[llvm] [RISCV] Allow larger offset when matching build_vector as vid sequence (PR #144756)
Philip Reames via llvm-commits
llvm-commits at lists.llvm.org
Wed Jun 18 10:11:12 PDT 2025
https://github.com/preames created https://github.com/llvm/llvm-project/pull/144756
I happened to notice that when legalizing get.active.lane.mask with large vectors we were materializing via constant pool instead of just shifting by a constant.
We should probably be doing a full cost comparison for the different lowering strategies as opposed to our current adhoc heuristics, but the few cases this regresses seem pretty minor. (Given the reduction in vset toggles, they might not be regressions at all.)
>From 3b916504e037fe27536855185ee9d63bdc6a84c4 Mon Sep 17 00:00:00 2001
From: Philip Reames <preames at rivosinc.com>
Date: Wed, 18 Jun 2025 07:35:51 -0700
Subject: [PATCH] [RISCV] Allow larger offset when matching build_vector as vid
sequence
I happened to notice that when legalizing get.active.lane.mask with
large vectors we were materializing via constant pool instead of
just shifting by a constant.
We should probably be doing a full cost comparison for the different
lowering strategies as opposed to our current adhoc heuristics,
but the few cases this regresses seem pretty minor. (Given the
reduction in vset toggles, they might not be regressions at all.)
---
llvm/lib/Target/RISCV/RISCVISelLowering.cpp | 10 +-
.../CodeGen/RISCV/rvv/active_lane_mask.ll | 130 ++++++++----------
.../rvv/fixed-vectors-fp-buildvec-bf16.ll | 16 ++-
.../RISCV/rvv/fixed-vectors-fp-buildvec.ll | 40 +++---
.../RISCV/rvv/fixed-vectors-int-buildvec.ll | 6 +-
.../rvv/fixed-vectors-reduction-int-vp.ll | 30 ++--
llvm/test/CodeGen/RISCV/rvv/vle_vid-vfcvt.ll | 17 ++-
7 files changed, 119 insertions(+), 130 deletions(-)
diff --git a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
index 33aae7ab16cca..d3d37b7954faa 100644
--- a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
+++ b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
@@ -3724,14 +3724,14 @@ static SDValue lowerBuildVectorViaVID(SDValue Op, SelectionDAG &DAG,
SplatStepVal = Log2_64(std::abs(StepNumerator));
}
- // Only emit VIDs with suitably-small steps/addends. We use imm5 is a
- // threshold since it's the immediate value many RVV instructions accept.
- // There is no vmul.vi instruction so ensure multiply constant can fit in
- // a single addi instruction.
+ // Only emit VIDs with suitably-small steps. We use imm5 is a threshold
+ // since it's the immediate value many RVV instructions accept. There is
