[RISCV] Use shNadd for scalable stack offsets #88062
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
If we need to multiply VLENB by 2, 4, or 8 and add it to the stack pointer, we can do so with a shNadd instead of separate shift and add instructions.
|
@llvm/pr-subscribers-backend-risc-v Author: Philip Reames (preames) ChangesIf we need to multiply VLENB by 2, 4, or 8 and add it to the stack pointer, we can do so with a shNadd instead of separate shift and add instructions. Full diff: https://github.com/llvm/llvm-project/pull/88062.diff 2 Files Affected:
diff --git a/llvm/lib/Target/RISCV/RISCVRegisterInfo.cpp b/llvm/lib/Target/RISCV/RISCVRegisterInfo.cpp
index 713260b090e9cf..ce8fdf9384b8e2 100644
--- a/llvm/lib/Target/RISCV/RISCVRegisterInfo.cpp
+++ b/llvm/lib/Target/RISCV/RISCVRegisterInfo.cpp
@@ -204,10 +204,21 @@ void RISCVRegisterInfo::adjustReg(MachineBasicBlock &MBB,
uint32_t NumOfVReg = ScalableValue / 8;
BuildMI(MBB, II, DL, TII->get(RISCV::PseudoReadVLENB), ScratchReg)
.setMIFlag(Flag);
- TII->mulImm(MF, MBB, II, DL, ScratchReg, NumOfVReg, Flag);
- BuildMI(MBB, II, DL, TII->get(ScalableAdjOpc), DestReg)
- .addReg(SrcReg).addReg(ScratchReg, RegState::Kill)
- .setMIFlag(Flag);
+
+ if (ScalableAdjOpc == RISCV::ADD && ST.hasStdExtZba() &&
+ (NumOfVReg == 2 || NumOfVReg == 4 || NumOfVReg == 8)) {
+ unsigned Opc = NumOfVReg == 2 ? RISCV::SH1ADD :
+ (NumOfVReg == 4 ? RISCV::SH2ADD : RISCV::SH3ADD);
+ BuildMI(MBB, II, DL, TII->get(Opc), DestReg)
+ .addReg(ScratchReg, RegState::Kill)
+ .addReg(SrcReg, getKillRegState(KillSrcReg))
+ .setMIFlag(Flag);
+ } else {
+ TII->mulImm(MF, MBB, II, DL, ScratchReg, NumOfVReg, Flag);
+ BuildMI(MBB, II, DL, TII->get(ScalableAdjOpc), DestReg)
+ .addReg(SrcReg).addReg(ScratchReg, RegState::Kill)
+ .setMIFlag(Flag);
+ }
SrcReg = DestReg;
KillSrcReg = true;
}
diff --git a/llvm/test/CodeGen/RISCV/rvv/allocate-lmul-2-4-8.ll b/llvm/test/CodeGen/RISCV/rvv/allocate-lmul-2-4-8.ll
index 466ab085b266b4..90794820ddd849 100644
--- a/llvm/test/CodeGen/RISCV/rvv/allocate-lmul-2-4-8.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/allocate-lmul-2-4-8.ll
@@ -7,29 +7,67 @@
; RUN: | FileCheck %s --check-prefixes=CHECK,NOMUL
define void @lmul1() nounwind {
-; CHECK-LABEL: lmul1:
-; CHECK: # %bb.0:
-; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 1
-; CHECK-NEXT: sub sp, sp, a0
-; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 1
-; CHECK-NEXT: add sp, sp, a0
-; CHECK-NEXT: ret
+; NOZBA-LABEL: lmul1:
+; NOZBA: # %bb.0:
+; NOZBA-NEXT: csrr a0, vlenb
+; NOZBA-NEXT: slli a0, a0, 1
+; NOZBA-NEXT: sub sp, sp, a0
+; NOZBA-NEXT: csrr a0, vlenb
+; NOZBA-NEXT: slli a0, a0, 1
+; NOZBA-NEXT: add sp, sp, a0
+; NOZBA-NEXT: ret
