shylie/llvm-project
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
llvm-project/llvm/test/Transforms/LoopVectorize/RISCV/reg-usage.ll
Luke Lau 7074471593
[RISCV] Enable tail folding by default (#151681) 
We have been tracking the performance of EVL tail folding in the loop
vectorizer on RISC-V for a while now, and after much hard work from
various contributors we think it should be generally profitable to
enable by default now.

With tail folding there is a 21% improvement on 525.x264_r on SPEC CPU
2017 on the BPI-F3 (-march=rva22u64_v -O3 -flto), as well as a 30%
geomean codesize reduction on SPEC and TSVC, with no significant
regressions detected.

Now that we are early into the LLVM 22.x development cycle it seems like
a good time to enable it to catch any issues. There are still more EVL
related items of work being tracked in #123069, which should continue to
improve performance.
2025-08-08 14:26:23 +08:00

119 lines
6.1 KiB
LLVM
Raw Permalink Blame History

; REQUIRES: asserts
; RUN: opt -passes=loop-vectorize -mtriple riscv64-linux-gnu \
; RUN: -mattr=+v,+d -debug-only=loop-vectorize,vplan --disable-output \
; RUN: -force-vector-width=1 -prefer-predicate-over-epilogue=scalar-epilogue \
; RUN: -S < %s 2>&1 | FileCheck %s --check-prefix=CHECK-SCALAR
; RUN: opt -passes=loop-vectorize -mtriple riscv64-linux-gnu \
; RUN: -mattr=+v,+d -debug-only=loop-vectorize,vplan --disable-output \
; RUN: -riscv-v-register-bit-width-lmul=1 -prefer-predicate-over-epilogue=scalar-epilogue \
; RUN: -S < %s 2>&1 | FileCheck %s --check-prefix=CHECK-LMUL1
; RUN: opt -passes=loop-vectorize -mtriple riscv64-linux-gnu \
; RUN: -mattr=+v,+d -debug-only=loop-vectorize,vplan --disable-output \
; RUN: -riscv-v-register-bit-width-lmul=2 -prefer-predicate-over-epilogue=scalar-epilogue \
; RUN: -S < %s 2>&1 | FileCheck %s --check-prefix=CHECK-LMUL2
; RUN: opt -passes=loop-vectorize -mtriple riscv64-linux-gnu \
; RUN: -mattr=+v,+d -debug-only=loop-vectorize,vplan --disable-output \
; RUN: -riscv-v-register-bit-width-lmul=4 -prefer-predicate-over-epilogue=scalar-epilogue \
; RUN: -S < %s 2>&1 | FileCheck %s --check-prefix=CHECK-LMUL4
; RUN: opt -passes=loop-vectorize -mtriple riscv64-linux-gnu \
; RUN: -mattr=+v,+d -debug-only=loop-vectorize,vplan --disable-output \
; RUN: -riscv-v-register-bit-width-lmul=8 -prefer-predicate-over-epilogue=scalar-epilogue \
; RUN: -S < %s 2>&1 | FileCheck %s --check-prefix=CHECK-LMUL8
; TODO: -prefer-predicate-over-epilogue=scalar-epilogue was added to allow
; unrolling. Calculate register pressure for all VPlans, not just unrolled ones,
; and remove.
define void @add(ptr noalias nocapture readonly %src1, ptr noalias nocapture readonly %src2, i32 signext %size, ptr noalias nocapture writeonly %result) {
; CHECK-LABEL: add
; CHECK-SCALAR: LV(REG): VF = 1
; CHECK-SCALAR-NEXT: LV(REG): Found max usage: 2 item
; CHECK-SCALAR-NEXT: LV(REG): RegisterClass: RISCV::GPRRC, 3 registers
; CHECK-SCALAR-NEXT: LV(REG): RegisterClass: RISCV::FPRRC, 2 registers
; CHECK-SCALAR-NEXT: LV(REG): Found invariant usage: 1 item
; CHECK-SCALAR-NEXT: LV(REG): RegisterClass: RISCV::GPRRC, 1 registers
; CHECK-LMUL1: LV(REG): Found max usage: 2 item
; CHECK-LMUL1-NEXT: LV(REG): RegisterClass: RISCV::GPRRC, 3 registers
; CHECK-LMUL1-NEXT: LV(REG): RegisterClass: RISCV::VRRC, 2 registers
; CHECK-LMUL1-NEXT: LV(REG): Found invariant usage: 1 item
; CHECK-LMUL1-NEXT: LV(REG): RegisterClass: RISCV::GPRRC, 1 registers
; CHECK-LMUL2: LV(REG): Found max usage: 2 item
