[llvm] [GISel][RISCV] Anyextend before copying f16 -> i32/i64 (PR #94993)
Yingwei Zheng via llvm-commits
llvm-commits at lists.llvm.org
Mon Jun 10 08:09:19 PDT 2024
https://github.com/dtcxzyw updated https://github.com/llvm/llvm-project/pull/94993
>From 67373a6643e9b248ffd29da9c36a1e8a3f5b1860 Mon Sep 17 00:00:00 2001
From: Yingwei Zheng <dtcxzyw2333 at gmail.com>
Date: Mon, 10 Jun 2024 22:54:18 +0800
Subject: [PATCH 1/2] [GISel][RISCV] Anyextend before copying f16 -> i32/i64
---
.../Target/RISCV/GISel/RISCVCallLowering.cpp | 13 +-
.../irtranslator/calling-conv-half.ll | 558 +++++++++++++++++-
2 files changed, 564 insertions(+), 7 deletions(-)
diff --git a/llvm/lib/Target/RISCV/GISel/RISCVCallLowering.cpp b/llvm/lib/Target/RISCV/GISel/RISCVCallLowering.cpp
index beee9405de02a..b9bcfd8fb79a6 100644
--- a/llvm/lib/Target/RISCV/GISel/RISCVCallLowering.cpp
+++ b/llvm/lib/Target/RISCV/GISel/RISCVCallLowering.cpp
@@ -102,9 +102,16 @@ struct RISCVOutgoingValueHandler : public CallLowering::OutgoingValueHandler {
void assignValueToReg(Register ValVReg, Register PhysReg,
const CCValAssign &VA) override {
- // If we're passing an f32 value into an i64, anyextend before copying.
- if (VA.getLocVT() == MVT::i64 && VA.getValVT() == MVT::f32)
- ValVReg = MIRBuilder.buildAnyExt(LLT::scalar(64), ValVReg).getReg(0);
+ // If we're passing a smaller fp value into a larger integer register,
+ // anyextend before copying.
+ if ((VA.getLocVT() == MVT::i64 && VA.getValVT() == MVT::f32) ||
+ ((VA.getLocVT() == MVT::i32 || VA.getLocVT() == MVT::i64) &&
+ VA.getValVT() == MVT::f16))
+ ValVReg =
+ MIRBuilder
+ .buildAnyExt(LLT::scalar(VA.getLocVT().getScalarSizeInBits()),
+ ValVReg)
+ .getReg(0);
Register ExtReg = extendRegister(ValVReg, VA);
MIRBuilder.buildCopy(PhysReg, ExtReg);
diff --git a/llvm/test/CodeGen/RISCV/GlobalISel/irtranslator/calling-conv-half.ll b/llvm/test/CodeGen/RISCV/GlobalISel/irtranslator/calling-conv-half.ll
index 0a0828e51893f..04fa62b195076 100644
--- a/llvm/test/CodeGen/RISCV/GlobalISel/irtranslator/calling-conv-half.ll
+++ b/llvm/test/CodeGen/RISCV/GlobalISel/irtranslator/calling-conv-half.ll
@@ -1,10 +1,16 @@
; NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
-; RUN: llc -mtriple=riscv32 -global-isel -stop-after=irtranslator < %s \
+; RUN: llc -mtriple=riscv32 -global-isel -stop-after=irtranslator -verify-machineinstrs < %s \
; RUN: | FileCheck -check-prefix=RV32I %s
-; RUN: llc -mtriple=riscv32 -mattr=+f -global-isel -stop-after=irtranslator < %s \
+; RUN: llc -mtriple=riscv32 -mattr=+f -global-isel -stop-after=irtranslator -verify-machineinstrs < %s \
; RUN: | FileCheck -check-prefix=RV32IF %s
-; RUN: llc -mtriple=riscv32 -mattr=+zfh -global-isel -stop-after=irtranslator < %s \
+; RUN: llc -mtriple=riscv32 -mattr=+zfh -global-isel -stop-after=irtranslator -verify-machineinstrs < %s \
; RUN: | FileCheck -check-prefix=RV32IZFH %s
+; RUN: llc -mtriple=riscv64 -global-isel -stop-after=irtranslator -verify-machineinstrs < %s \
+; RUN: | FileCheck -check-prefix=RV64I %s
+; RUN: llc -mtriple=riscv64 -mattr=+f -global-isel -stop-after=irtranslator -verify-machineinstrs < %s \
+; RUN: | FileCheck -check-prefix=RV64IF %s
+; RUN: llc -mtriple=riscv64 -mattr=+zfh -global-isel -stop-after=irtranslator -verify-machineinstrs < %s \
+; RUN: | FileCheck -check-prefix=RV64IZFH %s
define half @callee_half_in_regs(half %x) nounwind {
; RV32I-LABEL: name: callee_half_in_regs
@@ -34,6 +40,34 @@ define half @callee_half_in_regs(half %x) nounwind {
; RV32IZFH-NEXT: [[COPY:%[0-9]+]]:_(s16) = COPY $f10_h
; RV32IZFH-NEXT: $f10_h = COPY [[COPY]](s16)
; RV32IZFH-NEXT: PseudoRET implicit $f10_h
+ ;
+ ; RV64I-LABEL: name: callee_half_in_regs
+ ; RV64I: bb.1 (%ir-block.0):
+ ; RV64I-NEXT: liveins: $x10
+ ; RV64I-NEXT: {{ $}}
+ ; RV64I-NEXT: [[COPY:%[0-9]+]]:_(s64) = COPY $x10
+ ; RV64I-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s64)
+ ; RV64I-NEXT: [[ANYEXT:%[0-9]+]]:_(s64) = G_ANYEXT [[TRUNC]](s16)
+ ; RV64I-NEXT: $x10 = COPY [[ANYEXT]](s64)
+ ; RV64I-NEXT: PseudoRET implicit $x10
+ ;
+ ; RV64IF-LABEL: name: callee_half_in_regs
+ ; RV64IF: bb.1 (%ir-block.0):
+ ; RV64IF-NEXT: liveins: $f10_f
+ ; RV64IF-NEXT: {{ $}}
+ ; RV64IF-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $f10_f
+ ; RV64IF-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
+ ; RV64IF-NEXT: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC]](s16)
+ ; RV64IF-NEXT: $f10_f = COPY [[ANYEXT]](s32)
+ ; RV64IF-NEXT: PseudoRET implicit $f10_f
+ ;
+ ; RV64IZFH-LABEL: name: callee_half_in_regs
+ ; RV64IZFH: bb.1 (%ir-block.0):
+ ; RV64IZFH-NEXT: liveins: $f10_h
+ ; RV64IZFH-NEXT: {{ $}}
+ ; RV64IZFH-NEXT: [[COPY:%[0-9]+]]:_(s16) = COPY $f10_h
+ ; RV64IZFH-NEXT: $f10_h = COPY [[COPY]](s16)
+ ; RV64IZFH-NEXT: PseudoRET implicit $f10_h
ret half %x
}
@@ -84,6 +118,53 @@ define half @caller_half_in_regs(half %x) nounwind {
; RV32IZFH-NEXT: [[COPY1:%[0-9]+]]:_(s16) = COPY $f10_h