+;
+; ZBA-LABEL: lmul1:
+; ZBA: # %bb.0:
+; ZBA-NEXT: csrr a0, vlenb
+; ZBA-NEXT: slli a0, a0, 1
+; ZBA-NEXT: sub sp, sp, a0
+; ZBA-NEXT: csrr a0, vlenb
+; ZBA-NEXT: sh1add sp, a0, sp
+; ZBA-NEXT: ret
+;
+; NOMUL-LABEL: lmul1:
+; NOMUL: # %bb.0:
+; NOMUL-NEXT: csrr a0, vlenb
+; NOMUL-NEXT: slli a0, a0, 1
+; NOMUL-NEXT: sub sp, sp, a0
+; NOMUL-NEXT: csrr a0, vlenb
+; NOMUL-NEXT: slli a0, a0, 1
+; NOMUL-NEXT: add sp, sp, a0
+; NOMUL-NEXT: ret
%v = alloca <vscale x 1 x i64>
ret void
}
define void @lmul2() nounwind {
-; CHECK-LABEL: lmul2:
-; CHECK: # %bb.0:
-; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 1
-; CHECK-NEXT: sub sp, sp, a0
-; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 1
-; CHECK-NEXT: add sp, sp, a0
-; CHECK-NEXT: ret
+; NOZBA-LABEL: lmul2:
+; NOZBA: # %bb.0:
+; NOZBA-NEXT: csrr a0, vlenb
+; NOZBA-NEXT: slli a0, a0, 1
+; NOZBA-NEXT: sub sp, sp, a0
+; NOZBA-NEXT: csrr a0, vlenb
+; NOZBA-NEXT: slli a0, a0, 1
+; NOZBA-NEXT: add sp, sp, a0
+; NOZBA-NEXT: ret
+;
+; ZBA-LABEL: lmul2:
+; ZBA: # %bb.0:
+; ZBA-NEXT: csrr a0, vlenb
+; ZBA-NEXT: slli a0, a0, 1
+; ZBA-NEXT: sub sp, sp, a0
+; ZBA-NEXT: csrr a0, vlenb
+; ZBA-NEXT: sh1add sp, a0, sp
+; ZBA-NEXT: ret
+;
+; NOMUL-LABEL: lmul2:
+; NOMUL: # %bb.0:
+; NOMUL-NEXT: csrr a0, vlenb
+; NOMUL-NEXT: slli a0, a0, 1
+; NOMUL-NEXT: sub sp, sp, a0
+; NOMUL-NEXT: csrr a0, vlenb
+; NOMUL-NEXT: slli a0, a0, 1
+; NOMUL-NEXT: add sp, sp, a0
+; NOMUL-NEXT: ret
%v = alloca <vscale x 2 x i64>
ret void
}
@@ -75,15 +113,34 @@ define void @lmul8() nounwind {
}
define void @lmul1_and_2() nounwind {
-; CHECK-LABEL: lmul1_and_2:
-; CHECK: # %bb.0:
-; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 2
-; CHECK-NEXT: sub sp, sp, a0
-; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 2
-; CHECK-NEXT: add sp, sp, a0
-; CHECK-NEXT: ret
+; NOZBA-LABEL: lmul1_and_2:
+; NOZBA: # %bb.0:
+; NOZBA-NEXT: csrr a0, vlenb
+; NOZBA-NEXT: slli a0, a0, 2
+; NOZBA-NEXT: sub sp, sp, a0
+; NOZBA-NEXT: csrr a0, vlenb
+; NOZBA-NEXT: slli a0, a0, 2
+; NOZBA-NEXT: add sp, sp, a0
+; NOZBA-NEXT: ret
+;
+; ZBA-LABEL: lmul1_and_2:
+; ZBA: # %bb.0:
+; ZBA-NEXT: csrr a0, vlenb
+; ZBA-NEXT: slli a0, a0, 2
+; ZBA-NEXT: sub sp, sp, a0
+; ZBA-NEXT: csrr a0, vlenb
+; ZBA-NEXT: sh2add sp, a0, sp
+; ZBA-NEXT: ret
+;
+; NOMUL-LABEL: lmul1_and_2:
+; NOMUL: # %bb.0:
+; NOMUL-NEXT: csrr a0, vlenb
+; NOMUL-NEXT: slli a0, a0, 2
+; NOMUL-NEXT: sub sp, sp, a0
+; NOMUL-NEXT: csrr a0, vlenb
+; NOMUL-NEXT: slli a0, a0, 2
+; NOMUL-NEXT: add sp, sp, a0
+; NOMUL-NEXT: ret
%v1 = alloca <vscale x 1 x i64>
%v2 = alloca <vscale x 2 x i64>
ret void
@@ -132,15 +189,34 @@ define void @lmul1_and_4() nounwind {
}
define void @lmul2_and_1() nounwind {