+ // no vmul.vi instruction so ensure multiply constant can fit in a
+ // single addi instruction. For the addend, we allow up to 32 bits..
if (((StepOpcode == ISD::MUL && isInt<12>(SplatStepVal)) ||
(StepOpcode == ISD::SHL && isUInt<5>(SplatStepVal))) &&
isPowerOf2_32(StepDenominator) &&
- (SplatStepVal >= 0 || StepDenominator == 1) && isInt<5>(Addend)) {
+ (SplatStepVal >= 0 || StepDenominator == 1) && isInt<32>(Addend)) {
MVT VIDVT =
VT.isFloatingPoint() ? VT.changeVectorElementTypeToInteger() : VT;
MVT VIDContainerVT =
diff --git a/llvm/test/CodeGen/RISCV/rvv/active_lane_mask.ll b/llvm/test/CodeGen/RISCV/rvv/active_lane_mask.ll
index ec422a8fbb928..1acc830347de4 100644
--- a/llvm/test/CodeGen/RISCV/rvv/active_lane_mask.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/active_lane_mask.ll
@@ -103,18 +103,16 @@ define <8 x i1> @fv8(ptr %p, i64 %index, i64 %tc) {
define <32 x i1> @fv32(ptr %p, i64 %index, i64 %tc) {
; CHECK-LABEL: fv32:
; CHECK: # %bb.0:
-; CHECK-NEXT: lui a0, %hi(.LCPI8_0)
-; CHECK-NEXT: addi a0, a0, %lo(.LCPI8_0)
; CHECK-NEXT: vsetivli zero, 16, e64, m8, ta, ma
-; CHECK-NEXT: vle8.v v16, (a0)
; CHECK-NEXT: vid.v v8
+; CHECK-NEXT: li a0, 16
+; CHECK-NEXT: vadd.vx v16, v8, a0
; CHECK-NEXT: vsaddu.vx v8, v8, a1
+; CHECK-NEXT: vsaddu.vx v16, v16, a1
+; CHECK-NEXT: vmsltu.vx v24, v16, a2
; CHECK-NEXT: vmsltu.vx v0, v8, a2
-; CHECK-NEXT: vsext.vf8 v8, v16
-; CHECK-NEXT: vsaddu.vx v8, v8, a1
-; CHECK-NEXT: vmsltu.vx v16, v8, a2
; CHECK-NEXT: vsetivli zero, 4, e8, mf4, ta, ma
-; CHECK-NEXT: vslideup.vi v0, v16, 2
+; CHECK-NEXT: vslideup.vi v0, v24, 2
; CHECK-NEXT: ret
%mask = call <32 x i1> @llvm.get.active.lane.mask.v32i1.i64(i64 %index, i64 %tc)
ret <32 x i1> %mask
@@ -125,30 +123,24 @@ define <64 x i1> @fv64(ptr %p, i64 %index, i64 %tc) {
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 16, e64, m8, ta, ma
; CHECK-NEXT: vid.v v8
-; CHECK-NEXT: lui a0, %hi(.LCPI9_0)
-; CHECK-NEXT: addi a0, a0, %lo(.LCPI9_0)
-; CHECK-NEXT: vle8.v v16, (a0)
-; CHECK-NEXT: lui a0, %hi(.LCPI9_1)
-; CHECK-NEXT: addi a0, a0, %lo(.LCPI9_1)
-; CHECK-NEXT: vle8.v v17, (a0)
-; CHECK-NEXT: lui a0, %hi(.LCPI9_2)
-; CHECK-NEXT: addi a0, a0, %lo(.LCPI9_2)
-; CHECK-NEXT: vsaddu.vx v8, v8, a1
-; CHECK-NEXT: vle8.v v18, (a0)
-; CHECK-NEXT: vmsltu.vx v0, v8, a2
-; CHECK-NEXT: vsext.vf8 v8, v16
+; CHECK-NEXT: li a0, 16
+; CHECK-NEXT: vsaddu.vx v16, v8, a1
+; CHECK-NEXT: vmsltu.vx v0, v16, a2
+; CHECK-NEXT: vadd.vx v16, v8, a0
+; CHECK-NEXT: li a0, 32
+; CHECK-NEXT: vsaddu.vx v16, v16, a1
+; CHECK-NEXT: vmsltu.vx v24, v16, a2
+; CHECK-NEXT: vadd.vx v16, v8, a0