; RV32IZFH-NEXT: $f10_h = COPY [[COPY1]](s16)
; RV32IZFH-NEXT: PseudoRET implicit $f10_h
+ ;
+ ; RV64I-LABEL: name: caller_half_in_regs
+ ; RV64I: bb.1 (%ir-block.0):
+ ; RV64I-NEXT: liveins: $x10
+ ; RV64I-NEXT: {{ $}}
+ ; RV64I-NEXT: [[COPY:%[0-9]+]]:_(s64) = COPY $x10
+ ; RV64I-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s64)
+ ; RV64I-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $x2, implicit $x2
+ ; RV64I-NEXT: [[ANYEXT:%[0-9]+]]:_(s64) = G_ANYEXT [[TRUNC]](s16)
+ ; RV64I-NEXT: $x10 = COPY [[ANYEXT]](s64)
+ ; RV64I-NEXT: PseudoCALL target-flags(riscv-call) @caller_half_in_regs, csr_ilp32_lp64, implicit-def $x1, implicit $x10, implicit-def $x10
+ ; RV64I-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $x2, implicit $x2
+ ; RV64I-NEXT: [[COPY1:%[0-9]+]]:_(s64) = COPY $x10
+ ; RV64I-NEXT: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[COPY1]](s64)
+ ; RV64I-NEXT: [[ANYEXT1:%[0-9]+]]:_(s64) = G_ANYEXT [[TRUNC1]](s16)
+ ; RV64I-NEXT: $x10 = COPY [[ANYEXT1]](s64)
+ ; RV64I-NEXT: PseudoRET implicit $x10
+ ;
+ ; RV64IF-LABEL: name: caller_half_in_regs
+ ; RV64IF: bb.1 (%ir-block.0):
+ ; RV64IF-NEXT: liveins: $f10_f
+ ; RV64IF-NEXT: {{ $}}
+ ; RV64IF-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $f10_f
+ ; RV64IF-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
+ ; RV64IF-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $x2, implicit $x2
+ ; RV64IF-NEXT: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC]](s16)
+ ; RV64IF-NEXT: $f10_f = COPY [[ANYEXT]](s32)
+ ; RV64IF-NEXT: PseudoCALL target-flags(riscv-call) @caller_half_in_regs, csr_ilp32f_lp64f, implicit-def $x1, implicit $f10_f, implicit-def $f10_f
+ ; RV64IF-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $x2, implicit $x2
+ ; RV64IF-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $f10_f
+ ; RV64IF-NEXT: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[COPY1]](s32)
+ ; RV64IF-NEXT: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC1]](s16)
+ ; RV64IF-NEXT: $f10_f = COPY [[ANYEXT1]](s32)
+ ; RV64IF-NEXT: PseudoRET implicit $f10_f
+ ;
+ ; RV64IZFH-LABEL: name: caller_half_in_regs
+ ; RV64IZFH: bb.1 (%ir-block.0):
+ ; RV64IZFH-NEXT: liveins: $f10_h
+ ; RV64IZFH-NEXT: {{ $}}
+ ; RV64IZFH-NEXT: [[COPY:%[0-9]+]]:_(s16) = COPY $f10_h
+ ; RV64IZFH-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $x2, implicit $x2
+ ; RV64IZFH-NEXT: $f10_h = COPY [[COPY]](s16)
+ ; RV64IZFH-NEXT: PseudoCALL target-flags(riscv-call) @caller_half_in_regs, csr_ilp32f_lp64f, implicit-def $x1, implicit $f10_h, implicit-def $f10_h
+ ; RV64IZFH-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $x2, implicit $x2
+ ; RV64IZFH-NEXT: [[COPY1:%[0-9]+]]:_(s16) = COPY $f10_h
+ ; RV64IZFH-NEXT: $f10_h = COPY [[COPY1]](s16)
+ ; RV64IZFH-NEXT: PseudoRET implicit $f10_h
%y = call half @caller_half_in_regs(half %x)
ret half %y
}
@@ -119,6 +200,40 @@ define half @callee_half_mixed_with_int(i32 %x0, half %x) nounwind {
; RV32IZFH-NEXT: [[COPY1:%[0-9]+]]:_(s16) = COPY $f10_h
; RV32IZFH-NEXT: $f10_h = COPY [[COPY1]](s16)
; RV32IZFH-NEXT: PseudoRET implicit $f10_h
+ ;
+ ; RV64I-LABEL: name: callee_half_mixed_with_int
+ ; RV64I: bb.1 (%ir-block.0):
+ ; RV64I-NEXT: liveins: $x10, $x11
+ ; RV64I-NEXT: {{ $}}
+ ; RV64I-NEXT: [[COPY:%[0-9]+]]:_(s64) = COPY $x10
+ ; RV64I-NEXT: [[TRUNC:%[0-9]+]]:_(s32) = G_TRUNC [[COPY]](s64)
+ ; RV64I-NEXT: [[COPY1:%[0-9]+]]:_(s64) = COPY $x11
+ ; RV64I-NEXT: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[COPY1]](s64)
+ ; RV64I-NEXT: [[ANYEXT:%[0-9]+]]:_(s64) = G_ANYEXT [[TRUNC1]](s16)
+ ; RV64I-NEXT: $x10 = COPY [[ANYEXT]](s64)
+ ; RV64I-NEXT: PseudoRET implicit $x10
+ ;
+ ; RV64IF-LABEL: name: callee_half_mixed_with_int
+ ; RV64IF: bb.1 (%ir-block.0):
+ ; RV64IF-NEXT: liveins: $x10, $f10_f
+ ; RV64IF-NEXT: {{ $}}
+ ; RV64IF-NEXT: [[COPY:%[0-9]+]]:_(s64) = COPY $x10
+ ; RV64IF-NEXT: [[TRUNC:%[0-9]+]]:_(s32) = G_TRUNC [[COPY]](s64)
+ ; RV64IF-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $f10_f
+ ; RV64IF-NEXT: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[COPY1]](s32)
+ ; RV64IF-NEXT: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC1]](s16)
+ ; RV64IF-NEXT: $f10_f = COPY [[ANYEXT]](s32)
+ ; RV64IF-NEXT: PseudoRET implicit $f10_f
+ ;
+ ; RV64IZFH-LABEL: name: callee_half_mixed_with_int
+ ; RV64IZFH: bb.1 (%ir-block.0):
+ ; RV64IZFH-NEXT: liveins: $x10, $f10_h
+ ; RV64IZFH-NEXT: {{ $}}
+ ; RV64IZFH-NEXT: [[COPY:%[0-9]+]]:_(s64) = COPY $x10
+ ; RV64IZFH-NEXT: [[TRUNC:%[0-9]+]]:_(s32) = G_TRUNC [[COPY]](s64)
+ ; RV64IZFH-NEXT: [[COPY1:%[0-9]+]]:_(s16) = COPY $f10_h
+ ; RV64IZFH-NEXT: $f10_h = COPY [[COPY1]](s16)
+ ; RV64IZFH-NEXT: PseudoRET implicit $f10_h
ret half %x
}
@@ -175,6 +290,65 @@ define half @caller_half_mixed_with_int(half %x, i32 %x0) nounwind {
; RV32IZFH-NEXT: [[COPY2:%[0-9]+]]:_(s16) = COPY $f10_h
; RV32IZFH-NEXT: $f10_h = COPY [[COPY2]](s16)
; RV32IZFH-NEXT: PseudoRET implicit $f10_h
+ ;
+ ; RV64I-LABEL: name: caller_half_mixed_with_int
