[llvm] [RISCV][GISel] Use libcalls for rint, nearbyint, trunc, round, and roundeven intrinsics. (PR #108779)
Craig Topper via llvm-commits
llvm-commits at lists.llvm.org
Tue Sep 17 23:42:13 PDT 2024
================
@@ -0,0 +1,328 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
+# RUN: llc -mtriple=riscv32 -mattr=+d -run-pass=legalizer %s -o - \
+# RUN: | FileCheck %s
+# RUN: llc -mtriple=riscv64 -mattr=+d -run-pass=legalizer %s -o - \
+# RUN: | FileCheck %s
+
+---
+name: ceil_f32
+body: |
+ bb.1:
+ liveins: $f10_f
+
+ ; CHECK-LABEL: name: ceil_f32
+ ; CHECK: liveins: $f10_f
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $f10_f
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $x2, implicit $x2
+ ; CHECK-NEXT: $f10_f = COPY [[COPY]](s32)
+ ; CHECK-NEXT: PseudoCALL target-flags(riscv-call) &ceilf, csr_ilp32d_lp64d, implicit-def $x1, implicit $f10_f, implicit-def $f10_f
+ ; CHECK-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $x2, implicit $x2
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $f10_f
+ ; CHECK-NEXT: $f10_f = COPY [[COPY1]](s32)
+ ; CHECK-NEXT: PseudoRET implicit $f10_f
+ %0:_(s32) = COPY $f10_f
+ %1:_(s32) = G_FCEIL %0
+ $f10_f = COPY %1(s32)
+ PseudoRET implicit $f10_f
+
+...
+---
+name: floor_f32
+body: |
+ bb.1:
+ liveins: $f10_f
+
+ ; CHECK-LABEL: name: floor_f32
+ ; CHECK: liveins: $f10_f
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $f10_f
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $x2, implicit $x2
+ ; CHECK-NEXT: $f10_f = COPY [[COPY]](s32)
+ ; CHECK-NEXT: PseudoCALL target-flags(riscv-call) &floorf, csr_ilp32d_lp64d, implicit-def $x1, implicit $f10_f, implicit-def $f10_f
+ ; CHECK-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $x2, implicit $x2
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $f10_f
+ ; CHECK-NEXT: $f10_f = COPY [[COPY1]](s32)
+ ; CHECK-NEXT: PseudoRET implicit $f10_f
+ %0:_(s32) = COPY $f10_f
+ %1:_(s32) = G_FFLOOR %0
+ $f10_f = COPY %1(s32)
+ PseudoRET implicit $f10_f
+
+...
+---
+name: trunc_f32
+body: |
+ bb.1:
+ liveins: $f10_f
+
+ ; CHECK-LABEL: name: trunc_f32
+ ; CHECK: liveins: $f10_f
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $f10_f
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $x2, implicit $x2
+ ; CHECK-NEXT: $f10_f = COPY [[COPY]](s32)
+ ; CHECK-NEXT: PseudoCALL target-flags(riscv-call) &truncf, csr_ilp32d_lp64d, implicit-def $x1, implicit $f10_f, implicit-def $f10_f
+ ; CHECK-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $x2, implicit $x2
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $f10_f
+ ; CHECK-NEXT: $f10_f = COPY [[COPY1]](s32)
+ ; CHECK-NEXT: PseudoRET implicit $f10_f
+ %0:_(s32) = COPY $f10_f
+ %1:_(s32) = G_INTRINSIC_TRUNC %0
+ $f10_f = COPY %1(s32)
+ PseudoRET implicit $f10_f
+
+...
+---
+name: rint_f32
+body: |
+ bb.1:
+ liveins: $f10_f
+
+ ; CHECK-LABEL: name: rint_f32
+ ; CHECK: liveins: $f10_f
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $f10_f
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $x2, implicit $x2
+ ; CHECK-NEXT: $f10_f = COPY [[COPY]](s32)
+ ; CHECK-NEXT: PseudoCALL target-flags(riscv-call) &rintf, csr_ilp32d_lp64d, implicit-def $x1, implicit $f10_f, implicit-def $f10_f
+ ; CHECK-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $x2, implicit $x2
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $f10_f
+ ; CHECK-NEXT: $f10_f = COPY [[COPY1]](s32)
+ ; CHECK-NEXT: PseudoRET implicit $f10_f
+ %0:_(s32) = COPY $f10_f
+ %1:_(s32) = G_FRINT %0
+ $f10_f = COPY %1(s32)
+ PseudoRET implicit $f10_f
+
+...
