AMDGPUTargetMachine.h"
|
|
#include "AMDGPUUnitTests.h"
|
|
#include "gtest/gtest.h"
|
|
|
|
using namespace llvm;
|
|
|
|
TEST(AMDGPU, TestWave64DwarfRegMapping) {
|
|
for (auto Triple :
|
|
{"amdgcn-amd-", "amdgcn-amd-amdhsa", "amdgcn-amd-amdpal"}) {
|
|
auto TM = createAMDGPUTargetMachine(Triple, "gfx1010", "+wavefrontsize64");
|
|
if (TM) {
|
|
GCNSubtarget ST(TM->getTargetTriple(), std::string(TM->getTargetCPU()),
|
|
std::string(TM->getTargetFeatureString()), *TM);
|
|
auto MRI = ST.getRegisterInfo();
|
|
if (MRI) {
|
|
// Wave64 Dwarf register mapping test numbers
|
|
// PC_64 => 16, EXEC_MASK_64 => 17, S0 => 32, S63 => 95,
|
|
// S64 => 1088, S105 => 1129, V0 => 2560, V255 => 2815,
|
|
// A0 => 3072, A255 => 3327
|
|
for (int llvmReg :
|
|
{16, 17, 32, 95, 1088, 1129, 2560, 2815, 3072, 3327}) {
|
|
MCRegister PCReg(*MRI->getLLVMRegNum(llvmReg, false));
|
|
EXPECT_EQ(llvmReg, MRI->getDwarfRegNum(PCReg, false));
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
TEST(AMDGPU, TestWave32DwarfRegMapping) {
|
|
for (auto Triple :
|
|
{"amdgcn-amd-", "amdgcn-amd-amdhsa", "amdgcn-amd-amdpal"}) {
|
|
auto TM = createAMDGPUTargetMachine(Triple, "gfx1010", "+wavefrontsize32");
|
|
if (TM) {
|
|
GCNSubtarget ST(TM->getTargetTriple(), std::string(TM->getTargetCPU()),
|
|
std::string(TM->getTargetFeatureString()), *TM);
|
|
auto MRI = ST.getRegisterInfo();
|
|
if (MRI) {
|
|
// Wave32 Dwarf register mapping test numbers
|
|
// PC_64 => 16, EXEC_MASK_32 => 1, S0 => 32, S63 => 95,
|
|
// S64 => 1088, S105 => 1129, V0 => 1536, V255 => 1791,
|
|
// A0 => 2048, A255 => 2303
|
|
for (int llvmReg :
|
|
{16, 1, 32, 95, 1088, 1129, 1536, 1791, 2048, 2303}) {
|
|
MCRegister PCReg(*MRI->getLLVMRegNum(llvmReg, false));
|
|
EXPECT_EQ(llvmReg, MRI->getDwarfRegNum(PCReg, false));
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|