+ ; RV64I: bb.1 (%ir-block.0):
+ ; RV64I-NEXT: liveins: $x10, $x11
+ ; RV64I-NEXT: {{ $}}
+ ; RV64I-NEXT: [[COPY:%[0-9]+]]:_(s64) = COPY $x10
+ ; RV64I-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s64)
+ ; RV64I-NEXT: [[COPY1:%[0-9]+]]:_(s64) = COPY $x11
+ ; RV64I-NEXT: [[TRUNC1:%[0-9]+]]:_(s32) = G_TRUNC [[COPY1]](s64)
+ ; RV64I-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $x2, implicit $x2
+ ; RV64I-NEXT: [[ANYEXT:%[0-9]+]]:_(s64) = G_ANYEXT [[TRUNC1]](s32)
+ ; RV64I-NEXT: [[ANYEXT1:%[0-9]+]]:_(s64) = G_ANYEXT [[TRUNC]](s16)
+ ; RV64I-NEXT: $x10 = COPY [[ANYEXT]](s64)
+ ; RV64I-NEXT: $x11 = COPY [[ANYEXT1]](s64)
+ ; RV64I-NEXT: PseudoCALL target-flags(riscv-call) @callee_half_mixed_with_int, csr_ilp32_lp64, implicit-def $x1, implicit $x10, implicit $x11, implicit-def $x10
+ ; RV64I-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $x2, implicit $x2
+ ; RV64I-NEXT: [[COPY2:%[0-9]+]]:_(s64) = COPY $x10
+ ; RV64I-NEXT: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[COPY2]](s64)
+ ; RV64I-NEXT: [[ANYEXT2:%[0-9]+]]:_(s64) = G_ANYEXT [[TRUNC2]](s16)
+ ; RV64I-NEXT: $x10 = COPY [[ANYEXT2]](s64)
+ ; RV64I-NEXT: PseudoRET implicit $x10
+ ;
+ ; RV64IF-LABEL: name: caller_half_mixed_with_int
+ ; RV64IF: bb.1 (%ir-block.0):
+ ; RV64IF-NEXT: liveins: $x10, $f10_f
+ ; RV64IF-NEXT: {{ $}}
+ ; RV64IF-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $f10_f
+ ; RV64IF-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
+ ; RV64IF-NEXT: [[COPY1:%[0-9]+]]:_(s64) = COPY $x10
+ ; RV64IF-NEXT: [[TRUNC1:%[0-9]+]]:_(s32) = G_TRUNC [[COPY1]](s64)
+ ; RV64IF-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $x2, implicit $x2
+ ; RV64IF-NEXT: [[ANYEXT:%[0-9]+]]:_(s64) = G_ANYEXT [[TRUNC1]](s32)
+ ; RV64IF-NEXT: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC]](s16)
+ ; RV64IF-NEXT: $x10 = COPY [[ANYEXT]](s64)
+ ; RV64IF-NEXT: $f10_f = COPY [[ANYEXT1]](s32)
+ ; RV64IF-NEXT: PseudoCALL target-flags(riscv-call) @callee_half_mixed_with_int, csr_ilp32f_lp64f, implicit-def $x1, implicit $x10, implicit $f10_f, implicit-def $f10_f
+ ; RV64IF-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $x2, implicit $x2
+ ; RV64IF-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY $f10_f
+ ; RV64IF-NEXT: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[COPY2]](s32)
+ ; RV64IF-NEXT: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC2]](s16)
+ ; RV64IF-NEXT: $f10_f = COPY [[ANYEXT2]](s32)
+ ; RV64IF-NEXT: PseudoRET implicit $f10_f
+ ;
+ ; RV64IZFH-LABEL: name: caller_half_mixed_with_int
+ ; RV64IZFH: bb.1 (%ir-block.0):
+ ; RV64IZFH-NEXT: liveins: $x10, $f10_h
+ ; RV64IZFH-NEXT: {{ $}}
+ ; RV64IZFH-NEXT: [[COPY:%[0-9]+]]:_(s16) = COPY $f10_h
+ ; RV64IZFH-NEXT: [[COPY1:%[0-9]+]]:_(s64) = COPY $x10
+ ; RV64IZFH-NEXT: [[TRUNC:%[0-9]+]]:_(s32) = G_TRUNC [[COPY1]](s64)
+ ; RV64IZFH-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $x2, implicit $x2
+ ; RV64IZFH-NEXT: [[ANYEXT:%[0-9]+]]:_(s64) = G_ANYEXT [[TRUNC]](s32)
+ ; RV64IZFH-NEXT: $x10 = COPY [[ANYEXT]](s64)
+ ; RV64IZFH-NEXT: $f10_h = COPY [[COPY]](s16)
+ ; RV64IZFH-NEXT: PseudoCALL target-flags(riscv-call) @callee_half_mixed_with_int, csr_ilp32f_lp64f, implicit-def $x1, implicit $x10, implicit $f10_h, implicit-def $f10_h
+ ; RV64IZFH-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $x2, implicit $x2
+ ; RV64IZFH-NEXT: [[COPY2:%[0-9]+]]:_(s16) = COPY $f10_h
+ ; RV64IZFH-NEXT: $f10_h = COPY [[COPY2]](s16)
+ ; RV64IZFH-NEXT: PseudoRET implicit $f10_h
%y = call half @callee_half_mixed_with_int(i32 %x0, half %x)
ret half %y
}
@@ -232,6 +406,83 @@ define half @callee_half_return_stack1(i32 %v1, i32 %v2, i32 %v3, i32 %v4, i32 %
; RV32IZFH-NEXT: [[COPY8:%[0-9]+]]:_(s16) = COPY $f10_h
; RV32IZFH-NEXT: $f10_h = COPY [[COPY8]](s16)
; RV32IZFH-NEXT: PseudoRET implicit $f10_h
+ ;
+ ; RV64I-LABEL: name: callee_half_return_stack1
+ ; RV64I: bb.1 (%ir-block.0):
+ ; RV64I-NEXT: liveins: $x10, $x11, $x12, $x13, $x14, $x15, $x16, $x17
+ ; RV64I-NEXT: {{ $}}
+ ; RV64I-NEXT: [[COPY:%[0-9]+]]:_(s64) = COPY $x10
+ ; RV64I-NEXT: [[TRUNC:%[0-9]+]]:_(s32) = G_TRUNC [[COPY]](s64)
+ ; RV64I-NEXT: [[COPY1:%[0-9]+]]:_(s64) = COPY $x11
+ ; RV64I-NEXT: [[TRUNC1:%[0-9]+]]:_(s32) = G_TRUNC [[COPY1]](s64)
+ ; RV64I-NEXT: [[COPY2:%[0-9]+]]:_(s64) = COPY $x12
+ ; RV64I-NEXT: [[TRUNC2:%[0-9]+]]:_(s32) = G_TRUNC [[COPY2]](s64)
+ ; RV64I-NEXT: [[COPY3:%[0-9]+]]:_(s64) = COPY $x13
+ ; RV64I-NEXT: [[TRUNC3:%[0-9]+]]:_(s32) = G_TRUNC [[COPY3]](s64)
+ ; RV64I-NEXT: [[COPY4:%[0-9]+]]:_(s64) = COPY $x14
+ ; RV64I-NEXT: [[TRUNC4:%[0-9]+]]:_(s32) = G_TRUNC [[COPY4]](s64)
+ ; RV64I-NEXT: [[COPY5:%[0-9]+]]:_(s64) = COPY $x15
+ ; RV64I-NEXT: [[TRUNC5:%[0-9]+]]:_(s32) = G_TRUNC [[COPY5]](s64)
+ ; RV64I-NEXT: [[COPY6:%[0-9]+]]:_(s64) = COPY $x16
+ ; RV64I-NEXT: [[TRUNC6:%[0-9]+]]:_(s32) = G_TRUNC [[COPY6]](s64)
+ ; RV64I-NEXT: [[COPY7:%[0-9]+]]:_(s64) = COPY $x17
+ ; RV64I-NEXT: [[TRUNC7:%[0-9]+]]:_(s32) = G_TRUNC [[COPY7]](s64)
