llvm-project/llvm/test/CodeGen/RISCV/mul.ll

565 lines
14 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv32 -verify-machineinstrs < %s \
; RUN: | FileCheck -check-prefix=RV32I %s
; RUN: llc -mtriple=riscv32 -mattr=+m -verify-machineinstrs < %s \
; RUN: | FileCheck -check-prefix=RV32IM %s
; RUN: llc -mtriple=riscv64 -verify-machineinstrs < %s \
; RUN: | FileCheck -check-prefix=RV64I %s
; RUN: llc -mtriple=riscv64 -mattr=+m -verify-machineinstrs < %s \
; RUN: | FileCheck -check-prefix=RV64IM %s
define signext i32 @square(i32 %a) nounwind {
; RV32I-LABEL: square:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp)
; RV32I-NEXT: mv a1, a0
; RV32I-NEXT: call __mulsi3
; RV32I-NEXT: lw ra, 12(sp)
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV32IM-LABEL: square:
; RV32IM: # %bb.0:
; RV32IM-NEXT: mul a0, a0, a0
; RV32IM-NEXT: ret
;
; RV64I-LABEL: square:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp)
; RV64I-NEXT: mv a1, a0
; RV64I-NEXT: call __muldi3
; RV64I-NEXT: sext.w a0, a0
; RV64I-NEXT: ld ra, 8(sp)
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
;
; RV64IM-LABEL: square:
; RV64IM: # %bb.0:
; RV64IM-NEXT: mulw a0, a0, a0
; RV64IM-NEXT: ret
%1 = mul i32 %a, %a
ret i32 %1
}
define signext i32 @mul(i32 %a, i32 %b) nounwind {
; RV32I-LABEL: mul:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp)
; RV32I-NEXT: call __mulsi3
; RV32I-NEXT: lw ra, 12(sp)
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV32IM-LABEL: mul:
; RV32IM: # %bb.0:
; RV32IM-NEXT: mul a0, a0, a1
; RV32IM-NEXT: ret
;
; RV64I-LABEL: mul:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp)
; RV64I-NEXT: call __muldi3
; RV64I-NEXT: sext.w a0, a0
; RV64I-NEXT: ld ra, 8(sp)
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
;
; RV64IM-LABEL: mul:
; RV64IM: # %bb.0:
; RV64IM-NEXT: mulw a0, a0, a1
; RV64IM-NEXT: ret
%1 = mul i32 %a, %b
ret i32 %1
}
define signext i32 @mul_constant(i32 %a) nounwind {
; RV32I-LABEL: mul_constant:
; RV32I: # %bb.0:
; RV32I-NEXT: slli a1, a0, 2
; RV32I-NEXT: add a0, a1, a0
; RV32I-NEXT: ret
;
; RV32IM-LABEL: mul_constant:
; RV32IM: # %bb.0:
; RV32IM-NEXT: addi a1, zero, 5
; RV32IM-NEXT: mul a0, a0, a1
; RV32IM-NEXT: ret
;
; RV64I-LABEL: mul_constant:
; RV64I: # %bb.0:
; RV64I-NEXT: slli a1, a0, 2
; RV64I-NEXT: addw a0, a1, a0
; RV64I-NEXT: ret
;
; RV64IM-LABEL: mul_constant:
; RV64IM: # %bb.0:
; RV64IM-NEXT: slli a1, a0, 2
; RV64IM-NEXT: addw a0, a1, a0
; RV64IM-NEXT: ret
%1 = mul i32 %a, 5
ret i32 %1
}