+; CHECK-NEXT: vsaddu.vx v16, v16, a1
+; CHECK-NEXT: vmsltu.vx v25, v16, a2
+; CHECK-NEXT: li a0, 48
+; CHECK-NEXT: vadd.vx v8, v8, a0
; CHECK-NEXT: vsaddu.vx v8, v8, a1
-; CHECK-NEXT: vmsltu.vx v16, v8, a2
-; CHECK-NEXT: vsext.vf8 v8, v17
-; CHECK-NEXT: vsaddu.vx v8, v8, a1
-; CHECK-NEXT: vmsltu.vx v17, v8, a2
; CHECK-NEXT: vsetivli zero, 4, e8, mf2, tu, ma
-; CHECK-NEXT: vslideup.vi v0, v16, 2
+; CHECK-NEXT: vslideup.vi v0, v24, 2
; CHECK-NEXT: vsetivli zero, 6, e8, mf2, tu, ma
-; CHECK-NEXT: vslideup.vi v0, v17, 4
+; CHECK-NEXT: vslideup.vi v0, v25, 4
; CHECK-NEXT: vsetivli zero, 16, e64, m8, ta, ma
-; CHECK-NEXT: vsext.vf8 v8, v18
-; CHECK-NEXT: vsaddu.vx v8, v8, a1
; CHECK-NEXT: vmsltu.vx v16, v8, a2
; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, ma
; CHECK-NEXT: vslideup.vi v0, v16, 6
@@ -160,63 +152,49 @@ define <64 x i1> @fv64(ptr %p, i64 %index, i64 %tc) {
define <128 x i1> @fv128(ptr %p, i64 %index, i64 %tc) {
; CHECK-LABEL: fv128:
; CHECK: # %bb.0:
-; CHECK-NEXT: lui a0, %hi(.LCPI10_0)
-; CHECK-NEXT: addi a0, a0, %lo(.LCPI10_0)
; CHECK-NEXT: vsetivli zero, 16, e64, m8, ta, ma
-; CHECK-NEXT: vle8.v v16, (a0)
-; CHECK-NEXT: lui a0, %hi(.LCPI10_1)
-; CHECK-NEXT: addi a0, a0, %lo(.LCPI10_1)
-; CHECK-NEXT: vle8.v v17, (a0)
-; CHECK-NEXT: lui a0, %hi(.LCPI10_2)
-; CHECK-NEXT: addi a0, a0, %lo(.LCPI10_2)
-; CHECK-NEXT: vle8.v v18, (a0)
-; CHECK-NEXT: lui a0, %hi(.LCPI10_3)
-; CHECK-NEXT: addi a0, a0, %lo(.LCPI10_3)
; CHECK-NEXT: vid.v v8
-; CHECK-NEXT: vle8.v v19, (a0)
-; CHECK-NEXT: lui a0, %hi(.LCPI10_4)
-; CHECK-NEXT: addi a0, a0, %lo(.LCPI10_4)
-; CHECK-NEXT: vle8.v v20, (a0)
-; CHECK-NEXT: lui a0, %hi(.LCPI10_5)
-; CHECK-NEXT: addi a0, a0, %lo(.LCPI10_5)
-; CHECK-NEXT: vle8.v v21, (a0)
-; CHECK-NEXT: lui a0, %hi(.LCPI10_6)
-; CHECK-NEXT: addi a0, a0, %lo(.LCPI10_6)
-; CHECK-NEXT: vsaddu.vx v8, v8, a1
-; CHECK-NEXT: vle8.v v22, (a0)
-; CHECK-NEXT: vmsltu.vx v0, v8, a2
-; CHECK-NEXT: vsext.vf8 v8, v16
+; CHECK-NEXT: li a0, 80
+; CHECK-NEXT: vsaddu.vx v16, v8, a1
+; CHECK-NEXT: vmsltu.vx v0, v16, a2
+; CHECK-NEXT: vadd.vx v16, v8, a0
+; CHECK-NEXT: li a0, 64
+; CHECK-NEXT: vsaddu.vx v16, v16, a1
+; CHECK-NEXT: vmsltu.vx v24, v16, a2
+; CHECK-NEXT: vadd.vx v16, v8, a0
+; CHECK-NEXT: li a0, 96
+; CHECK-NEXT: vsaddu.vx v16, v16, a1
+; CHECK-NEXT: vmsltu.vx v25, v16, a2
+; CHECK-NEXT: vadd.vx v16, v8, a0
+; CHECK-NEXT: li a0, 112
+; CHECK-NEXT: vsaddu.vx v16, v16, a1
+; CHECK-NEXT: vmsltu.vx v26, v16, a2
+; CHECK-NEXT: vadd.vx v16, v8, a0
+; CHECK-NEXT: li a0, 16
+; CHECK-NEXT: vsaddu.vx v16, v16, a1
+; CHECK-NEXT: vmsltu.vx v27, v16, a2