; CHECK-LMUL2-NEXT: LV(REG): RegisterClass: RISCV::GPRRC, 3 registers
; CHECK-LMUL2-NEXT: LV(REG): RegisterClass: RISCV::VRRC, 4 registers
; CHECK-LMUL2-NEXT: LV(REG): Found invariant usage: 1 item
; CHECK-LMUL2-NEXT: LV(REG): RegisterClass: RISCV::GPRRC, 1 registers
; CHECK-LMUL4: LV(REG): Found max usage: 2 item
; CHECK-LMUL4-NEXT: LV(REG): RegisterClass: RISCV::GPRRC, 3 registers
; CHECK-LMUL4-NEXT: LV(REG): RegisterClass: RISCV::VRRC, 8 registers
; CHECK-LMUL4-NEXT: LV(REG): Found invariant usage: 1 item
; CHECK-LMUL4-NEXT: LV(REG): RegisterClass: RISCV::GPRRC, 1 registers
; CHECK-LMUL8: LV(REG): Found max usage: 2 item
; CHECK-LMUL8-NEXT: LV(REG): RegisterClass: RISCV::GPRRC, 3 registers
; CHECK-LMUL8-NEXT: LV(REG): RegisterClass: RISCV::VRRC, 16 registers
; CHECK-LMUL8-NEXT: LV(REG): Found invariant usage: 1 item
; CHECK-LMUL8-NEXT: LV(REG): RegisterClass: RISCV::GPRRC, 1 registers
entry:
%conv = zext i32 %size to i64
%cmp10.not = icmp eq i32 %size, 0
br i1 %cmp10.not, label %for.cond.cleanup, label %for.body
for.cond.cleanup:
ret void
for.body:
%i.011 = phi i64 [ %add4, %for.body ], [ 0, %entry ]
%arrayidx = getelementptr inbounds float, ptr %src1, i64 %i.011
%0 = load float, ptr %arrayidx, align 4
%arrayidx2 = getelementptr inbounds float, ptr %src2, i64 %i.011
%1 = load float, ptr %arrayidx2, align 4
%add = fadd float %0, %1
%arrayidx3 = getelementptr inbounds float, ptr %result, i64 %i.011
store float %add, ptr %arrayidx3, align 4
%add4 = add nuw nsw i64 %i.011, 1
%exitcond.not = icmp eq i64 %add4, %conv
br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
}
define void @goo(ptr nocapture noundef %a, i32 noundef signext %n) {
; CHECK-LABEL: goo
; CHECK-SCALAR: LV(REG): VF = 1
; CHECK-SCALAR-NEXT: LV(REG): Found max usage: 1 item
; CHECK-SCALAR-NEXT: LV(REG): RegisterClass: RISCV::GPRRC, 3 registers
; CHECK-LMUL1: LV(REG): Found max usage: 2 item
; CHECK-LMUL1-NEXT: LV(REG): RegisterClass: RISCV::GPRRC, 2 registers
; CHECK-LMUL1-NEXT: LV(REG): RegisterClass: RISCV::VRRC, 1 registers
; CHECK-LMUL2: LV(REG): Found max usage: 2 item
; CHECK-LMUL2-NEXT: LV(REG): RegisterClass: RISCV::GPRRC, 2 registers
; CHECK-LMUL2-NEXT: LV(REG): RegisterClass: RISCV::VRRC, 2 registers
; CHECK-LMUL4: LV(REG): Found max usage: 2 item
; CHECK-LMUL4-NEXT: LV(REG): RegisterClass: RISCV::GPRRC, 2 registers
; CHECK-LMUL4-NEXT: LV(REG): RegisterClass: RISCV::VRRC, 4 registers
; CHECK-LMUL8: LV(REG): Found max usage: 2 item
; CHECK-LMUL8-NEXT: LV(REG): RegisterClass: RISCV::GPRRC, 2 registers
; CHECK-LMUL8-NEXT: LV(REG): RegisterClass: RISCV::VRRC, 8 registers
entry:
%cmp3 = icmp sgt i32 %n, 0
br i1 %cmp3, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader: ; preds = %entry
%wide.trip.count = zext i32 %n to i64
br label %for.body
for.cond.cleanup.loopexit: ; preds = %for.body
br label %for.cond.cleanup
for.cond.cleanup: ; preds = %for.cond.cleanup.loopexit, %entry
ret void
for.body: ; preds = %for.body.preheader, %for.body
%indvars.iv = phi i64 [ 0, %for.body.preheader ], [ %indvars.iv.next, %for.body ]
%arrayidx = getelementptr inbounds ptr, ptr %a, i64 %indvars.iv
%0 = load ptr, ptr %arrayidx, align 8
%add.ptr = getelementptr inbounds i32, ptr %0, i64 1
store ptr %add.ptr, ptr %arrayidx, align 8
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond.not = icmp eq i64 %indvars.iv.next, %wide.trip.count
br i1 %exitcond.not, label %for.cond.cleanup.loopexit, label %for.body
}
Reference in New Issue View Git Blame Copy Permalink