Skip to content

[AMDGPU] Shrink to SOPK with 32-bit signed literals #70263

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Oct 26, 2023
Merged

[AMDGPU] Shrink to SOPK with 32-bit signed literals #70263

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 10 additions & 5 deletions llvm/lib/Target/AMDGPU/SIShrinkInstructions.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -159,7 +159,7 @@ bool SIShrinkInstructions::shouldShrinkTrue16(MachineInstr &MI) const {
}

bool SIShrinkInstructions::isKImmOperand(const MachineOperand &Src) const {
return isInt<16>(Src.getImm()) &&
return isInt<16>(SignExtend64(Src.getImm(), 32)) &&
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could write this as isInt<16>((int32_t)Src.getImm()) but it's a matter of taste I guess.

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could write this as isInt<16>((int32_t)Src.getImm()) but it's a matter of taste I guess.

Same thing in principle.

!TII->isInlineConstant(*Src.getParent(), Src.getOperandNo());
}

Expand All @@ -170,7 +170,7 @@ bool SIShrinkInstructions::isKUImmOperand(const MachineOperand &Src) const {

bool SIShrinkInstructions::isKImmOrKUImmOperand(const MachineOperand &Src,
bool &IsUnsigned) const {
if (isInt<16>(Src.getImm())) {
if (isInt<16>(SignExtend64(Src.getImm(), 32))) {
IsUnsigned = false;
return !TII->isInlineConstant(Src);
}
Expand Down Expand Up @@ -221,7 +221,7 @@ void SIShrinkInstructions::shrinkScalarCompare(MachineInstr &MI) const {
if (!Src0.isReg())
return;

const MachineOperand &Src1 = MI.getOperand(1);
MachineOperand &Src1 = MI.getOperand(1);
if (!Src1.isImm())
return;

Expand All @@ -237,6 +237,7 @@ void SIShrinkInstructions::shrinkScalarCompare(MachineInstr &MI) const {
if (!HasUImm) {
SOPKOpc = (SOPKOpc == AMDGPU::S_CMPK_EQ_U32) ?
AMDGPU::S_CMPK_EQ_I32 : AMDGPU::S_CMPK_LG_I32;
Src1.setImm(SignExtend32(Src1.getImm(), 32));
}

MI.setDesc(TII->get(SOPKOpc));
Expand All @@ -249,6 +250,8 @@ void SIShrinkInstructions::shrinkScalarCompare(MachineInstr &MI) const {

if ((TII->sopkIsZext(SOPKOpc) && isKUImmOperand(Src1)) ||
(!TII->sopkIsZext(SOPKOpc) && isKImmOperand(Src1))) {
if (!TII->sopkIsZext(SOPKOpc))
Src1.setImm(SignExtend64(Src1.getImm(), 32));
MI.setDesc(NewDesc);
}
}
Expand Down Expand Up @@ -838,6 +841,7 @@ bool SIShrinkInstructions::runOnMachineFunction(MachineFunction &MF) {
unsigned Opc = (MI.getOpcode() == AMDGPU::S_ADD_I32) ?
AMDGPU::S_ADDK_I32 : AMDGPU::S_MULK_I32;

Src1->setImm(SignExtend64(Src1->getImm(), 32));
MI.setDesc(TII->get(Opc));
MI.tieOperands(0, 1);
}
Expand All @@ -857,9 +861,10 @@ bool SIShrinkInstructions::runOnMachineFunction(MachineFunction &MF) {

if (Src.isImm() && Dst.getReg().isPhysical()) {
int32_t ReverseImm;
if (isKImmOperand(Src))
if (isKImmOperand(Src)) {
MI.setDesc(TII->get(AMDGPU::S_MOVK_I32));
else if (isReverseInlineImm(Src, ReverseImm)) {
Src.setImm(SignExtend64(Src.getImm(), 32));
} else if (isReverseInlineImm(Src, ReverseImm)) {
MI.setDesc(TII->get(AMDGPU::S_BREV_B32));
Src.setImm(ReverseImm);
}
Expand Down
57 changes: 57 additions & 0 deletions llvm/test/CodeGen/AMDGPU/shrink-i32-kimm.mir
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,57 @@
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 3
# RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs -run-pass=si-shrink-instructions -o - %s | FileCheck -check-prefix=GCN %s

---
name: shrink_kimm32_mov_b32
tracksRegLiveness: true
body: |
bb.0:

; GCN-LABEL: name: shrink_kimm32_mov_b32
; GCN: $sgpr0 = S_MOVK_I32 -2048
$sgpr0 = S_MOV_B32 4294965248
...

---
name: shrink_kimm32_cmp_eq_u32
tracksRegLiveness: true
body: |
bb.0:

; GCN-LABEL: name: shrink_kimm32_cmp_eq_u32
; GCN: S_CMPK_EQ_I32 undef $sgpr0, -2048, implicit-def $scc
S_CMP_EQ_U32 undef $sgpr0, 4294965248, implicit-def $scc
...

---
name: shrink_kimm32_cmp_gt_i32
tracksRegLiveness: true
body: |
bb.0:

; GCN-LABEL: name: shrink_kimm32_cmp_gt_i32
; GCN: S_CMPK_GT_I32 undef $sgpr0, -2048, implicit-def $scc
S_CMP_GT_I32 undef $sgpr0, 4294965248, implicit-def $scc
...

---
name: shrink_kimm32_add_i32
tracksRegLiveness: true
body: |
bb.0:

; GCN-LABEL: name: shrink_kimm32_add_i32
; GCN: $sgpr0 = S_ADDK_I32 undef $sgpr0, -2048, implicit-def $scc
$sgpr0 = S_ADD_I32 undef $sgpr0, 4294965248, implicit-def $scc
...

---
name: shrink_kimm32_mul_i32
tracksRegLiveness: true
body: |
bb.0:

; GCN-LABEL: name: shrink_kimm32_mul_i32
; GCN: $sgpr0 = S_MULK_I32 undef $sgpr0, -2048, implicit-def $scc
$sgpr0 = S_MUL_I32 undef $sgpr0, 4294965248, implicit-def $scc
...