+; CHECK-NEXT: vadd.vx v16, v8, a0
+; CHECK-NEXT: li a0, 32
+; CHECK-NEXT: vsaddu.vx v16, v16, a1
+; CHECK-NEXT: vmsltu.vx v28, v16, a2
+; CHECK-NEXT: vadd.vx v16, v8, a0
+; CHECK-NEXT: vsaddu.vx v16, v16, a1
+; CHECK-NEXT: vmsltu.vx v29, v16, a2
+; CHECK-NEXT: li a0, 48
+; CHECK-NEXT: vadd.vx v8, v8, a0
; CHECK-NEXT: vsaddu.vx v8, v8, a1
; CHECK-NEXT: vmsltu.vx v16, v8, a2
-; CHECK-NEXT: vsext.vf8 v8, v17
-; CHECK-NEXT: vsaddu.vx v8, v8, a1
-; CHECK-NEXT: vmsltu.vx v17, v8, a2
-; CHECK-NEXT: vsext.vf8 v8, v18
-; CHECK-NEXT: vsaddu.vx v8, v8, a1
-; CHECK-NEXT: vmsltu.vx v18, v8, a2
-; CHECK-NEXT: vsext.vf8 v8, v19
-; CHECK-NEXT: vsaddu.vx v8, v8, a1
-; CHECK-NEXT: vmsltu.vx v19, v8, a2
-; CHECK-NEXT: vsext.vf8 v8, v20
-; CHECK-NEXT: vsaddu.vx v8, v8, a1
-; CHECK-NEXT: vmsltu.vx v20, v8, a2
-; CHECK-NEXT: vsext.vf8 v8, v21
-; CHECK-NEXT: vsaddu.vx v8, v8, a1
-; CHECK-NEXT: vmsltu.vx v21, v8, a2
-; CHECK-NEXT: vsext.vf8 v8, v22
-; CHECK-NEXT: vsaddu.vx v8, v8, a1
-; CHECK-NEXT: vmsltu.vx v22, v8, a2
; CHECK-NEXT: vsetivli zero, 4, e8, mf2, tu, ma
-; CHECK-NEXT: vslideup.vi v17, v16, 2
-; CHECK-NEXT: vslideup.vi v0, v20, 2
+; CHECK-NEXT: vslideup.vi v25, v24, 2
+; CHECK-NEXT: vslideup.vi v0, v28, 2
; CHECK-NEXT: vsetivli zero, 6, e8, mf2, tu, ma
-; CHECK-NEXT: vslideup.vi v17, v18, 4
-; CHECK-NEXT: vslideup.vi v0, v21, 4
+; CHECK-NEXT: vslideup.vi v25, v26, 4
+; CHECK-NEXT: vslideup.vi v0, v29, 4
; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, ma
-; CHECK-NEXT: vslideup.vi v17, v19, 6
-; CHECK-NEXT: vslideup.vi v0, v22, 6
+; CHECK-NEXT: vslideup.vi v25, v27, 6
+; CHECK-NEXT: vslideup.vi v0, v16, 6
; CHECK-NEXT: vsetivli zero, 16, e8, m1, ta, ma
-; CHECK-NEXT: vslideup.vi v0, v17, 8
+; CHECK-NEXT: vslideup.vi v0, v25, 8
; CHECK-NEXT: ret
%mask = call <128 x i1> @llvm.get.active.lane.mask.v128i1.i64(i64 %index, i64 %tc)
ret <128 x i1> %mask
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp-buildvec-bf16.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp-buildvec-bf16.ll
index 3f7cd91737f4b..9bb3f4a976ab0 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp-buildvec-bf16.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp-buildvec-bf16.ll
@@ -94,10 +94,12 @@ define <2 x bfloat> @vid_v2bf16() {
define <2 x bfloat> @vid_addend1_v2bf16() {
; CHECK-LABEL: vid_addend1_v2bf16:
; CHECK: # %bb.0:
-; CHECK-NEXT: lui a0, 262148
+; CHECK-NEXT: vsetivli zero, 2, e16, mf4, ta, ma
+; CHECK-NEXT: vid.v v8
+; CHECK-NEXT: lui a0, 4
+; CHECK-NEXT: vsll.vi v8, v8, 7
; CHECK-NEXT: addi a0, a0, -128
-; CHECK-NEXT: vsetivli zero, 2, e32, m1, ta, ma
