llvm-project/llvm/test/CodeGen/RISCV/frm-dependency.ll

125 lines
5.5 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
; RUN: llc -mtriple=riscv32 -mattr=+f,+d -stop-after=finalize-isel < %s \
; RUN: | FileCheck -check-prefixes=RV32IF %s
; RUN: llc -mtriple=riscv64 -mattr=+f,+d -stop-after=finalize-isel < %s \
; RUN: | FileCheck -check-prefixes=RV64IF %s
; Make sure an implicit FRM dependency is added to instructions with dynamic
; rounding.
define float @fadd_s(float %a, float %b) nounwind {
; RV32IF-LABEL: name: fadd_s
; RV32IF: bb.0 (%ir-block.0):
; RV32IF-NEXT: liveins: $x10, $x11
; RV32IF-NEXT: {{ $}}
; RV32IF-NEXT: [[COPY:%[0-9]+]]:gpr = COPY $x11
; RV32IF-NEXT: [[COPY1:%[0-9]+]]:gpr = COPY $x10
; RV32IF-NEXT: [[FMV_W_X:%[0-9]+]]:fpr32 = FMV_W_X [[COPY]]
; RV32IF-NEXT: [[FMV_W_X1:%[0-9]+]]:fpr32 = FMV_W_X [[COPY1]]
; RV32IF-NEXT: %4:fpr32 = nofpexcept FADD_S killed [[FMV_W_X1]], killed [[FMV_W_X]], 7, implicit $frm
; RV32IF-NEXT: [[FMV_X_W:%[0-9]+]]:gpr = FMV_X_W killed %4
; RV32IF-NEXT: $x10 = COPY [[FMV_X_W]]
; RV32IF-NEXT: PseudoRET implicit $x10
; RV64IF-LABEL: name: fadd_s
; RV64IF: bb.0 (%ir-block.0):
; RV64IF-NEXT: liveins: $x10, $x11
; RV64IF-NEXT: {{ $}}
; RV64IF-NEXT: [[COPY:%[0-9]+]]:gpr = COPY $x11
; RV64IF-NEXT: [[COPY1:%[0-9]+]]:gpr = COPY $x10
; RV64IF-NEXT: [[FMV_W_X:%[0-9]+]]:fpr32 = FMV_W_X [[COPY]]
; RV64IF-NEXT: [[FMV_W_X1:%[0-9]+]]:fpr32 = FMV_W_X [[COPY1]]
; RV64IF-NEXT: %4:fpr32 = nofpexcept FADD_S killed [[FMV_W_X1]], killed [[FMV_W_X]], 7, implicit $frm
; RV64IF-NEXT: [[FMV_X_W:%[0-9]+]]:gpr = FMV_X_W killed %4
; RV64IF-NEXT: $x10 = COPY [[FMV_X_W]]
; RV64IF-NEXT: PseudoRET implicit $x10
%1 = fadd float %a, %b
ret float %1
}
declare float @llvm.fma.f32(float, float, float)
define float @fmadd_s(float %a, float %b, float %c) nounwind {
; RV32IF-LABEL: name: fmadd_s
; RV32IF: bb.0 (%ir-block.0):
; RV32IF-NEXT: liveins: $x10, $x11, $x12
; RV32IF-NEXT: {{ $}}
; RV32IF-NEXT: [[COPY:%[0-9]+]]:gpr = COPY $x12
; RV32IF-NEXT: [[COPY1:%[0-9]+]]:gpr = COPY $x11
; RV32IF-NEXT: [[COPY2:%[0-9]+]]:gpr = COPY $x10
; RV32IF-NEXT: [[FMV_W_X:%[0-9]+]]:fpr32 = FMV_W_X [[COPY]]
; RV32IF-NEXT: [[FMV_W_X1:%[0-9]+]]:fpr32 = FMV_W_X [[COPY1]]
; RV32IF-NEXT: [[FMV_W_X2:%[0-9]+]]:fpr32 = FMV_W_X [[COPY2]]
; RV32IF-NEXT: %6:fpr32 = nofpexcept FMADD_S killed [[FMV_W_X2]], killed [[FMV_W_X1]], killed [[FMV_W_X]], 7, implicit $frm
; RV32IF-NEXT: [[FMV_X_W:%[0-9]+]]:gpr = FMV_X_W killed %6
; RV32IF-NEXT: $x10 = COPY [[FMV_X_W]]
; RV32IF-NEXT: PseudoRET implicit $x10
; RV64IF-LABEL: name: fmadd_s
; RV64IF: bb.0 (%ir-block.0):
; RV64IF-NEXT: liveins: $x10, $x11, $x12
; RV64IF-NEXT: {{ $}}
; RV64IF-NEXT: [[COPY:%[0-9]+]]:gpr = COPY $x12
; RV64IF-NEXT: [[COPY1:%[0-9]+]]:gpr = COPY $x11
; RV64IF-NEXT: [[COPY2:%[0-9]+]]:gpr = COPY $x10
; RV64IF-NEXT: [[FMV_W_X:%[0-9]+]]:fpr32 = FMV_W_X [[COPY]]
; RV64IF-NEXT: [[FMV_W_X1:%[0-9]+]]:fpr32 = FMV_W_X [[COPY1]]
; RV64IF-NEXT: [[FMV_W_X2:%[0-9]+]]:fpr32 = FMV_W_X [[COPY2]]
; RV64IF-NEXT: %6:fpr32 = nofpexcept FMADD_S killed [[FMV_W_X2]], killed [[FMV_W_X1]], killed [[FMV_W_X]], 7, implicit $frm
; RV64IF-NEXT: [[FMV_X_W:%[0-9]+]]:gpr = FMV_X_W killed %6
; RV64IF-NEXT: $x10 = COPY [[FMV_X_W]]
; RV64IF-NEXT: PseudoRET implicit $x10
%1 = call float @llvm.fma.f32(float %a, float %b, float %c)
ret float %1
}
; This uses rtz instead of dyn rounding mode so shouldn't have an FRM dependncy.