+ ; RV64I-NEXT: [[FRAME_INDEX:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.0
+ ; RV64I-NEXT: [[LOAD:%[0-9]+]]:_(s64) = G_LOAD [[FRAME_INDEX]](p0) :: (load (s64) from %fixed-stack.0, align 16)
+ ; RV64I-NEXT: [[TRUNC8:%[0-9]+]]:_(s16) = G_TRUNC [[LOAD]](s64)
+ ; RV64I-NEXT: [[ANYEXT:%[0-9]+]]:_(s64) = G_ANYEXT [[TRUNC8]](s16)
+ ; RV64I-NEXT: $x10 = COPY [[ANYEXT]](s64)
+ ; RV64I-NEXT: PseudoRET implicit $x10
+ ;
+ ; RV64IF-LABEL: name: callee_half_return_stack1
+ ; RV64IF: bb.1 (%ir-block.0):
+ ; RV64IF-NEXT: liveins: $x10, $x11, $x12, $x13, $x14, $x15, $x16, $x17, $f10_f
+ ; RV64IF-NEXT: {{ $}}
+ ; RV64IF-NEXT: [[COPY:%[0-9]+]]:_(s64) = COPY $x10
+ ; RV64IF-NEXT: [[TRUNC:%[0-9]+]]:_(s32) = G_TRUNC [[COPY]](s64)
+ ; RV64IF-NEXT: [[COPY1:%[0-9]+]]:_(s64) = COPY $x11
+ ; RV64IF-NEXT: [[TRUNC1:%[0-9]+]]:_(s32) = G_TRUNC [[COPY1]](s64)
+ ; RV64IF-NEXT: [[COPY2:%[0-9]+]]:_(s64) = COPY $x12
+ ; RV64IF-NEXT: [[TRUNC2:%[0-9]+]]:_(s32) = G_TRUNC [[COPY2]](s64)
+ ; RV64IF-NEXT: [[COPY3:%[0-9]+]]:_(s64) = COPY $x13
+ ; RV64IF-NEXT: [[TRUNC3:%[0-9]+]]:_(s32) = G_TRUNC [[COPY3]](s64)
+ ; RV64IF-NEXT: [[COPY4:%[0-9]+]]:_(s64) = COPY $x14
+ ; RV64IF-NEXT: [[TRUNC4:%[0-9]+]]:_(s32) = G_TRUNC [[COPY4]](s64)
+ ; RV64IF-NEXT: [[COPY5:%[0-9]+]]:_(s64) = COPY $x15
+ ; RV64IF-NEXT: [[TRUNC5:%[0-9]+]]:_(s32) = G_TRUNC [[COPY5]](s64)
+ ; RV64IF-NEXT: [[COPY6:%[0-9]+]]:_(s64) = COPY $x16
+ ; RV64IF-NEXT: [[TRUNC6:%[0-9]+]]:_(s32) = G_TRUNC [[COPY6]](s64)
+ ; RV64IF-NEXT: [[COPY7:%[0-9]+]]:_(s64) = COPY $x17
+ ; RV64IF-NEXT: [[TRUNC7:%[0-9]+]]:_(s32) = G_TRUNC [[COPY7]](s64)
+ ; RV64IF-NEXT: [[COPY8:%[0-9]+]]:_(s32) = COPY $f10_f
+ ; RV64IF-NEXT: [[TRUNC8:%[0-9]+]]:_(s16) = G_TRUNC [[COPY8]](s32)
+ ; RV64IF-NEXT: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC8]](s16)
+ ; RV64IF-NEXT: $f10_f = COPY [[ANYEXT]](s32)
+ ; RV64IF-NEXT: PseudoRET implicit $f10_f
+ ;
+ ; RV64IZFH-LABEL: name: callee_half_return_stack1
+ ; RV64IZFH: bb.1 (%ir-block.0):
+ ; RV64IZFH-NEXT: liveins: $x10, $x11, $x12, $x13, $x14, $x15, $x16, $x17, $f10_h
+ ; RV64IZFH-NEXT: {{ $}}
+ ; RV64IZFH-NEXT: [[COPY:%[0-9]+]]:_(s64) = COPY $x10
+ ; RV64IZFH-NEXT: [[TRUNC:%[0-9]+]]:_(s32) = G_TRUNC [[COPY]](s64)
+ ; RV64IZFH-NEXT: [[COPY1:%[0-9]+]]:_(s64) = COPY $x11
+ ; RV64IZFH-NEXT: [[TRUNC1:%[0-9]+]]:_(s32) = G_TRUNC [[COPY1]](s64)
+ ; RV64IZFH-NEXT: [[COPY2:%[0-9]+]]:_(s64) = COPY $x12
+ ; RV64IZFH-NEXT: [[TRUNC2:%[0-9]+]]:_(s32) = G_TRUNC [[COPY2]](s64)
+ ; RV64IZFH-NEXT: [[COPY3:%[0-9]+]]:_(s64) = COPY $x13
+ ; RV64IZFH-NEXT: [[TRUNC3:%[0-9]+]]:_(s32) = G_TRUNC [[COPY3]](s64)
+ ; RV64IZFH-NEXT: [[COPY4:%[0-9]+]]:_(s64) = COPY $x14
+ ; RV64IZFH-NEXT: [[TRUNC4:%[0-9]+]]:_(s32) = G_TRUNC [[COPY4]](s64)
+ ; RV64IZFH-NEXT: [[COPY5:%[0-9]+]]:_(s64) = COPY $x15
+ ; RV64IZFH-NEXT: [[TRUNC5:%[0-9]+]]:_(s32) = G_TRUNC [[COPY5]](s64)
+ ; RV64IZFH-NEXT: [[COPY6:%[0-9]+]]:_(s64) = COPY $x16
+ ; RV64IZFH-NEXT: [[TRUNC6:%[0-9]+]]:_(s32) = G_TRUNC [[COPY6]](s64)
+ ; RV64IZFH-NEXT: [[COPY7:%[0-9]+]]:_(s64) = COPY $x17
+ ; RV64IZFH-NEXT: [[TRUNC7:%[0-9]+]]:_(s32) = G_TRUNC [[COPY7]](s64)
+ ; RV64IZFH-NEXT: [[COPY8:%[0-9]+]]:_(s16) = COPY $f10_h
+ ; RV64IZFH-NEXT: $f10_h = COPY [[COPY8]](s16)
+ ; RV64IZFH-NEXT: PseudoRET implicit $f10_h
ret half %x
}
@@ -333,6 +584,131 @@ define half @caller_half_return_stack1(i32 %v1, half %x) nounwind {
; RV32IZFH-NEXT: [[COPY2:%[0-9]+]]:_(s16) = COPY $f10_h
; RV32IZFH-NEXT: $f10_h = COPY [[COPY2]](s16)
; RV32IZFH-NEXT: PseudoRET implicit $f10_h
+ ;
+ ; RV64I-LABEL: name: caller_half_return_stack1
+ ; RV64I: bb.1 (%ir-block.0):
+ ; RV64I-NEXT: liveins: $x10, $x11
+ ; RV64I-NEXT: {{ $}}
+ ; RV64I-NEXT: [[COPY:%[0-9]+]]:_(s64) = COPY $x10
+ ; RV64I-NEXT: [[TRUNC:%[0-9]+]]:_(s32) = G_TRUNC [[COPY]](s64)
+ ; RV64I-NEXT: [[COPY1:%[0-9]+]]:_(s64) = COPY $x11
+ ; RV64I-NEXT: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[COPY1]](s64)
+ ; RV64I-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
+ ; RV64I-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 1
+ ; RV64I-NEXT: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 2
+ ; RV64I-NEXT: [[C3:%[0-9]+]]:_(s32) = G_CONSTANT i32 5
+ ; RV64I-NEXT: [[C4:%[0-9]+]]:_(s32) = G_CONSTANT i32 6
+ ; RV64I-NEXT: [[C5:%[0-9]+]]:_(s32) = G_CONSTANT i32 7
+ ; RV64I-NEXT: [[C6:%[0-9]+]]:_(s32) = G_CONSTANT i32 8
+ ; RV64I-NEXT: ADJCALLSTACKDOWN 8, 0, implicit-def $x2, implicit $x2
+ ; RV64I-NEXT: [[ANYEXT:%[0-9]+]]:_(s64) = G_ANYEXT [[C]](s32)
+ ; RV64I-NEXT: [[ANYEXT1:%[0-9]+]]:_(s64) = G_ANYEXT [[C1]](s32)
+ ; RV64I-NEXT: [[ANYEXT2:%[0-9]+]]:_(s64) = G_ANYEXT [[C2]](s32)
+ ; RV64I-NEXT: [[ANYEXT3:%[0-9]+]]:_(s64) = G_ANYEXT [[TRUNC]](s32)
+ ; RV64I-NEXT: [[ANYEXT4:%[0-9]+]]:_(s64) = G_ANYEXT [[C3]](s32)
+ ; RV64I-NEXT: [[ANYEXT5:%[0-9]+]]:_(s64) = G_ANYEXT [[C4]](s32)
+ ; RV64I-NEXT: [[ANYEXT6:%[0-9]+]]:_(s64) = G_ANYEXT [[C5]](s32)
+ ; RV64I-NEXT: [[ANYEXT7:%[0-9]+]]:_(s64) = G_ANYEXT [[C6]](s32)