-; CHECK-NEXT: vmv.s.x v8, a0
+; CHECK-NEXT: vadd.vx v8, v8, a0
; CHECK-NEXT: ret
ret <2 x bfloat> <bfloat 1.0, bfloat 2.0>
}
@@ -105,10 +107,12 @@ define <2 x bfloat> @vid_addend1_v2bf16() {
define <2 x bfloat> @vid_denominator2_v2bf16() {
; CHECK-LABEL: vid_denominator2_v2bf16:
; CHECK: # %bb.0:
-; CHECK-NEXT: lui a0, 260100
+; CHECK-NEXT: vsetivli zero, 2, e16, mf4, ta, ma
+; CHECK-NEXT: vid.v v8
+; CHECK-NEXT: lui a0, 4
+; CHECK-NEXT: vsll.vi v8, v8, 7
; CHECK-NEXT: addi a0, a0, -256
-; CHECK-NEXT: vsetivli zero, 2, e32, m1, ta, ma
-; CHECK-NEXT: vmv.s.x v8, a0
+; CHECK-NEXT: vadd.vx v8, v8, a0
; CHECK-NEXT: ret
ret <2 x bfloat> <bfloat 0.5, bfloat 1.0>
}
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp-buildvec.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp-buildvec.ll
index eb40c133514fe..564e95c43f68a 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp-buildvec.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp-buildvec.ll
@@ -1573,18 +1573,22 @@ define <2 x half> @vid_addend1_v2f16() {
;
; RV32ZVFHMIN-LABEL: vid_addend1_v2f16:
; RV32ZVFHMIN: # %bb.0:
-; RV32ZVFHMIN-NEXT: lui a0, 262148
-; RV32ZVFHMIN-NEXT: addi a0, a0, -1024
-; RV32ZVFHMIN-NEXT: vsetivli zero, 2, e32, m1, ta, ma
-; RV32ZVFHMIN-NEXT: vmv.s.x v8, a0
+; RV32ZVFHMIN-NEXT: vsetivli zero, 2, e16, mf4, ta, ma
+; RV32ZVFHMIN-NEXT: vid.v v8
+; RV32ZVFHMIN-NEXT: li a0, 15
+; RV32ZVFHMIN-NEXT: vsll.vi v8, v8, 10
+; RV32ZVFHMIN-NEXT: slli a0, a0, 10
+; RV32ZVFHMIN-NEXT: vadd.vx v8, v8, a0
; RV32ZVFHMIN-NEXT: ret
;
; RV64ZVFHMIN-LABEL: vid_addend1_v2f16:
; RV64ZVFHMIN: # %bb.0:
-; RV64ZVFHMIN-NEXT: lui a0, 262148
-; RV64ZVFHMIN-NEXT: addi a0, a0, -1024
-; RV64ZVFHMIN-NEXT: vsetivli zero, 2, e32, m1, ta, ma
-; RV64ZVFHMIN-NEXT: vmv.s.x v8, a0
+; RV64ZVFHMIN-NEXT: vsetivli zero, 2, e16, mf4, ta, ma
+; RV64ZVFHMIN-NEXT: vid.v v8
+; RV64ZVFHMIN-NEXT: li a0, 15
+; RV64ZVFHMIN-NEXT: vsll.vi v8, v8, 10
+; RV64ZVFHMIN-NEXT: slli a0, a0, 10
+; RV64ZVFHMIN-NEXT: vadd.vx v8, v8, a0
; RV64ZVFHMIN-NEXT: ret
ret <2 x half> <half 1.0, half 2.0>
}
@@ -1608,18 +1612,22 @@ define <2 x half> @vid_denominator2_v2f16() {
;
; RV32ZVFHMIN-LABEL: vid_denominator2_v2f16:
; RV32ZVFHMIN: # %bb.0:
-; RV32ZVFHMIN-NEXT: lui a0, 245764
-; RV32ZVFHMIN-NEXT: addi a0, a0, -2048
-; RV32ZVFHMIN-NEXT: vsetivli zero, 2, e32, m1, ta, ma
-; RV32ZVFHMIN-NEXT: vmv.s.x v8, a0
+; RV32ZVFHMIN-NEXT: vsetivli zero, 2, e16, mf4, ta, ma
+; RV32ZVFHMIN-NEXT: vid.v v8
+; RV32ZVFHMIN-NEXT: li a0, 7
+; RV32ZVFHMIN-NEXT: vsll.vi v8, v8, 10
+; RV32ZVFHMIN-NEXT: slli a0, a0, 11
