[llvm] 7ac8486 - [RISCVInsertVSETVLI] Allow PRE with non-immediate AVLs (#71728)
via llvm-commits
llvm-commits at lists.llvm.org
Thu Nov 9 08:03:17 PST 2023
Author: Philip Reames
Date: 2023-11-09T08:03:13-08:00
New Revision: 7ac8486e54d99ed72c15da391dbeed134a37bae5
URL: https://github.com/llvm/llvm-project/commit/7ac8486e54d99ed72c15da391dbeed134a37bae5
DIFF: https://github.com/llvm/llvm-project/commit/7ac8486e54d99ed72c15da391dbeed134a37bae5.diff
LOG: [RISCVInsertVSETVLI] Allow PRE with non-immediate AVLs (#71728)
Extend our PRE logic to cover non-immediate AVL values. This covers
large constant AVLs (which must be materialized in registers), and may
help some code written explicitly with intrinsics.
Looking at the existing code, I can't entirely figure out why I thought
we needed VL == AVL to perform the PRE. My best guess is that I was
worried about the VLMAX < VL < 2 * VLMAX case, but the spec explicitly
says that vsetvli must be determinist on any particular AVL value.
That case was, possibly by accident, covering another legality
precondition. Specifically, by only returning true for immediate and
VLMAX AVL values, we didn't encounter the case where the AVL was a
register and that register wasn't available in the predecessor (e.g. if
AVL is a load in the MBB block itself).
---------
Co-authored-by: Luke Lau <luke_lau at icloud.com>
Added:
Modified:
llvm/lib/Target/RISCV/RISCVInsertVSETVLI.cpp
llvm/test/CodeGen/RISCV/rvv/fixed-vectors-strided-load-store-asm.ll
llvm/test/CodeGen/RISCV/rvv/sink-splat-operands.ll
Removed:
################################################################################
diff --git a/llvm/lib/Target/RISCV/RISCVInsertVSETVLI.cpp b/llvm/lib/Target/RISCV/RISCVInsertVSETVLI.cpp
index f6d8b1f0a70e13d..999ff9920716e87 100644
--- a/llvm/lib/Target/RISCV/RISCVInsertVSETVLI.cpp
+++ b/llvm/lib/Target/RISCV/RISCVInsertVSETVLI.cpp
@@ -1308,29 +1308,6 @@ void RISCVInsertVSETVLI::emitVSETVLIs(MachineBasicBlock &MBB) {
}
}
-/// Return true if the VL value configured by a vset(i)vli with the
-/// provided Info must be equal to the requested AVL. That is, that
-/// AVL <= VLMAX.
-static bool willVLBeAVL(const VSETVLIInfo &Info, const RISCVSubtarget &ST) {
- if (!Info.hasAVLImm())
- // VLMAX is always the same value.
- // TODO: Could extend to other registers by looking at the associated vreg
- // def placement.
- return RISCV::X0 == Info.getAVLReg();
-
- unsigned AVL = Info.getAVLImm();
- unsigned SEW = Info.getSEW();
- unsigned AVLInBits = AVL * SEW;
-
- unsigned LMul;
- bool Fractional;
- std::tie(LMul, Fractional) = RISCVVType::decodeVLMUL(Info.getVLMUL());
-
- if (Fractional)
- return ST.getRealMinVLen() / LMul >= AVLInBits;
- return ST.getRealMinVLen() * LMul >= AVLInBits;
-}
-
/// Perform simple partial redundancy elimination of the VSETVLI instructions
/// we're about to insert by looking for cases where we can PRE from the
/// beginning of one block to the end of one of its predecessors. Specifically,
@@ -1364,9 +1341,21 @@ void RISCVInsertVSETVLI::doPRE(MachineBasicBlock &MBB) {
if (UnavailablePred->succ_size() != 1)
return;
- // If VL can be less than AVL, then we can't reduce the frequency of exec.
- if (!willVLBeAVL(AvailableInfo, *ST))
- return;
+ // If the AVL value is a register (other than our VLMAX sentinel),
+ // we need to prove the value is available at the point we're going
+ // to insert the vsetvli at.
+ if (AvailableInfo.hasAVLReg() && RISCV::X0 != AvailableInfo.getAVLReg()) {
+ MachineInstr *AVLDefMI = MRI->getVRegDef(AvailableInfo.getAVLReg());
+ if (!AVLDefMI)
+ return;
+ // This is an inline dominance check which covers the case of
+ // UnavailablePred being the preheader of a loop.