define i32 @fcvt_w_s(float %a) nounwind {
; RV32IF-LABEL: name: fcvt_w_s
; RV32IF: bb.0 (%ir-block.0):
; RV32IF-NEXT: liveins: $x10
; RV32IF-NEXT: {{ $}}
; RV32IF-NEXT: [[COPY:%[0-9]+]]:gpr = COPY $x10
; RV32IF-NEXT: [[FMV_W_X:%[0-9]+]]:fpr32 = FMV_W_X [[COPY]]
; RV32IF-NEXT: %2:gpr = nofpexcept FCVT_W_S killed [[FMV_W_X]], 1
; RV32IF-NEXT: $x10 = COPY %2
; RV32IF-NEXT: PseudoRET implicit $x10
; RV64IF-LABEL: name: fcvt_w_s
; RV64IF: bb.0 (%ir-block.0):
; RV64IF-NEXT: liveins: $x10
; RV64IF-NEXT: {{ $}}
; RV64IF-NEXT: [[COPY:%[0-9]+]]:gpr = COPY $x10
; RV64IF-NEXT: [[FMV_W_X:%[0-9]+]]:fpr32 = FMV_W_X [[COPY]]
; RV64IF-NEXT: %2:gpr = nofpexcept FCVT_W_S killed [[FMV_W_X]], 1
; RV64IF-NEXT: $x10 = COPY %2
; RV64IF-NEXT: PseudoRET implicit $x10
%1 = fptosi float %a to i32
ret i32 %1
}
; This doesn't use a rounding mode since i32 can be represented exactly as a
; double.
define double @fcvt_d_w(i32 %a) nounwind {
; RV32IF-LABEL: name: fcvt_d_w
; RV32IF: bb.0 (%ir-block.0):
; RV32IF-NEXT: liveins: $x10
; RV32IF-NEXT: {{ $}}
; RV32IF-NEXT: [[COPY:%[0-9]+]]:gpr = COPY $x10
; RV32IF-NEXT: %1:fpr64 = nofpexcept FCVT_D_W [[COPY]]
; RV32IF-NEXT: FSD killed %1, %stack.0, 0 :: (store (s64) into %stack.0)
; RV32IF-NEXT: [[LW:%[0-9]+]]:gpr = LW %stack.0, 0 :: (load (s32) from %stack.0, align 8)
; RV32IF-NEXT: [[LW1:%[0-9]+]]:gpr = LW %stack.0, 4 :: (load (s32) from %stack.0 + 4, basealign 8)
; RV32IF-NEXT: $x10 = COPY [[LW]]
; RV32IF-NEXT: $x11 = COPY [[LW1]]
; RV32IF-NEXT: PseudoRET implicit $x10, implicit $x11
; RV64IF-LABEL: name: fcvt_d_w
; RV64IF: bb.0 (%ir-block.0):
; RV64IF-NEXT: liveins: $x10
; RV64IF-NEXT: {{ $}}
; RV64IF-NEXT: [[COPY:%[0-9]+]]:gpr = COPY $x10
; RV64IF-NEXT: %1:fpr64 = nofpexcept FCVT_D_W [[COPY]]
; RV64IF-NEXT: [[FMV_X_D:%[0-9]+]]:gpr = FMV_X_D killed %1
; RV64IF-NEXT: $x10 = COPY [[FMV_X_D]]
; RV64IF-NEXT: PseudoRET implicit $x10
%1 = sitofp i32 %a to double
ret double %1
}