+---
+name: nearbyint_f32
+body: |
+ bb.1:
+ liveins: $f10_f
+
+ ; CHECK-LABEL: name: nearbyint_f32
+ ; CHECK: liveins: $f10_f
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $f10_f
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $x2, implicit $x2
+ ; CHECK-NEXT: $f10_f = COPY [[COPY]](s32)
+ ; CHECK-NEXT: PseudoCALL target-flags(riscv-call) &nearbyintf, csr_ilp32d_lp64d, implicit-def $x1, implicit $f10_f, implicit-def $f10_f
+ ; CHECK-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $x2, implicit $x2
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $f10_f
+ ; CHECK-NEXT: $f10_f = COPY [[COPY1]](s32)
+ ; CHECK-NEXT: PseudoRET implicit $f10_f
+ %0:_(s32) = COPY $f10_f
+ %1:_(s32) = G_FNEARBYINT %0
+ $f10_f = COPY %1(s32)
+ PseudoRET implicit $f10_f
+
+...
+---
+name: round_f32
+body: |
+ bb.1:
+ liveins: $f10_f
+
+ ; CHECK-LABEL: name: round_f32
+ ; CHECK: liveins: $f10_f
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $f10_f
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $x2, implicit $x2
+ ; CHECK-NEXT: $f10_f = COPY [[COPY]](s32)
+ ; CHECK-NEXT: PseudoCALL target-flags(riscv-call) &roundf, csr_ilp32d_lp64d, implicit-def $x1, implicit $f10_f, implicit-def $f10_f
+ ; CHECK-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $x2, implicit $x2
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $f10_f
+ ; CHECK-NEXT: $f10_f = COPY [[COPY1]](s32)
+ ; CHECK-NEXT: PseudoRET implicit $f10_f
+ %0:_(s32) = COPY $f10_f
+ %1:_(s32) = G_INTRINSIC_ROUND %0
+ $f10_f = COPY %1(s32)
+ PseudoRET implicit $f10_f
+
+...
+---
+name: roundeven_f32
+body: |
+ bb.1:
+ liveins: $f10_f
+
+ ; CHECK-LABEL: name: roundeven_f32
+ ; CHECK: liveins: $f10_f
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $f10_f
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $x2, implicit $x2
+ ; CHECK-NEXT: $f10_f = COPY [[COPY]](s32)
+ ; CHECK-NEXT: PseudoCALL target-flags(riscv-call) &roundevenf, csr_ilp32d_lp64d, implicit-def $x1, implicit $f10_f, implicit-def $f10_f
+ ; CHECK-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $x2, implicit $x2
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $f10_f
+ ; CHECK-NEXT: $f10_f = COPY [[COPY1]](s32)
+ ; CHECK-NEXT: PseudoRET implicit $f10_f
+ %0:_(s32) = COPY $f10_f
+ %1:_(s32) = G_INTRINSIC_ROUNDEVEN %0
+ $f10_f = COPY %1(s32)
+ PseudoRET implicit $f10_f
+
+...
+---
+name: ceil_f64
+body: |
+ bb.1:
+ liveins: $f10_d
+
+ ; CHECK-LABEL: name: ceil_f64
+ ; CHECK: liveins: $f10_d
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s64) = COPY $f10_d
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $x2, implicit $x2
+ ; CHECK-NEXT: $f10_d = COPY [[COPY]](s64)
+ ; CHECK-NEXT: PseudoCALL target-flags(riscv-call) &ceil, csr_ilp32d_lp64d, implicit-def $x1, implicit $f10_d, implicit-def $f10_d
+ ; CHECK-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $x2, implicit $x2
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s64) = COPY $f10_d
+ ; CHECK-NEXT: $f10_d = COPY [[COPY1]](s64)
+ ; CHECK-NEXT: PseudoRET implicit $f10_d
+ %0:_(s64) = COPY $f10_d
+ %1:_(s64) = G_FCEIL %0
+ $f10_d = COPY %1(s64)
+ PseudoRET implicit $f10_d
+
+...
+---
+name: floor_f64
+body: |
+ bb.1:
+ liveins: $f10_d
+
+ ; CHECK-LABEL: name: floor_f64
+ ; CHECK: liveins: $f10_d
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s64) = COPY $f10_d
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $x2, implicit $x2
+ ; CHECK-NEXT: $f10_d = COPY [[COPY]](s64)
+ ; CHECK-NEXT: PseudoCALL target-flags(riscv-call) &floor, csr_ilp32d_lp64d, implicit-def $x1, implicit $f10_d, implicit-def $f10_d
+ ; CHECK-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $x2, implicit $x2
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s64) = COPY $f10_d
+ ; CHECK-NEXT: $f10_d = COPY [[COPY1]](s64)
+ ; CHECK-NEXT: PseudoRET implicit $f10_d
+ %0:_(s64) = COPY $f10_d
+ %1:_(s64) = G_FFLOOR %0
+ $f10_d = COPY %1(s64)
+ PseudoRET implicit $f10_d
+
+...