+ if (AVLDefMI->getParent() != UnavailablePred)
+ return;
+ for (auto &TermMI : UnavailablePred->terminators())
+ if (&TermMI == AVLDefMI)
+ return;
+ }
// Model the effect of changing the input state of the block MBB to
// AvailableInfo. We're looking for two issues here; one legality,
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-strided-load-store-asm.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-strided-load-store-asm.ll
index ef970ad63ae77a8..846295b3ead27dc 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-strided-load-store-asm.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-strided-load-store-asm.ll
@@ -14,12 +14,12 @@ define void @gather(ptr noalias nocapture %A, ptr noalias nocapture readonly %B)
; CHECK-LABEL: gather:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: li a2, 1024
-; CHECK-NEXT: li a3, 32
-; CHECK-NEXT: li a4, 5
+; CHECK-NEXT: li a4, 32
+; CHECK-NEXT: li a3, 5
+; CHECK-NEXT: vsetvli zero, a4, e8, m1, ta, ma
; CHECK-NEXT: .LBB0_1: # %vector.body
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
-; CHECK-NEXT: vsetvli zero, a3, e8, m1, ta, ma
-; CHECK-NEXT: vlse8.v v8, (a1), a4
+; CHECK-NEXT: vlse8.v v8, (a1), a3
; CHECK-NEXT: vle8.v v9, (a0)
; CHECK-NEXT: vadd.vv v8, v9, v8
; CHECK-NEXT: vse8.v v8, (a0)
@@ -126,12 +126,12 @@ define void @gather_negative_stride(ptr noalias nocapture %A, ptr noalias nocapt
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addi a1, a1, 155
; CHECK-NEXT: li a2, 1024
-; CHECK-NEXT: li a3, 32
-; CHECK-NEXT: li a4, -5
+; CHECK-NEXT: li a4, 32
+; CHECK-NEXT: li a3, -5
+; CHECK-NEXT: vsetvli zero, a4, e8, m1, ta, ma
; CHECK-NEXT: .LBB2_1: # %vector.body
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
-; CHECK-NEXT: vsetvli zero, a3, e8, m1, ta, ma
-; CHECK-NEXT: vlse8.v v8, (a1), a4
+; CHECK-NEXT: vlse8.v v8, (a1), a3
; CHECK-NEXT: vle8.v v9, (a0)
; CHECK-NEXT: vadd.vv v8, v9, v8
; CHECK-NEXT: vse8.v v8, (a0)
@@ -168,12 +168,12 @@ define void @gather_zero_stride(ptr noalias nocapture %A, ptr noalias nocapture
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: li a2, 1024
; CHECK-NEXT: li a3, 32
+; CHECK-NEXT: vsetvli zero, a3, e8, m1, ta, ma
; CHECK-NEXT: .LBB3_1: # %vector.body
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
-; CHECK-NEXT: lbu a4, 0(a1)
-; CHECK-NEXT: vsetvli zero, a3, e8, m1, ta, ma
+; CHECK-NEXT: lbu a3, 0(a1)
; CHECK-NEXT: vle8.v v8, (a0)
-; CHECK-NEXT: vadd.vx v8, v8, a4
+; CHECK-NEXT: vadd.vx v8, v8, a3
; CHECK-NEXT: vse8.v v8, (a0)
; CHECK-NEXT: addi a2, a2, -32
; CHECK-NEXT: addi a0, a0, 32
@@ -208,9 +208,9 @@ define void @gather_zero_stride_unfold(ptr noalias nocapture %A, ptr noalias noc
; V: # %bb.0: # %entry
; V-NEXT: li a2, 1024
; V-NEXT: li a3, 32
+; V-NEXT: vsetvli zero, a3, e8, m1, ta, ma
; V-NEXT: .LBB4_1: # %vector.body
; V-NEXT: # =>This Inner Loop Header: Depth=1
-; V-NEXT: vsetvli zero, a3, e8, m1, ta, ma
; V-NEXT: vlse8.v v8, (a1), zero
; V-NEXT: vle8.v v9, (a0)
; V-NEXT: vdivu.vv v8, v8, v9
@@ -226,9 +226,9 @@ define void @gather_zero_stride_unfold(ptr noalias nocapture %A, ptr noalias noc
; ZVE32F: # %bb.0: # %entry
; ZVE32F-NEXT: li a2, 1024
; ZVE32F-NEXT: li a3, 32