+ ; RV64I-NEXT: [[ANYEXT8:%[0-9]+]]:_(s64) = G_ANYEXT [[TRUNC1]](s16)
+ ; RV64I-NEXT: [[COPY2:%[0-9]+]]:_(p0) = COPY $x2
+ ; RV64I-NEXT: [[C7:%[0-9]+]]:_(s64) = G_CONSTANT i64 0
+ ; RV64I-NEXT: [[PTR_ADD:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY2]], [[C7]](s64)
+ ; RV64I-NEXT: G_STORE [[ANYEXT8]](s64), [[PTR_ADD]](p0) :: (store (s64) into stack, align 16)
+ ; RV64I-NEXT: $x10 = COPY [[ANYEXT]](s64)
+ ; RV64I-NEXT: $x11 = COPY [[ANYEXT1]](s64)
+ ; RV64I-NEXT: $x12 = COPY [[ANYEXT2]](s64)
+ ; RV64I-NEXT: $x13 = COPY [[ANYEXT3]](s64)
+ ; RV64I-NEXT: $x14 = COPY [[ANYEXT4]](s64)
+ ; RV64I-NEXT: $x15 = COPY [[ANYEXT5]](s64)
+ ; RV64I-NEXT: $x16 = COPY [[ANYEXT6]](s64)
+ ; RV64I-NEXT: $x17 = COPY [[ANYEXT7]](s64)
+ ; RV64I-NEXT: PseudoCALL target-flags(riscv-call) @callee_half_return_stack1, csr_ilp32_lp64, implicit-def $x1, implicit $x10, implicit $x11, implicit $x12, implicit $x13, implicit $x14, implicit $x15, implicit $x16, implicit $x17, implicit-def $x10
+ ; RV64I-NEXT: ADJCALLSTACKUP 8, 0, implicit-def $x2, implicit $x2
+ ; RV64I-NEXT: [[COPY3:%[0-9]+]]:_(s64) = COPY $x10
+ ; RV64I-NEXT: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[COPY3]](s64)
+ ; RV64I-NEXT: [[ANYEXT9:%[0-9]+]]:_(s64) = G_ANYEXT [[TRUNC2]](s16)
+ ; RV64I-NEXT: $x10 = COPY [[ANYEXT9]](s64)
+ ; RV64I-NEXT: PseudoRET implicit $x10
+ ;
+ ; RV64IF-LABEL: name: caller_half_return_stack1
+ ; RV64IF: bb.1 (%ir-block.0):
+ ; RV64IF-NEXT: liveins: $x10, $f10_f
+ ; RV64IF-NEXT: {{ $}}
+ ; RV64IF-NEXT: [[COPY:%[0-9]+]]:_(s64) = COPY $x10
+ ; RV64IF-NEXT: [[TRUNC:%[0-9]+]]:_(s32) = G_TRUNC [[COPY]](s64)
+ ; RV64IF-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $f10_f
+ ; RV64IF-NEXT: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[COPY1]](s32)
+ ; RV64IF-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
+ ; RV64IF-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 1
+ ; RV64IF-NEXT: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 2
+ ; RV64IF-NEXT: [[C3:%[0-9]+]]:_(s32) = G_CONSTANT i32 5
+ ; RV64IF-NEXT: [[C4:%[0-9]+]]:_(s32) = G_CONSTANT i32 6
+ ; RV64IF-NEXT: [[C5:%[0-9]+]]:_(s32) = G_CONSTANT i32 7
+ ; RV64IF-NEXT: [[C6:%[0-9]+]]:_(s32) = G_CONSTANT i32 8
+ ; RV64IF-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $x2, implicit $x2
+ ; RV64IF-NEXT: [[ANYEXT:%[0-9]+]]:_(s64) = G_ANYEXT [[C]](s32)
+ ; RV64IF-NEXT: [[ANYEXT1:%[0-9]+]]:_(s64) = G_ANYEXT [[C1]](s32)
+ ; RV64IF-NEXT: [[ANYEXT2:%[0-9]+]]:_(s64) = G_ANYEXT [[C2]](s32)
+ ; RV64IF-NEXT: [[ANYEXT3:%[0-9]+]]:_(s64) = G_ANYEXT [[TRUNC]](s32)
+ ; RV64IF-NEXT: [[ANYEXT4:%[0-9]+]]:_(s64) = G_ANYEXT [[C3]](s32)
+ ; RV64IF-NEXT: [[ANYEXT5:%[0-9]+]]:_(s64) = G_ANYEXT [[C4]](s32)
+ ; RV64IF-NEXT: [[ANYEXT6:%[0-9]+]]:_(s64) = G_ANYEXT [[C5]](s32)
+ ; RV64IF-NEXT: [[ANYEXT7:%[0-9]+]]:_(s64) = G_ANYEXT [[C6]](s32)
+ ; RV64IF-NEXT: [[ANYEXT8:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC1]](s16)
+ ; RV64IF-NEXT: $x10 = COPY [[ANYEXT]](s64)
+ ; RV64IF-NEXT: $x11 = COPY [[ANYEXT1]](s64)
+ ; RV64IF-NEXT: $x12 = COPY [[ANYEXT2]](s64)
+ ; RV64IF-NEXT: $x13 = COPY [[ANYEXT3]](s64)
+ ; RV64IF-NEXT: $x14 = COPY [[ANYEXT4]](s64)
+ ; RV64IF-NEXT: $x15 = COPY [[ANYEXT5]](s64)
+ ; RV64IF-NEXT: $x16 = COPY [[ANYEXT6]](s64)
+ ; RV64IF-NEXT: $x17 = COPY [[ANYEXT7]](s64)
+ ; RV64IF-NEXT: $f10_f = COPY [[ANYEXT8]](s32)
+ ; RV64IF-NEXT: PseudoCALL target-flags(riscv-call) @callee_half_return_stack1, csr_ilp32f_lp64f, implicit-def $x1, implicit $x10, implicit $x11, implicit $x12, implicit $x13, implicit $x14, implicit $x15, implicit $x16, implicit $x17, implicit $f10_f, implicit-def $f10_f
+ ; RV64IF-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $x2, implicit $x2
+ ; RV64IF-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY $f10_f
+ ; RV64IF-NEXT: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[COPY2]](s32)
+ ; RV64IF-NEXT: [[ANYEXT9:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC2]](s16)
+ ; RV64IF-NEXT: $f10_f = COPY [[ANYEXT9]](s32)
+ ; RV64IF-NEXT: PseudoRET implicit $f10_f
+ ;
+ ; RV64IZFH-LABEL: name: caller_half_return_stack1
+ ; RV64IZFH: bb.1 (%ir-block.0):
+ ; RV64IZFH-NEXT: liveins: $x10, $f10_h
+ ; RV64IZFH-NEXT: {{ $}}
+ ; RV64IZFH-NEXT: [[COPY:%[0-9]+]]:_(s64) = COPY $x10
+ ; RV64IZFH-NEXT: [[TRUNC:%[0-9]+]]:_(s32) = G_TRUNC [[COPY]](s64)
+ ; RV64IZFH-NEXT: [[COPY1:%[0-9]+]]:_(s16) = COPY $f10_h
+ ; RV64IZFH-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
+ ; RV64IZFH-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 1
+ ; RV64IZFH-NEXT: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 2
+ ; RV64IZFH-NEXT: [[C3:%[0-9]+]]:_(s32) = G_CONSTANT i32 5
+ ; RV64IZFH-NEXT: [[C4:%[0-9]+]]:_(s32) = G_CONSTANT i32 6
+ ; RV64IZFH-NEXT: [[C5:%[0-9]+]]:_(s32) = G_CONSTANT i32 7
+ ; RV64IZFH-NEXT: [[C6:%[0-9]+]]:_(s32) = G_CONSTANT i32 8
+ ; RV64IZFH-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $x2, implicit $x2
+ ; RV64IZFH-NEXT: [[ANYEXT:%[0-9]+]]:_(s64) = G_ANYEXT [[C]](s32)