+; RV32ZVFHMIN-NEXT: vadd.vx v8, v8, a0
; RV32ZVFHMIN-NEXT: ret
;
; RV64ZVFHMIN-LABEL: vid_denominator2_v2f16:
; RV64ZVFHMIN: # %bb.0:
-; RV64ZVFHMIN-NEXT: lui a0, 245764
-; RV64ZVFHMIN-NEXT: addi a0, a0, -2048
-; RV64ZVFHMIN-NEXT: vsetivli zero, 2, e32, m1, ta, ma
-; RV64ZVFHMIN-NEXT: vmv.s.x v8, a0
+; RV64ZVFHMIN-NEXT: vsetivli zero, 2, e16, mf4, ta, ma
+; RV64ZVFHMIN-NEXT: vid.v v8
+; RV64ZVFHMIN-NEXT: li a0, 7
+; RV64ZVFHMIN-NEXT: vsll.vi v8, v8, 10
+; RV64ZVFHMIN-NEXT: slli a0, a0, 11
+; RV64ZVFHMIN-NEXT: vadd.vx v8, v8, a0
; RV64ZVFHMIN-NEXT: ret
ret <2 x half> <half 0.5, half 1.0>
}
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-buildvec.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-buildvec.ll
index 1fa96d3c07ca9..f235540cc8ffb 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-buildvec.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-buildvec.ll
@@ -58,10 +58,10 @@ define void @buildvec_vid_plus_imm_v16i8(ptr %x) {
define void @buildvec_vid_plus_nonimm_v16i8(ptr %x) {
; CHECK-LABEL: buildvec_vid_plus_nonimm_v16i8:
; CHECK: # %bb.0:
-; CHECK-NEXT: lui a1, %hi(.LCPI4_0)
-; CHECK-NEXT: addi a1, a1, %lo(.LCPI4_0)
; CHECK-NEXT: vsetivli zero, 16, e8, m1, ta, ma
-; CHECK-NEXT: vle8.v v8, (a1)
+; CHECK-NEXT: vid.v v8
+; CHECK-NEXT: li a1, 100
+; CHECK-NEXT: vadd.vx v8, v8, a1
; CHECK-NEXT: vse8.v v8, (a0)
; CHECK-NEXT: ret
store <16 x i8> <i8 100, i8 101, i8 102, i8 103, i8 104, i8 105, i8 106, i8 107, i8 108, i8 109, i8 110, i8 111, i8 112, i8 113, i8 114, i8 115>, ptr %x
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-reduction-int-vp.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-reduction-int-vp.ll
index 722a1186facab..dfe8f358b7782 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-reduction-int-vp.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-reduction-int-vp.ll
@@ -1734,19 +1734,16 @@ define signext i8 @vpreduce_mul_v64i8(i8 signext %s, <64 x i8> %v, <64 x i1> %m,
; RV32-NEXT: .cfi_offset ra, -4
; RV32-NEXT: mv a2, a0
; RV32-NEXT: li a0, 32
-; RV32-NEXT: lui a3, %hi(.LCPI72_0)
-; RV32-NEXT: addi a3, a3, %lo(.LCPI72_0)
; RV32-NEXT: vsetvli zero, a0, e32, m8, ta, ma
-; RV32-NEXT: vle8.v v12, (a3)
; RV32-NEXT: vid.v v16
-; RV32-NEXT: vmsltu.vx v14, v16, a1
-; RV32-NEXT: li a3, 64
-; RV32-NEXT: vsext.vf4 v16, v12
; RV32-NEXT: vmsltu.vx v12, v16, a1
+; RV32-NEXT: vadd.vx v16, v16, a0
+; RV32-NEXT: vmsltu.vx v13, v16, a1
+; RV32-NEXT: li a1, 64
; RV32-NEXT: vsetivli zero, 8, e8, mf2, ta, ma
-; RV32-NEXT: vslideup.vi v14, v12, 4
-; RV32-NEXT: vsetvli zero, a3, e8, m4, ta, ma
-; RV32-NEXT: vmand.mm v0, v14, v0