+; ZVE32F-NEXT: vsetvli zero, a3, e8, m1, ta, ma
; ZVE32F-NEXT: .LBB4_1: # %vector.body
; ZVE32F-NEXT: # =>This Inner Loop Header: Depth=1
-; ZVE32F-NEXT: vsetvli zero, a3, e8, m1, ta, ma
; ZVE32F-NEXT: vlse8.v v8, (a1), zero
; ZVE32F-NEXT: vle8.v v9, (a0)
; ZVE32F-NEXT: vdivu.vv v8, v8, v9
@@ -244,12 +244,12 @@ define void @gather_zero_stride_unfold(ptr noalias nocapture %A, ptr noalias noc
; NOT-OPTIMIZED: # %bb.0: # %entry
; NOT-OPTIMIZED-NEXT: li a2, 1024
; NOT-OPTIMIZED-NEXT: li a3, 32
+; NOT-OPTIMIZED-NEXT: vsetvli zero, a3, e8, m1, ta, ma
; NOT-OPTIMIZED-NEXT: .LBB4_1: # %vector.body
; NOT-OPTIMIZED-NEXT: # =>This Inner Loop Header: Depth=1
-; NOT-OPTIMIZED-NEXT: lbu a4, 0(a1)
-; NOT-OPTIMIZED-NEXT: vsetvli zero, a3, e8, m1, ta, ma
+; NOT-OPTIMIZED-NEXT: lbu a3, 0(a1)
; NOT-OPTIMIZED-NEXT: vle8.v v8, (a0)
-; NOT-OPTIMIZED-NEXT: vmv.v.x v9, a4
+; NOT-OPTIMIZED-NEXT: vmv.v.x v9, a3
; NOT-OPTIMIZED-NEXT: vdivu.vv v8, v9, v8
; NOT-OPTIMIZED-NEXT: vse8.v v8, (a0)
; NOT-OPTIMIZED-NEXT: addi a2, a2, -32
@@ -288,15 +288,15 @@ define void @scatter(ptr noalias nocapture %A, ptr noalias nocapture readonly %B
; CHECK-LABEL: scatter:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: li a2, 1024
-; CHECK-NEXT: li a3, 32
-; CHECK-NEXT: li a4, 5
+; CHECK-NEXT: li a4, 32
+; CHECK-NEXT: li a3, 5
+; CHECK-NEXT: vsetvli zero, a4, e8, m1, ta, ma
; CHECK-NEXT: .LBB5_1: # %vector.body
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
-; CHECK-NEXT: vsetvli zero, a3, e8, m1, ta, ma
; CHECK-NEXT: vle8.v v8, (a1)
-; CHECK-NEXT: vlse8.v v9, (a0), a4
+; CHECK-NEXT: vlse8.v v9, (a0), a3
; CHECK-NEXT: vadd.vv v8, v9, v8
-; CHECK-NEXT: vsse8.v v8, (a0), a4
+; CHECK-NEXT: vsse8.v v8, (a0), a3
; CHECK-NEXT: addi a2, a2, -32
; CHECK-NEXT: addi a1, a1, 32
; CHECK-NEXT: addi a0, a0, 160
@@ -821,20 +821,20 @@ define void @strided_load_startval_add_with_splat(ptr noalias nocapture %arg, pt
; CHECK-NEXT: add a6, a0, a2
; CHECK-NEXT: add a2, a1, a2
; CHECK-NEXT: add a2, a2, a7
-; CHECK-NEXT: li a7, 32
-; CHECK-NEXT: li t0, 5
-; CHECK-NEXT: mv t1, a5
+; CHECK-NEXT: li t0, 32
+; CHECK-NEXT: li a7, 5
+; CHECK-NEXT: vsetvli zero, t0, e8, m1, ta, ma
+; CHECK-NEXT: mv t0, a5
; CHECK-NEXT: .LBB13_3: # %bb15
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
-; CHECK-NEXT: vsetvli zero, a7, e8, m1, ta, ma
-; CHECK-NEXT: vlse8.v v8, (a2), t0
+; CHECK-NEXT: vlse8.v v8, (a2), a7
; CHECK-NEXT: vle8.v v9, (a6)
; CHECK-NEXT: vadd.vv v8, v9, v8
; CHECK-NEXT: vse8.v v8, (a6)
-; CHECK-NEXT: addi t1, t1, -32
+; CHECK-NEXT: addi t0, t0, -32
; CHECK-NEXT: addi a6, a6, 32
; CHECK-NEXT: addi a2, a2, 160
-; CHECK-NEXT: bnez t1, .LBB13_3
+; CHECK-NEXT: bnez t0, .LBB13_3
; CHECK-NEXT: # %bb.4: # %bb30
; CHECK-NEXT: beq a4, a5, .LBB13_7
; CHECK-NEXT: .LBB13_5: # %bb32
diff --git a/llvm/test/CodeGen/RISCV/rvv/sink-splat-operands.ll b/llvm/test/CodeGen/RISCV/rvv/sink-splat-operands.ll
index f08bfce409305c8..9b083fc286e7c02 100644
--- a/llvm/test/CodeGen/RISCV/rvv/sink-splat-operands.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/sink-splat-operands.ll
@@ -3892,9 +3892,9 @@ define void @sink_splat_mul_lmul8(ptr nocapture %a, i32 signext %x) {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: li a2, 1024