+ ; RV64IZFH-NEXT: [[ANYEXT1:%[0-9]+]]:_(s64) = G_ANYEXT [[C1]](s32)
+ ; RV64IZFH-NEXT: [[ANYEXT2:%[0-9]+]]:_(s64) = G_ANYEXT [[C2]](s32)
+ ; RV64IZFH-NEXT: [[ANYEXT3:%[0-9]+]]:_(s64) = G_ANYEXT [[TRUNC]](s32)
+ ; RV64IZFH-NEXT: [[ANYEXT4:%[0-9]+]]:_(s64) = G_ANYEXT [[C3]](s32)
+ ; RV64IZFH-NEXT: [[ANYEXT5:%[0-9]+]]:_(s64) = G_ANYEXT [[C4]](s32)
+ ; RV64IZFH-NEXT: [[ANYEXT6:%[0-9]+]]:_(s64) = G_ANYEXT [[C5]](s32)
+ ; RV64IZFH-NEXT: [[ANYEXT7:%[0-9]+]]:_(s64) = G_ANYEXT [[C6]](s32)
+ ; RV64IZFH-NEXT: $x10 = COPY [[ANYEXT]](s64)
+ ; RV64IZFH-NEXT: $x11 = COPY [[ANYEXT1]](s64)
+ ; RV64IZFH-NEXT: $x12 = COPY [[ANYEXT2]](s64)
+ ; RV64IZFH-NEXT: $x13 = COPY [[ANYEXT3]](s64)
+ ; RV64IZFH-NEXT: $x14 = COPY [[ANYEXT4]](s64)
+ ; RV64IZFH-NEXT: $x15 = COPY [[ANYEXT5]](s64)
+ ; RV64IZFH-NEXT: $x16 = COPY [[ANYEXT6]](s64)
+ ; RV64IZFH-NEXT: $x17 = COPY [[ANYEXT7]](s64)
+ ; RV64IZFH-NEXT: $f10_h = COPY [[COPY1]](s16)
+ ; RV64IZFH-NEXT: PseudoCALL target-flags(riscv-call) @callee_half_return_stack1, csr_ilp32f_lp64f, implicit-def $x1, implicit $x10, implicit $x11, implicit $x12, implicit $x13, implicit $x14, implicit $x15, implicit $x16, implicit $x17, implicit $f10_h, implicit-def $f10_h
+ ; RV64IZFH-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $x2, implicit $x2
+ ; RV64IZFH-NEXT: [[COPY2:%[0-9]+]]:_(s16) = COPY $f10_h
+ ; RV64IZFH-NEXT: $f10_h = COPY [[COPY2]](s16)
+ ; RV64IZFH-NEXT: PseudoRET implicit $f10_h
%y = call half @callee_half_return_stack1(i32 0, i32 1, i32 2, i32 %v1, i32 5, i32 6, i32 7, i32 8, half %x)
ret half %y
}
@@ -407,6 +783,76 @@ define half @callee_half_return_stack2(half %v1, half %v2, half %v3, half %v4, h
; RV32IZFH-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY8]](s32)
; RV32IZFH-NEXT: $f10_h = COPY [[TRUNC]](s16)
; RV32IZFH-NEXT: PseudoRET implicit $f10_h
+ ;
+ ; RV64I-LABEL: name: callee_half_return_stack2
+ ; RV64I: bb.1 (%ir-block.0):
+ ; RV64I-NEXT: liveins: $x10, $x11, $x12, $x13, $x14, $x15, $x16, $x17
+ ; RV64I-NEXT: {{ $}}
+ ; RV64I-NEXT: [[COPY:%[0-9]+]]:_(s64) = COPY $x10
+ ; RV64I-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s64)
+ ; RV64I-NEXT: [[COPY1:%[0-9]+]]:_(s64) = COPY $x11
+ ; RV64I-NEXT: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[COPY1]](s64)
+ ; RV64I-NEXT: [[COPY2:%[0-9]+]]:_(s64) = COPY $x12
+ ; RV64I-NEXT: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[COPY2]](s64)
+ ; RV64I-NEXT: [[COPY3:%[0-9]+]]:_(s64) = COPY $x13
+ ; RV64I-NEXT: [[TRUNC3:%[0-9]+]]:_(s16) = G_TRUNC [[COPY3]](s64)
+ ; RV64I-NEXT: [[COPY4:%[0-9]+]]:_(s64) = COPY $x14
+ ; RV64I-NEXT: [[TRUNC4:%[0-9]+]]:_(s16) = G_TRUNC [[COPY4]](s64)
+ ; RV64I-NEXT: [[COPY5:%[0-9]+]]:_(s64) = COPY $x15
+ ; RV64I-NEXT: [[TRUNC5:%[0-9]+]]:_(s16) = G_TRUNC [[COPY5]](s64)
+ ; RV64I-NEXT: [[COPY6:%[0-9]+]]:_(s64) = COPY $x16
+ ; RV64I-NEXT: [[TRUNC6:%[0-9]+]]:_(s16) = G_TRUNC [[COPY6]](s64)
+ ; RV64I-NEXT: [[COPY7:%[0-9]+]]:_(s64) = COPY $x17
+ ; RV64I-NEXT: [[TRUNC7:%[0-9]+]]:_(s16) = G_TRUNC [[COPY7]](s64)
+ ; RV64I-NEXT: [[FRAME_INDEX:%[0-9]+]]:_(p0) = G_FRAME_INDEX %fixed-stack.0
+ ; RV64I-NEXT: [[LOAD:%[0-9]+]]:_(s64) = G_LOAD [[FRAME_INDEX]](p0) :: (load (s64) from %fixed-stack.0, align 16)
+ ; RV64I-NEXT: [[TRUNC8:%[0-9]+]]:_(s16) = G_TRUNC [[LOAD]](s64)
+ ; RV64I-NEXT: [[ANYEXT:%[0-9]+]]:_(s64) = G_ANYEXT [[TRUNC8]](s16)
+ ; RV64I-NEXT: $x10 = COPY [[ANYEXT]](s64)
+ ; RV64I-NEXT: PseudoRET implicit $x10
+ ;
+ ; RV64IF-LABEL: name: callee_half_return_stack2
+ ; RV64IF: bb.1 (%ir-block.0):
+ ; RV64IF-NEXT: liveins: $x10, $f10_f, $f11_f, $f12_f, $f13_f, $f14_f, $f15_f, $f16_f, $f17_f
+ ; RV64IF-NEXT: {{ $}}
+ ; RV64IF-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $f10_f
+ ; RV64IF-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
+ ; RV64IF-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $f11_f
+ ; RV64IF-NEXT: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[COPY1]](s32)
+ ; RV64IF-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY $f12_f
+ ; RV64IF-NEXT: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[COPY2]](s32)
+ ; RV64IF-NEXT: [[COPY3:%[0-9]+]]:_(s32) = COPY $f13_f
+ ; RV64IF-NEXT: [[TRUNC3:%[0-9]+]]:_(s16) = G_TRUNC [[COPY3]](s32)
+ ; RV64IF-NEXT: [[COPY4:%[0-9]+]]:_(s32) = COPY $f14_f
+ ; RV64IF-NEXT: [[TRUNC4:%[0-9]+]]:_(s16) = G_TRUNC [[COPY4]](s32)
+ ; RV64IF-NEXT: [[COPY5:%[0-9]+]]:_(s32) = COPY $f15_f
+ ; RV64IF-NEXT: [[TRUNC5:%[0-9]+]]:_(s16) = G_TRUNC [[COPY5]](s32)
+ ; RV64IF-NEXT: [[COPY6:%[0-9]+]]:_(s32) = COPY $f16_f
+ ; RV64IF-NEXT: [[TRUNC6:%[0-9]+]]:_(s16) = G_TRUNC [[COPY6]](s32)
+ ; RV64IF-NEXT: [[COPY7:%[0-9]+]]:_(s32) = COPY $f17_f
+ ; RV64IF-NEXT: [[TRUNC7:%[0-9]+]]:_(s16) = G_TRUNC [[COPY7]](s32)
+ ; RV64IF-NEXT: [[COPY8:%[0-9]+]]:_(s64) = COPY $x10
+ ; RV64IF-NEXT: [[TRUNC8:%[0-9]+]]:_(s16) = G_TRUNC [[COPY8]](s64)
+ ; RV64IF-NEXT: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC8]](s16)
+ ; RV64IF-NEXT: $f10_f = COPY [[ANYEXT]](s32)
+ ; RV64IF-NEXT: PseudoRET implicit $f10_f