+---
+name: trunc_f64
+body: |
+ bb.1:
+ liveins: $f10_d
+
+ ; CHECK-LABEL: name: trunc_f64
+ ; CHECK: liveins: $f10_d
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s64) = COPY $f10_d
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $x2, implicit $x2
+ ; CHECK-NEXT: $f10_d = COPY [[COPY]](s64)
+ ; CHECK-NEXT: PseudoCALL target-flags(riscv-call) &trunc, csr_ilp32d_lp64d, implicit-def $x1, implicit $f10_d, implicit-def $f10_d
+ ; CHECK-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $x2, implicit $x2
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s64) = COPY $f10_d
+ ; CHECK-NEXT: $f10_d = COPY [[COPY1]](s64)
+ ; CHECK-NEXT: PseudoRET implicit $f10_d
+ %0:_(s64) = COPY $f10_d
+ %1:_(s64) = G_INTRINSIC_TRUNC %0
+ $f10_d = COPY %1(s64)
+ PseudoRET implicit $f10_d
+
+...
+---
+name: rint_f64
+body: |
+ bb.1:
+ liveins: $f10_d
+
+ ; CHECK-LABEL: name: rint_f64
+ ; CHECK: liveins: $f10_d
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s64) = COPY $f10_d
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $x2, implicit $x2
+ ; CHECK-NEXT: $f10_d = COPY [[COPY]](s64)
+ ; CHECK-NEXT: PseudoCALL target-flags(riscv-call) &rint, csr_ilp32d_lp64d, implicit-def $x1, implicit $f10_d, implicit-def $f10_d
+ ; CHECK-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $x2, implicit $x2
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s64) = COPY $f10_d
+ ; CHECK-NEXT: $f10_d = COPY [[COPY1]](s64)
+ ; CHECK-NEXT: PseudoRET implicit $f10_d
+ %0:_(s64) = COPY $f10_d
+ %1:_(s64) = G_FRINT %0
+ $f10_d = COPY %1(s64)
+ PseudoRET implicit $f10_d
+
+...
+---
+name: nearbyint_f64
+body: |
+ bb.1:
+ liveins: $f10_d
+
+ ; CHECK-LABEL: name: nearbyint_f64
+ ; CHECK: liveins: $f10_d
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s64) = COPY $f10_d
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $x2, implicit $x2
+ ; CHECK-NEXT: $f10_d = COPY [[COPY]](s64)
+ ; CHECK-NEXT: PseudoCALL target-flags(riscv-call) &nearbyint, csr_ilp32d_lp64d, implicit-def $x1, implicit $f10_d, implicit-def $f10_d
+ ; CHECK-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $x2, implicit $x2
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s64) = COPY $f10_d
+ ; CHECK-NEXT: $f10_d = COPY [[COPY1]](s64)
+ ; CHECK-NEXT: PseudoRET implicit $f10_d
+ %0:_(s64) = COPY $f10_d
+ %1:_(s64) = G_FNEARBYINT %0
+ $f10_d = COPY %1(s64)
+ PseudoRET implicit $f10_d
+
+...
+---
+name: round_f64
+body: |
+ bb.1:
+ liveins: $f10_d
+
+ ; CHECK-LABEL: name: round_f64
+ ; CHECK: liveins: $f10_d
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s64) = COPY $f10_d
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $x2, implicit $x2
+ ; CHECK-NEXT: $f10_d = COPY [[COPY]](s64)
+ ; CHECK-NEXT: PseudoCALL target-flags(riscv-call) &round, csr_ilp32d_lp64d, implicit-def $x1, implicit $f10_d, implicit-def $f10_d
+ ; CHECK-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $x2, implicit $x2
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s64) = COPY $f10_d
+ ; CHECK-NEXT: $f10_d = COPY [[COPY1]](s64)
+ ; CHECK-NEXT: PseudoRET implicit $f10_d
+ %0:_(s64) = COPY $f10_d
+ %1:_(s64) = G_INTRINSIC_ROUND %0
+ $f10_d = COPY %1(s64)
+ PseudoRET implicit $f10_d
+
+...
+---
----------------
topperc wrote:
Agreed. I'll commit this as is and then try to replace with an IR test as a followup.
https://github.com/llvm/llvm-project/pull/108779
More information about the llvm-commits
mailing list