+; RV32-NEXT: vslideup.vi v12, v13, 4
+; RV32-NEXT: vsetvli zero, a1, e8, m4, ta, ma
+; RV32-NEXT: vmand.mm v0, v12, v0
; RV32-NEXT: vmv.v.i v12, 1
; RV32-NEXT: vmerge.vvm v8, v12, v8, v0
; RV32-NEXT: vslidedown.vx v12, v8, a0
@@ -1780,19 +1777,16 @@ define signext i8 @vpreduce_mul_v64i8(i8 signext %s, <64 x i8> %v, <64 x i1> %m,
; RV64-NEXT: .cfi_offset ra, -8
; RV64-NEXT: mv a2, a0
; RV64-NEXT: li a0, 32
-; RV64-NEXT: lui a3, %hi(.LCPI72_0)
-; RV64-NEXT: addi a3, a3, %lo(.LCPI72_0)
; RV64-NEXT: vsetvli zero, a0, e32, m8, ta, ma
-; RV64-NEXT: vle8.v v12, (a3)
; RV64-NEXT: vid.v v16
-; RV64-NEXT: vmsltu.vx v14, v16, a1
-; RV64-NEXT: li a3, 64
-; RV64-NEXT: vsext.vf4 v16, v12
; RV64-NEXT: vmsltu.vx v12, v16, a1
+; RV64-NEXT: vadd.vx v16, v16, a0
+; RV64-NEXT: vmsltu.vx v13, v16, a1
+; RV64-NEXT: li a1, 64
; RV64-NEXT: vsetivli zero, 8, e8, mf2, ta, ma
-; RV64-NEXT: vslideup.vi v14, v12, 4
-; RV64-NEXT: vsetvli zero, a3, e8, m4, ta, ma
-; RV64-NEXT: vmand.mm v0, v14, v0
+; RV64-NEXT: vslideup.vi v12, v13, 4
+; RV64-NEXT: vsetvli zero, a1, e8, m4, ta, ma
+; RV64-NEXT: vmand.mm v0, v12, v0
; RV64-NEXT: vmv.v.i v12, 1
; RV64-NEXT: vmerge.vvm v8, v12, v8, v0
; RV64-NEXT: vslidedown.vx v12, v8, a0
diff --git a/llvm/test/CodeGen/RISCV/rvv/vle_vid-vfcvt.ll b/llvm/test/CodeGen/RISCV/rvv/vle_vid-vfcvt.ll
index bf330ea38a007..c837063231e3e 100644
--- a/llvm/test/CodeGen/RISCV/rvv/vle_vid-vfcvt.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/vle_vid-vfcvt.ll
@@ -4,10 +4,12 @@
define void @foo_1(ptr nocapture noundef writeonly %t) {
; CHECK-LABEL: foo_1:
; CHECK: # %bb.0: # %entry
-; CHECK-NEXT: lui a1, %hi(.LCPI0_0)
-; CHECK-NEXT: addi a1, a1, %lo(.LCPI0_0)
; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, ma
-; CHECK-NEXT: vle32.v v8, (a1)
+; CHECK-NEXT: vid.v v8
+; CHECK-NEXT: vsll.vi v8, v8, 7
+; CHECK-NEXT: lui a1, 524288
+; CHECK-NEXT: vadd.vx v8, v8, a1
+; CHECK-NEXT: vfcvt.f.x.v v8, v8
; CHECK-NEXT: vse32.v v8, (a0)
; CHECK-NEXT: ret
entry:
@@ -18,10 +20,13 @@ entry:
define void @foo_2(ptr nocapture noundef writeonly %t) {
; CHECK-LABEL: foo_2:
; CHECK: # %bb.0: # %entry
-; CHECK-NEXT: lui a1, %hi(.LCPI1_0)
-; CHECK-NEXT: addi a1, a1, %lo(.LCPI1_0)
; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, ma
-; CHECK-NEXT: vle32.v v8, (a1)
+; CHECK-NEXT: vid.v v8
+; CHECK-NEXT: lui a1, 524288
+; CHECK-NEXT: vsll.vi v8, v8, 7
+; CHECK-NEXT: addi a1, a1, -512
+; CHECK-NEXT: vadd.vx v8, v8, a1
+; CHECK-NEXT: vfcvt.f.x.v v8, v8
; CHECK-NEXT: vse32.v v8, (a0)
; CHECK-NEXT: ret
entry:
More information about the llvm-commits
mailing list