define i32 @mul_pow2(i32 %a) nounwind {
; RV32I-LABEL: mul_pow2:
; RV32I: # %bb.0:
; RV32I-NEXT: slli a0, a0, 3
; RV32I-NEXT: ret
;
; RV32IM-LABEL: mul_pow2:
; RV32IM: # %bb.0:
; RV32IM-NEXT: slli a0, a0, 3
; RV32IM-NEXT: ret
;
; RV64I-LABEL: mul_pow2:
; RV64I: # %bb.0:
; RV64I-NEXT: slli a0, a0, 3
; RV64I-NEXT: ret
;
; RV64IM-LABEL: mul_pow2:
; RV64IM: # %bb.0:
; RV64IM-NEXT: slli a0, a0, 3
; RV64IM-NEXT: ret
%1 = mul i32 %a, 8
ret i32 %1
}
define i64 @mul64(i64 %a, i64 %b) nounwind {
; RV32I-LABEL: mul64:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp)
; RV32I-NEXT: call __muldi3
; RV32I-NEXT: lw ra, 12(sp)
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV32IM-LABEL: mul64:
; RV32IM: # %bb.0:
; RV32IM-NEXT: mul a3, a0, a3
; RV32IM-NEXT: mulhu a4, a0, a2
; RV32IM-NEXT: add a3, a4, a3
; RV32IM-NEXT: mul a1, a1, a2
; RV32IM-NEXT: add a1, a3, a1
; RV32IM-NEXT: mul a0, a0, a2
; RV32IM-NEXT: ret
;
; RV64I-LABEL: mul64:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp)
; RV64I-NEXT: call __muldi3
; RV64I-NEXT: ld ra, 8(sp)
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
;
; RV64IM-LABEL: mul64:
; RV64IM: # %bb.0:
; RV64IM-NEXT: mul a0, a0, a1
; RV64IM-NEXT: ret
%1 = mul i64 %a, %b
ret i64 %1
}
define i64 @mul64_constant(i64 %a) nounwind {
; RV32I-LABEL: mul64_constant:
; RV32I: # %bb.0:
; RV32I-NEXT: slli a3, a0, 2
; RV32I-NEXT: add a2, a3, a0
; RV32I-NEXT: sltu a3, a2, a3
; RV32I-NEXT: srli a0, a0, 30
; RV32I-NEXT: slli a4, a1, 2
; RV32I-NEXT: or a0, a4, a0
; RV32I-NEXT: add a0, a0, a1
; RV32I-NEXT: add a1, a0, a3
; RV32I-NEXT: mv a0, a2
; RV32I-NEXT: ret
;
; RV32IM-LABEL: mul64_constant:
; RV32IM: # %bb.0:
; RV32IM-NEXT: addi a2, zero, 5
; RV32IM-NEXT: mul a1, a1, a2
; RV32IM-NEXT: mulhu a3, a0, a2
; RV32IM-NEXT: add a1, a3, a1
; RV32IM-NEXT: mul a0, a0, a2
; RV32IM-NEXT: ret
;
; RV64I-LABEL: mul64_constant:
; RV64I: # %bb.0:
; RV64I-NEXT: slli a1, a0, 2
; RV64I-NEXT: add a0, a1, a0
; RV64I-NEXT: ret
;
; RV64IM-LABEL: mul64_constant:
; RV64IM: # %bb.0:
; RV64IM-NEXT: slli a1, a0, 2
; RV64IM-NEXT: add a0, a1, a0
; RV64IM-NEXT: ret
%1 = mul i64 %a, 5
ret i64 %1
}
define i32 @mulhs(i32 %a, i32 %b) nounwind {
; RV32I-LABEL: mulhs:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp)
; RV32I-NEXT: mv a2, a1
; RV32I-NEXT: srai a1, a0, 31
; RV32I-NEXT: srai a3, a2, 31
; RV32I-NEXT: call __muldi3
; RV32I-NEXT: mv a0, a1
; RV32I-NEXT: lw ra, 12(sp)
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV32IM-LABEL: mulhs:
; RV32IM: # %bb.0:
; RV32IM-NEXT: mulh a0, a0, a1
; RV32IM-NEXT: ret
;
; RV64I-LABEL: mulhs:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp)
; RV64I-NEXT: sext.w a0, a0
; RV64I-NEXT: sext.w a1, a1
; RV64I-NEXT: call __muldi3
; RV64I-NEXT: srli a0, a0, 32
; RV64I-NEXT: ld ra, 8(sp)
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
;
; RV64IM-LABEL: mulhs:
; RV64IM: # %bb.0:
; RV64IM-NEXT: sext.w a0, a0
; RV64IM-NEXT: sext.w a1, a1
; RV64IM-NEXT: mul a0, a0, a1
; RV64IM-NEXT: srli a0, a0, 32
; RV64IM-NEXT: ret
%1 = sext i32 %a to i64
%2 = sext i32 %b to i64
%3 = mul i64 %1, %2
%4 = lshr i64 %3, 32
%5 = trunc i64 %4 to i32
ret i32 %5
}
define zeroext i32 @mulhu(i32 zeroext %a, i32 zeroext %b) nounwind {
; RV32I-LABEL: mulhu:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp)
; RV32I-NEXT: mv a2, a1
; RV32I-NEXT: mv a1, zero
; RV32I-NEXT: mv a3, zero
; RV32I-NEXT: call __muldi3
; RV32I-NEXT: mv a0, a1
; RV32I-NEXT: lw ra, 12(sp)
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV32IM-LABEL: mulhu:
; RV32IM: # %bb.0:
; RV32IM-NEXT: mulhu a0, a0, a1
; RV32IM-NEXT: ret
;
; RV64I-LABEL: mulhu:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp)
; RV64I-NEXT: call __muldi3
; RV64I-NEXT: srli a0, a0, 32
; RV64I-NEXT: ld ra, 8(sp)
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
;
; RV64IM-LABEL: mulhu:
; RV64IM: # %bb.0:
; RV64IM-NEXT: mul a0, a0, a1
; RV64IM-NEXT: srli a0, a0, 32
; RV64IM-NEXT: ret
%1 = zext i32 %a to i64
%2 = zext i32 %b to i64
%3 = mul i64 %1, %2
%4 = lshr i64 %3, 32
%5 = trunc i64 %4 to i32
ret i32 %5
}
define i32 @muli32_p65(i32 %a) nounwind {
; RV32I-LABEL: muli32_p65:
; RV32I: # %bb.0:
; RV32I-NEXT: slli a1, a0, 6
; RV32I-NEXT: add a0, a1, a0
; RV32I-NEXT: ret
;
; RV32IM-LABEL: muli32_p65:
; RV32IM: # %bb.0:
; RV32IM-NEXT: addi a1, zero, 65
; RV32IM-NEXT: mul a0, a0, a1
; RV32IM-NEXT: ret
;
; RV64I-LABEL: muli32_p65:
; RV64I: # %bb.0:
; RV64I-NEXT: slli a1, a0, 6
; RV64I-NEXT: addw a0, a1, a0
; RV64I-NEXT: ret
;
; RV64IM-LABEL: muli32_p65:
; RV64IM: # %bb.0:
; RV64IM-NEXT: slli a1, a0, 6
; RV64IM-NEXT: addw a0, a1, a0
; RV64IM-NEXT: ret
%1 = mul i32 %a, 65
ret i32 %1
}
define i32 @muli32_p63(i32 %a) nounwind {
; RV32I-LABEL: muli32_p63:
; RV32I: # %bb.0:
; RV32I-NEXT: slli a1, a0, 6
; RV32I-NEXT: sub a0, a1, a0
; RV32I-NEXT: ret
;
; RV32IM-LABEL: muli32_p63:
; RV32IM: # %bb.0:
; RV32IM-NEXT: addi a1, zero, 63
; RV32IM-NEXT: mul a0, a0, a1
; RV32IM-NEXT: ret
;
; RV64I-LABEL: muli32_p63:
; RV64I: # %bb.0:
; RV64I-NEXT: slli a1, a0, 6
; RV64I-NEXT: subw a0, a1, a0
; RV64I-NEXT: ret
;
; RV64IM-LABEL: muli32_p63:
; RV64IM: # %bb.0:
; RV64IM-NEXT: slli a1, a0, 6
; RV64IM-NEXT: subw a0, a1, a0
; RV64IM-NEXT: ret
%1 = mul i32 %a, 63
ret i32 %1
}
define i64 @muli64_p65(i64 %a) nounwind {
; RV32I-LABEL: muli64_p65:
; RV32I: # %bb.0:
; RV32I-NEXT: slli a3, a0, 6
; RV32I-NEXT: add a2, a3, a0
; RV32I-NEXT: sltu a3, a2, a3
; RV32I-NEXT: srli a0, a0, 26
; RV32I-NEXT: slli a4, a1, 6
; RV32I-NEXT: or a0, a4, a0
; RV32I-NEXT: add a0, a0, a1
; RV32I-NEXT: add a1, a0, a3
; RV32I-NEXT: mv a0, a2
; RV32I-NEXT: ret
;
; RV32IM-LABEL: muli64_p65:
; RV32IM: # %bb.0:
; RV32IM-NEXT: addi a2, zero, 65
; RV32IM-NEXT: mul a1, a1, a2
; RV32IM-NEXT: mulhu a3, a0, a2
; RV32IM-NEXT: add a1, a3, a1
; RV32IM-NEXT: mul a0, a0, a2
; RV32IM-NEXT: ret
;
; RV64I-LABEL: muli64_p65:
; RV64I: # %bb.0:
; RV64I-NEXT: slli a1, a0, 6
; RV64I-NEXT: add a0, a1, a0
; RV64I-NEXT: ret
;
; RV64IM-LABEL: muli64_p65:
; RV64IM: # %bb.0:
; RV64IM-NEXT: slli a1, a0, 6
; RV64IM-NEXT: add a0, a1, a0
; RV64IM-NEXT: ret
%1 = mul i64 %a, 65
ret i64 %1
}
define i64 @muli64_p63(i64 %a) nounwind {
; RV32I-LABEL: muli64_p63:
; RV32I: # %bb.0:
; RV32I-NEXT: slli a2, a0, 6
; RV32I-NEXT: sltu a3, a2, a0
; RV32I-NEXT: srli a4, a0, 26
; RV32I-NEXT: slli a5, a1, 6
; RV32I-NEXT: or a4, a5, a4
; RV32I-NEXT: sub a1, a4, a1
; RV32I-NEXT: sub a1, a1, a3
; RV32I-NEXT: sub a0, a2, a0
; RV32I-NEXT: ret
;
; RV32IM-LABEL: muli64_p63:
; RV32IM: # %bb.0:
; RV32IM-NEXT: addi a2, zero, 63
; RV32IM-NEXT: mul a1, a1, a2
; RV32IM-NEXT: mulhu a3, a0, a2
; RV32IM-NEXT: add a1, a3, a1
; RV32IM-NEXT: mul a0, a0, a2
; RV32IM-NEXT: ret
;
; RV64I-LABEL: muli64_p63:
; RV64I: # %bb.0:
; RV64I-NEXT: slli a1, a0, 6
; RV64I-NEXT: sub a0, a1, a0
; RV64I-NEXT: ret
;
; RV64IM-LABEL: muli64_p63:
; RV64IM: # %bb.0:
; RV64IM-NEXT: slli a1, a0, 6
; RV64IM-NEXT: sub a0, a1, a0
; RV64IM-NEXT: ret
%1 = mul i64 %a, 63
ret i64 %1
}
define i32 @muli32_m63(i32 %a) nounwind {
; RV32I-LABEL: muli32_m63:
; RV32I: # %bb.0:
; RV32I-NEXT: slli a1, a0, 6
; RV32I-NEXT: sub a0, a0, a1
; RV32I-NEXT: ret
;
; RV32IM-LABEL: muli32_m63:
; RV32IM: # %bb.0:
; RV32IM-NEXT: addi a1, zero, -63
; RV32IM-NEXT: mul a0, a0, a1
; RV32IM-NEXT: ret
;
; RV64I-LABEL: muli32_m63:
; RV64I: # %bb.0:
; RV64I-NEXT: slli a1, a0, 6
; RV64I-NEXT: subw a0, a0, a1
; RV64I-NEXT: ret
;
; RV64IM-LABEL: muli32_m63:
; RV64IM: # %bb.0:
; RV64IM-NEXT: slli a1, a0, 6
; RV64IM-NEXT: subw a0, a0, a1