; CHECK-NEXT: li a3, 32
+; CHECK-NEXT: vsetvli zero, a3, e32, m8, ta, ma
; CHECK-NEXT: .LBB74_1: # %vector.body
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
-; CHECK-NEXT: vsetvli zero, a3, e32, m8, ta, ma
; CHECK-NEXT: vle32.v v8, (a0)
; CHECK-NEXT: vmul.vx v8, v8, a1
; CHECK-NEXT: vse32.v v8, (a0)
@@ -3927,9 +3927,9 @@ define void @sink_splat_add_lmul8(ptr nocapture %a, i32 signext %x) {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: li a2, 1024
; CHECK-NEXT: li a3, 32
+; CHECK-NEXT: vsetvli zero, a3, e32, m8, ta, ma
; CHECK-NEXT: .LBB75_1: # %vector.body
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
-; CHECK-NEXT: vsetvli zero, a3, e32, m8, ta, ma
; CHECK-NEXT: vle32.v v8, (a0)
; CHECK-NEXT: vadd.vx v8, v8, a1
; CHECK-NEXT: vse32.v v8, (a0)
@@ -3962,9 +3962,9 @@ define void @sink_splat_sub_lmul8(ptr nocapture %a, i32 signext %x) {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: li a2, 1024
; CHECK-NEXT: li a3, 32
+; CHECK-NEXT: vsetvli zero, a3, e32, m8, ta, ma
; CHECK-NEXT: .LBB76_1: # %vector.body
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
-; CHECK-NEXT: vsetvli zero, a3, e32, m8, ta, ma
; CHECK-NEXT: vle32.v v8, (a0)
; CHECK-NEXT: vsub.vx v8, v8, a1
; CHECK-NEXT: vse32.v v8, (a0)
@@ -3997,9 +3997,9 @@ define void @sink_splat_rsub_lmul8(ptr nocapture %a, i32 signext %x) {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: li a2, 1024
; CHECK-NEXT: li a3, 32
+; CHECK-NEXT: vsetvli zero, a3, e32, m8, ta, ma
; CHECK-NEXT: .LBB77_1: # %vector.body
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
-; CHECK-NEXT: vsetvli zero, a3, e32, m8, ta, ma
; CHECK-NEXT: vle32.v v8, (a0)
; CHECK-NEXT: vrsub.vx v8, v8, a1
; CHECK-NEXT: vse32.v v8, (a0)
@@ -4032,9 +4032,9 @@ define void @sink_splat_and_lmul8(ptr nocapture %a, i32 signext %x) {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: li a2, 1024
; CHECK-NEXT: li a3, 32
+; CHECK-NEXT: vsetvli zero, a3, e32, m8, ta, ma
; CHECK-NEXT: .LBB78_1: # %vector.body
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
-; CHECK-NEXT: vsetvli zero, a3, e32, m8, ta, ma
; CHECK-NEXT: vle32.v v8, (a0)
; CHECK-NEXT: vand.vx v8, v8, a1
; CHECK-NEXT: vse32.v v8, (a0)
@@ -4067,9 +4067,9 @@ define void @sink_splat_or_lmul8(ptr nocapture %a, i32 signext %x) {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: li a2, 1024
; CHECK-NEXT: li a3, 32
+; CHECK-NEXT: vsetvli zero, a3, e32, m8, ta, ma
; CHECK-NEXT: .LBB79_1: # %vector.body
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
-; CHECK-NEXT: vsetvli zero, a3, e32, m8, ta, ma
; CHECK-NEXT: vle32.v v8, (a0)
; CHECK-NEXT: vor.vx v8, v8, a1
; CHECK-NEXT: vse32.v v8, (a0)
@@ -4102,9 +4102,9 @@ define void @sink_splat_xor_lmul8(ptr nocapture %a, i32 signext %x) {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: li a2, 1024
; CHECK-NEXT: li a3, 32
+; CHECK-NEXT: vsetvli zero, a3, e32, m8, ta, ma
; CHECK-NEXT: .LBB80_1: # %vector.body
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
-; CHECK-NEXT: vsetvli zero, a3, e32, m8, ta, ma
; CHECK-NEXT: vle32.v v8, (a0)
; CHECK-NEXT: vxor.vx v8, v8, a1
; CHECK-NEXT: vse32.v v8, (a0)
More information about the llvm-commits
mailing list