+ ;
+ ; RV64IZFH-LABEL: name: callee_half_return_stack2
+ ; RV64IZFH: bb.1 (%ir-block.0):
+ ; RV64IZFH-NEXT: liveins: $x10, $f10_h, $f11_h, $f12_h, $f13_h, $f14_h, $f15_h, $f16_h, $f17_h
+ ; RV64IZFH-NEXT: {{ $}}
+ ; RV64IZFH-NEXT: [[COPY:%[0-9]+]]:_(s16) = COPY $f10_h
+ ; RV64IZFH-NEXT: [[COPY1:%[0-9]+]]:_(s16) = COPY $f11_h
+ ; RV64IZFH-NEXT: [[COPY2:%[0-9]+]]:_(s16) = COPY $f12_h
+ ; RV64IZFH-NEXT: [[COPY3:%[0-9]+]]:_(s16) = COPY $f13_h
+ ; RV64IZFH-NEXT: [[COPY4:%[0-9]+]]:_(s16) = COPY $f14_h
+ ; RV64IZFH-NEXT: [[COPY5:%[0-9]+]]:_(s16) = COPY $f15_h
+ ; RV64IZFH-NEXT: [[COPY6:%[0-9]+]]:_(s16) = COPY $f16_h
+ ; RV64IZFH-NEXT: [[COPY7:%[0-9]+]]:_(s16) = COPY $f17_h
+ ; RV64IZFH-NEXT: [[COPY8:%[0-9]+]]:_(s64) = COPY $x10
+ ; RV64IZFH-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY8]](s64)
+ ; RV64IZFH-NEXT: $f10_h = COPY [[TRUNC]](s16)
+ ; RV64IZFH-NEXT: PseudoRET implicit $f10_h
ret half %x
}
@@ -505,12 +951,116 @@ define half @caller_half_return_stack2(half %x, half %y) nounwind {
; RV32IZFH-NEXT: $f15_h = COPY [[COPY1]](s16)
; RV32IZFH-NEXT: $f16_h = COPY [[COPY1]](s16)
; RV32IZFH-NEXT: $f17_h = COPY [[COPY1]](s16)
- ; RV32IZFH-NEXT: $x10 = COPY [[COPY]](s16)
+ ; RV32IZFH-NEXT: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[COPY]](s16)
+ ; RV32IZFH-NEXT: $x10 = COPY [[ANYEXT]](s32)
; RV32IZFH-NEXT: PseudoCALL target-flags(riscv-call) @callee_half_return_stack2, csr_ilp32f_lp64f, implicit-def $x1, implicit $f10_h, implicit $f11_h, implicit $f12_h, implicit $f13_h, implicit $f14_h, implicit $f15_h, implicit $f16_h, implicit $f17_h, implicit $x10, implicit-def $f10_h
; RV32IZFH-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $x2, implicit $x2
; RV32IZFH-NEXT: [[COPY2:%[0-9]+]]:_(s16) = COPY $f10_h
; RV32IZFH-NEXT: $f10_h = COPY [[COPY2]](s16)
; RV32IZFH-NEXT: PseudoRET implicit $f10_h
+ ;
+ ; RV64I-LABEL: name: caller_half_return_stack2
+ ; RV64I: bb.1 (%ir-block.0):
+ ; RV64I-NEXT: liveins: $x10, $x11
+ ; RV64I-NEXT: {{ $}}
+ ; RV64I-NEXT: [[COPY:%[0-9]+]]:_(s64) = COPY $x10
+ ; RV64I-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s64)
+ ; RV64I-NEXT: [[COPY1:%[0-9]+]]:_(s64) = COPY $x11
+ ; RV64I-NEXT: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[COPY1]](s64)
+ ; RV64I-NEXT: [[C:%[0-9]+]]:_(s16) = G_FCONSTANT half 0xH3C00
+ ; RV64I-NEXT: [[C1:%[0-9]+]]:_(s16) = G_FCONSTANT half 0xH4200
+ ; RV64I-NEXT: ADJCALLSTACKDOWN 8, 0, implicit-def $x2, implicit $x2
+ ; RV64I-NEXT: [[ANYEXT:%[0-9]+]]:_(s64) = G_ANYEXT [[TRUNC]](s16)
+ ; RV64I-NEXT: [[ANYEXT1:%[0-9]+]]:_(s64) = G_ANYEXT [[C]](s16)
+ ; RV64I-NEXT: [[ANYEXT2:%[0-9]+]]:_(s64) = G_ANYEXT [[TRUNC]](s16)
+ ; RV64I-NEXT: [[ANYEXT3:%[0-9]+]]:_(s64) = G_ANYEXT [[C1]](s16)
+ ; RV64I-NEXT: [[ANYEXT4:%[0-9]+]]:_(s64) = G_ANYEXT [[TRUNC]](s16)
+ ; RV64I-NEXT: [[ANYEXT5:%[0-9]+]]:_(s64) = G_ANYEXT [[TRUNC1]](s16)
+ ; RV64I-NEXT: [[ANYEXT6:%[0-9]+]]:_(s64) = G_ANYEXT [[TRUNC1]](s16)
+ ; RV64I-NEXT: [[ANYEXT7:%[0-9]+]]:_(s64) = G_ANYEXT [[TRUNC1]](s16)
+ ; RV64I-NEXT: [[ANYEXT8:%[0-9]+]]:_(s64) = G_ANYEXT [[TRUNC]](s16)
+ ; RV64I-NEXT: [[COPY2:%[0-9]+]]:_(p0) = COPY $x2
+ ; RV64I-NEXT: [[C2:%[0-9]+]]:_(s64) = G_CONSTANT i64 0
+ ; RV64I-NEXT: [[PTR_ADD:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY2]], [[C2]](s64)
+ ; RV64I-NEXT: G_STORE [[ANYEXT8]](s64), [[PTR_ADD]](p0) :: (store (s64) into stack, align 16)
+ ; RV64I-NEXT: $x10 = COPY [[ANYEXT]](s64)
+ ; RV64I-NEXT: $x11 = COPY [[ANYEXT1]](s64)
+ ; RV64I-NEXT: $x12 = COPY [[ANYEXT2]](s64)
+ ; RV64I-NEXT: $x13 = COPY [[ANYEXT3]](s64)
+ ; RV64I-NEXT: $x14 = COPY [[ANYEXT4]](s64)
+ ; RV64I-NEXT: $x15 = COPY [[ANYEXT5]](s64)
+ ; RV64I-NEXT: $x16 = COPY [[ANYEXT6]](s64)
+ ; RV64I-NEXT: $x17 = COPY [[ANYEXT7]](s64)
+ ; RV64I-NEXT: PseudoCALL target-flags(riscv-call) @callee_half_return_stack2, csr_ilp32_lp64, implicit-def $x1, implicit $x10, implicit $x11, implicit $x12, implicit $x13, implicit $x14, implicit $x15, implicit $x16, implicit $x17, implicit-def $x10
+ ; RV64I-NEXT: ADJCALLSTACKUP 8, 0, implicit-def $x2, implicit $x2
+ ; RV64I-NEXT: [[COPY3:%[0-9]+]]:_(s64) = COPY $x10
+ ; RV64I-NEXT: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[COPY3]](s64)
+ ; RV64I-NEXT: [[ANYEXT9:%[0-9]+]]:_(s64) = G_ANYEXT [[TRUNC2]](s16)
+ ; RV64I-NEXT: $x10 = COPY [[ANYEXT9]](s64)
+ ; RV64I-NEXT: PseudoRET implicit $x10
+ ;
+ ; RV64IF-LABEL: name: caller_half_return_stack2
+ ; RV64IF: bb.1 (%ir-block.0):
+ ; RV64IF-NEXT: liveins: $f10_f, $f11_f
+ ; RV64IF-NEXT: {{ $}}
+ ; RV64IF-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $f10_f
+ ; RV64IF-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
+ ; RV64IF-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $f11_f
+ ; RV64IF-NEXT: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[COPY1]](s32)
+ ; RV64IF-NEXT: [[C:%[0-9]+]]:_(s16) = G_FCONSTANT half 0xH3C00
+ ; RV64IF-NEXT: [[C1:%[0-9]+]]:_(s16) = G_FCONSTANT half 0xH4200