-; CHECK-LABEL: lmul2_and_1:
-; CHECK: # %bb.0:
-; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 2
-; CHECK-NEXT: sub sp, sp, a0
-; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 2
-; CHECK-NEXT: add sp, sp, a0
-; CHECK-NEXT: ret
+; NOZBA-LABEL: lmul2_and_1:
+; NOZBA: # %bb.0:
+; NOZBA-NEXT: csrr a0, vlenb
+; NOZBA-NEXT: slli a0, a0, 2
+; NOZBA-NEXT: sub sp, sp, a0
+; NOZBA-NEXT: csrr a0, vlenb
+; NOZBA-NEXT: slli a0, a0, 2
+; NOZBA-NEXT: add sp, sp, a0
+; NOZBA-NEXT: ret
+;
+; ZBA-LABEL: lmul2_and_1:
+; ZBA: # %bb.0:
+; ZBA-NEXT: csrr a0, vlenb
+; ZBA-NEXT: slli a0, a0, 2
+; ZBA-NEXT: sub sp, sp, a0
+; ZBA-NEXT: csrr a0, vlenb
+; ZBA-NEXT: sh2add sp, a0, sp
+; ZBA-NEXT: ret
+;
+; NOMUL-LABEL: lmul2_and_1:
+; NOMUL: # %bb.0:
+; NOMUL-NEXT: csrr a0, vlenb
+; NOMUL-NEXT: slli a0, a0, 2
+; NOMUL-NEXT: sub sp, sp, a0
+; NOMUL-NEXT: csrr a0, vlenb
+; NOMUL-NEXT: slli a0, a0, 2
+; NOMUL-NEXT: add sp, sp, a0
+; NOMUL-NEXT: ret
%v1 = alloca <vscale x 2 x i64>
%v2 = alloca <vscale x 1 x i64>
ret void
@@ -273,19 +349,46 @@ define void @lmul4_and_2_x2_1() nounwind {
define void @gpr_and_lmul1_and_2() nounwind {
-; CHECK-LABEL: gpr_and_lmul1_and_2:
-; CHECK: # %bb.0:
-; CHECK-NEXT: addi sp, sp, -16
-; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 2
-; CHECK-NEXT: sub sp, sp, a0
-; CHECK-NEXT: li a0, 3
-; CHECK-NEXT: sd a0, 8(sp)
-; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 2
-; CHECK-NEXT: add sp, sp, a0
-; CHECK-NEXT: addi sp, sp, 16
-; CHECK-NEXT: ret
+; NOZBA-LABEL: gpr_and_lmul1_and_2:
+; NOZBA: # %bb.0:
+; NOZBA-NEXT: addi sp, sp, -16
+; NOZBA-NEXT: csrr a0, vlenb
+; NOZBA-NEXT: slli a0, a0, 2
+; NOZBA-NEXT: sub sp, sp, a0
+; NOZBA-NEXT: li a0, 3
+; NOZBA-NEXT: sd a0, 8(sp)
+; NOZBA-NEXT: csrr a0, vlenb
+; NOZBA-NEXT: slli a0, a0, 2
+; NOZBA-NEXT: add sp, sp, a0
+; NOZBA-NEXT: addi sp, sp, 16
+; NOZBA-NEXT: ret
+;
+; ZBA-LABEL: gpr_and_lmul1_and_2:
+; ZBA: # %bb.0:
+; ZBA-NEXT: addi sp, sp, -16
+; ZBA-NEXT: csrr a0, vlenb
+; ZBA-NEXT: slli a0, a0, 2
+; ZBA-NEXT: sub sp, sp, a0
+; ZBA-NEXT: li a0, 3
+; ZBA-NEXT: sd a0, 8(sp)
+; ZBA-NEXT: csrr a0, vlenb
+; ZBA-NEXT: sh2add sp, a0, sp
+; ZBA-NEXT: addi sp, sp, 16
+; ZBA-NEXT: ret
+;
+; NOMUL-LABEL: gpr_and_lmul1_and_2:
+; NOMUL: # %bb.0:
+; NOMUL-NEXT: addi sp, sp, -16
+; NOMUL-NEXT: csrr a0, vlenb
+; NOMUL-NEXT: slli a0, a0, 2
+; NOMUL-NEXT: sub sp, sp, a0
+; NOMUL-NEXT: li a0, 3
+; NOMUL-NEXT: sd a0, 8(sp)
+; NOMUL-NEXT: csrr a0, vlenb
+; NOMUL-NEXT: slli a0, a0, 2
+; NOMUL-NEXT: add sp, sp, a0
+; NOMUL-NEXT: addi sp, sp, 16
+; NOMUL-NEXT: ret
%x1 = alloca i64
%v1 = alloca <vscale x 1 x i64>
%v2 = alloca <vscale x 2 x i64>
@@ -396,15 +499,34 @@ define void @lmul_1_2_4_8_x2_1() nounwind {
}
define void @masks() nounwind {
-; CHECK-LABEL: masks:
-; CHECK: # %bb.0:
-; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 2
-; CHECK-NEXT: sub sp, sp, a0
-; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 2
-; CHECK-NEXT: add sp, sp, a0
-; CHECK-NEXT: ret
+; NOZBA-LABEL: masks:
+; NOZBA: # %bb.0:
+; NOZBA-NEXT: csrr a0, vlenb
+; NOZBA-NEXT: slli a0, a0, 2
+; NOZBA-NEXT: sub sp, sp, a0
+; NOZBA-NEXT: csrr a0, vlenb
+; NOZBA-NEXT: slli a0, a0, 2
+; NOZBA-NEXT: add sp, sp, a0
+; NOZBA-NEXT: ret
+;
+; ZBA-LABEL: masks:
+; ZBA: # %bb.0:
+; ZBA-NEXT: csrr a0, vlenb
+; ZBA-NEXT: slli a0, a0, 2
+; ZBA-NEXT: sub sp, sp, a0
+; ZBA-NEXT: csrr a0, vlenb
+; ZBA-NEXT: sh2add sp, a0, sp
+; ZBA-NEXT: ret
+;
+; NOMUL-LABEL: masks:
+; NOMUL: # %bb.0:
+; NOMUL-NEXT: csrr a0, vlenb
+; NOMUL-NEXT: slli a0, a0, 2
+; NOMUL-NEXT: sub sp, sp, a0
+; NOMUL-NEXT: csrr a0, vlenb
+; NOMUL-NEXT: slli a0, a0, 2
+; NOMUL-NEXT: add sp, sp, a0
+; NOMUL-NEXT: ret
%v1 = alloca <vscale x 1 x i1>
%v2 = alloca <vscale x 2 x i1>
%v4 = alloca <vscale x 4 x i1>
|
You can test this locally with the following command:git-clang-format --diff f5cf98c02655de50401f6547ea181efed6a4c1f1 646e509c90215405453a78c578d240590cab518a -- llvm/lib/Target/RISCV/RISCVRegisterInfo.cppView the diff from clang-format here.diff --git a/llvm/lib/Target/RISCV/RISCVRegisterInfo.cpp b/llvm/lib/Target/RISCV/RISCVRegisterInfo.cpp
index ce8fdf9384..11d0368cef 100644
--- a/llvm/lib/Target/RISCV/RISCVRegisterInfo.cpp
+++ b/llvm/lib/Target/RISCV/RISCVRegisterInfo.cpp
@@ -207,8 +207,9 @@ void RISCVRegisterInfo::adjustReg(MachineBasicBlock &MBB,
if (ScalableAdjOpc == RISCV::ADD && ST.hasStdExtZba() &&
(NumOfVReg == 2 || NumOfVReg == 4 || NumOfVReg == 8)) {
- unsigned Opc = NumOfVReg == 2 ? RISCV::SH1ADD :
- (NumOfVReg == 4 ? RISCV::SH2ADD : RISCV::SH3ADD);
+ unsigned Opc = NumOfVReg == 2
+ ? RISCV::SH1ADD
+ : (NumOfVReg == 4 ? RISCV::SH2ADD : RISCV::SH3ADD);
BuildMI(MBB, II, DL, TII->get(Opc), DestReg)
.addReg(ScratchReg, RegState::Kill)
.addReg(SrcReg, getKillRegState(KillSrcReg))
@@ -216,7 +217,8 @@ void RISCVRegisterInfo::adjustReg(MachineBasicBlock &MBB,
} else {
TII->mulImm(MF, MBB, II, DL, ScratchReg, NumOfVReg, Flag);
BuildMI(MBB, II, DL, TII->get(ScalableAdjOpc), DestReg)
- .addReg(SrcReg).addReg(ScratchReg, RegState::Kill)
+ .addReg(SrcReg)
+ .addReg(ScratchReg, RegState::Kill)
.setMIFlag(Flag);
}
SrcReg = DestReg;
|
frasercrmck
approved these changes
Apr 9, 2024
frasercrmck
reviewed
Apr 9, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
If we need to multiply VLENB by 2, 4, or 8 and add it to the stack pointer, we can do so with a shNadd instead of separate shift and add instructions.