+ ; RV64IF-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $x2, implicit $x2
+ ; RV64IF-NEXT: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC]](s16)
+ ; RV64IF-NEXT: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[C]](s16)
+ ; RV64IF-NEXT: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC]](s16)
+ ; RV64IF-NEXT: [[ANYEXT3:%[0-9]+]]:_(s32) = G_ANYEXT [[C1]](s16)
+ ; RV64IF-NEXT: [[ANYEXT4:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC]](s16)
+ ; RV64IF-NEXT: [[ANYEXT5:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC1]](s16)
+ ; RV64IF-NEXT: [[ANYEXT6:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC1]](s16)
+ ; RV64IF-NEXT: [[ANYEXT7:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC1]](s16)
+ ; RV64IF-NEXT: [[ANYEXT8:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC]](s16)
+ ; RV64IF-NEXT: $f10_f = COPY [[ANYEXT]](s32)
+ ; RV64IF-NEXT: $f11_f = COPY [[ANYEXT1]](s32)
+ ; RV64IF-NEXT: $f12_f = COPY [[ANYEXT2]](s32)
+ ; RV64IF-NEXT: $f13_f = COPY [[ANYEXT3]](s32)
+ ; RV64IF-NEXT: $f14_f = COPY [[ANYEXT4]](s32)
+ ; RV64IF-NEXT: $f15_f = COPY [[ANYEXT5]](s32)
+ ; RV64IF-NEXT: $f16_f = COPY [[ANYEXT6]](s32)
+ ; RV64IF-NEXT: $f17_f = COPY [[ANYEXT7]](s32)
+ ; RV64IF-NEXT: [[ANYEXT9:%[0-9]+]]:_(s64) = G_ANYEXT [[ANYEXT8]](s32)
+ ; RV64IF-NEXT: $x10 = COPY [[ANYEXT9]](s64)
+ ; RV64IF-NEXT: PseudoCALL target-flags(riscv-call) @callee_half_return_stack2, csr_ilp32f_lp64f, implicit-def $x1, implicit $f10_f, implicit $f11_f, implicit $f12_f, implicit $f13_f, implicit $f14_f, implicit $f15_f, implicit $f16_f, implicit $f17_f, implicit $x10, implicit-def $f10_f
+ ; RV64IF-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $x2, implicit $x2
+ ; RV64IF-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY $f10_f
+ ; RV64IF-NEXT: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[COPY2]](s32)
+ ; RV64IF-NEXT: [[ANYEXT10:%[0-9]+]]:_(s32) = G_ANYEXT [[TRUNC2]](s16)
+ ; RV64IF-NEXT: $f10_f = COPY [[ANYEXT10]](s32)
+ ; RV64IF-NEXT: PseudoRET implicit $f10_f
+ ;
+ ; RV64IZFH-LABEL: name: caller_half_return_stack2
+ ; RV64IZFH: bb.1 (%ir-block.0):
+ ; RV64IZFH-NEXT: liveins: $f10_h, $f11_h
+ ; RV64IZFH-NEXT: {{ $}}
+ ; RV64IZFH-NEXT: [[COPY:%[0-9]+]]:_(s16) = COPY $f10_h
+ ; RV64IZFH-NEXT: [[COPY1:%[0-9]+]]:_(s16) = COPY $f11_h
+ ; RV64IZFH-NEXT: [[C:%[0-9]+]]:_(s16) = G_FCONSTANT half 0xH3C00
+ ; RV64IZFH-NEXT: [[C1:%[0-9]+]]:_(s16) = G_FCONSTANT half 0xH4200
+ ; RV64IZFH-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $x2, implicit $x2
+ ; RV64IZFH-NEXT: $f10_h = COPY [[COPY]](s16)
+ ; RV64IZFH-NEXT: $f11_h = COPY [[C]](s16)
+ ; RV64IZFH-NEXT: $f12_h = COPY [[COPY]](s16)
+ ; RV64IZFH-NEXT: $f13_h = COPY [[C1]](s16)
+ ; RV64IZFH-NEXT: $f14_h = COPY [[COPY]](s16)
+ ; RV64IZFH-NEXT: $f15_h = COPY [[COPY1]](s16)
+ ; RV64IZFH-NEXT: $f16_h = COPY [[COPY1]](s16)
+ ; RV64IZFH-NEXT: $f17_h = COPY [[COPY1]](s16)
+ ; RV64IZFH-NEXT: [[ANYEXT:%[0-9]+]]:_(s64) = G_ANYEXT [[COPY]](s16)
+ ; RV64IZFH-NEXT: $x10 = COPY [[ANYEXT]](s64)
+ ; RV64IZFH-NEXT: PseudoCALL target-flags(riscv-call) @callee_half_return_stack2, csr_ilp32f_lp64f, implicit-def $x1, implicit $f10_h, implicit $f11_h, implicit $f12_h, implicit $f13_h, implicit $f14_h, implicit $f15_h, implicit $f16_h, implicit $f17_h, implicit $x10, implicit-def $f10_h
+ ; RV64IZFH-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $x2, implicit $x2
+ ; RV64IZFH-NEXT: [[COPY2:%[0-9]+]]:_(s16) = COPY $f10_h
+ ; RV64IZFH-NEXT: $f10_h = COPY [[COPY2]](s16)
+ ; RV64IZFH-NEXT: PseudoRET implicit $f10_h
%z = call half @callee_half_return_stack2(half %x, half 1.0, half %x, half 3.0, half %x, half %y, half %y, half %y, half %x)
ret half %z
}
>From 4b6d1eb1d1cce99fb0e86c58f4481e6ce9d71db4 Mon Sep 17 00:00:00 2001
From: Yingwei Zheng <dtcxzyw2333 at gmail.com>
Date: Mon, 10 Jun 2024 23:08:50 +0800
Subject: [PATCH 2/2] [GISel][RISCV] Format code. NFC.
---
llvm/lib/Target/RISCV/GISel/RISCVCallLowering.cpp | 10 ++++------
1 file changed, 4 insertions(+), 6 deletions(-)
diff --git a/llvm/lib/Target/RISCV/GISel/RISCVCallLowering.cpp b/llvm/lib/Target/RISCV/GISel/RISCVCallLowering.cpp
index b9bcfd8fb79a6..3267821e7e081 100644
--- a/llvm/lib/Target/RISCV/GISel/RISCVCallLowering.cpp
+++ b/llvm/lib/Target/RISCV/GISel/RISCVCallLowering.cpp
@@ -106,12 +106,10 @@ struct RISCVOutgoingValueHandler : public CallLowering::OutgoingValueHandler {
// anyextend before copying.
if ((VA.getLocVT() == MVT::i64 && VA.getValVT() == MVT::f32) ||
((VA.getLocVT() == MVT::i32 || VA.getLocVT() == MVT::i64) &&
- VA.getValVT() == MVT::f16))
- ValVReg =
- MIRBuilder
- .buildAnyExt(LLT::scalar(VA.getLocVT().getScalarSizeInBits()),
- ValVReg)
- .getReg(0);
+ VA.getValVT() == MVT::f16)) {
+ LLT DstTy = LLT::scalar(VA.getLocVT().getScalarSizeInBits());
+ ValVReg = MIRBuilder.buildAnyExt(DstTy, ValVReg).getReg(0);
+ }
Register ExtReg = extendRegister(ValVReg, VA);
MIRBuilder.buildCopy(PhysReg, ExtReg);
More information about the llvm-commits
mailing list