; RV64IM-NEXT: ret
%1 = mul i32 %a, -63
ret i32 %1
}
define i32 @muli32_m65(i32 %a) nounwind {
; RV32I-LABEL: muli32_m65:
; RV32I: # %bb.0:
; RV32I-NEXT: slli a1, a0, 6
; RV32I-NEXT: add a0, a1, a0
; RV32I-NEXT: neg a0, a0
; RV32I-NEXT: ret
;
; RV32IM-LABEL: muli32_m65:
; RV32IM: # %bb.0:
; RV32IM-NEXT: addi a1, zero, -65
; RV32IM-NEXT: mul a0, a0, a1
; RV32IM-NEXT: ret
;
; RV64I-LABEL: muli32_m65:
; RV64I: # %bb.0:
; RV64I-NEXT: slli a1, a0, 6
; RV64I-NEXT: add a0, a1, a0
; RV64I-NEXT: negw a0, a0
; RV64I-NEXT: ret
;
; RV64IM-LABEL: muli32_m65:
; RV64IM: # %bb.0:
; RV64IM-NEXT: slli a1, a0, 6
; RV64IM-NEXT: add a0, a1, a0
; RV64IM-NEXT: negw a0, a0
; RV64IM-NEXT: ret
%1 = mul i32 %a, -65
ret i32 %1
}
define i64 @muli64_m63(i64 %a) nounwind {
; RV32I-LABEL: muli64_m63:
; RV32I: # %bb.0:
; RV32I-NEXT: slli a2, a0, 6
; RV32I-NEXT: sltu a3, a0, a2
; RV32I-NEXT: srli a4, a0, 26
; RV32I-NEXT: slli a5, a1, 6
; RV32I-NEXT: or a4, a5, a4
; RV32I-NEXT: sub a1, a1, a4
; RV32I-NEXT: sub a1, a1, a3
; RV32I-NEXT: sub a0, a0, a2
; RV32I-NEXT: ret
;
; RV32IM-LABEL: muli64_m63:
; RV32IM: # %bb.0:
; RV32IM-NEXT: addi a2, zero, -63
; RV32IM-NEXT: mul a1, a1, a2
; RV32IM-NEXT: mulhu a3, a0, a2
; RV32IM-NEXT: sub a3, a3, a0
; RV32IM-NEXT: add a1, a3, a1
; RV32IM-NEXT: mul a0, a0, a2
; RV32IM-NEXT: ret
;
; RV64I-LABEL: muli64_m63:
; RV64I: # %bb.0:
; RV64I-NEXT: slli a1, a0, 6
; RV64I-NEXT: sub a0, a0, a1
; RV64I-NEXT: ret
;
; RV64IM-LABEL: muli64_m63:
; RV64IM: # %bb.0:
; RV64IM-NEXT: slli a1, a0, 6
; RV64IM-NEXT: sub a0, a0, a1
; RV64IM-NEXT: ret
%1 = mul i64 %a, -63
ret i64 %1
}
define i64 @muli64_m65(i64 %a) nounwind {
; RV32I-LABEL: muli64_m65:
; RV32I: # %bb.0:
; RV32I-NEXT: slli a2, a0, 6
; RV32I-NEXT: add a3, a2, a0
; RV32I-NEXT: sltu a2, a3, a2
; RV32I-NEXT: srli a0, a0, 26
; RV32I-NEXT: slli a4, a1, 6
; RV32I-NEXT: or a0, a4, a0
; RV32I-NEXT: add a0, a0, a1
; RV32I-NEXT: add a0, a0, a2
; RV32I-NEXT: snez a1, a3
; RV32I-NEXT: add a0, a0, a1
; RV32I-NEXT: neg a1, a0
; RV32I-NEXT: neg a0, a3
; RV32I-NEXT: ret
;
; RV32IM-LABEL: muli64_m65:
; RV32IM: # %bb.0:
; RV32IM-NEXT: addi a2, zero, -65
; RV32IM-NEXT: mul a1, a1, a2
; RV32IM-NEXT: mulhu a3, a0, a2
; RV32IM-NEXT: sub a3, a3, a0
; RV32IM-NEXT: add a1, a3, a1
; RV32IM-NEXT: mul a0, a0, a2
; RV32IM-NEXT: ret
;
; RV64I-LABEL: muli64_m65:
; RV64I: # %bb.0:
; RV64I-NEXT: slli a1, a0, 6
; RV64I-NEXT: add a0, a1, a0
; RV64I-NEXT: neg a0, a0
; RV64I-NEXT: ret
;
; RV64IM-LABEL: muli64_m65:
; RV64IM: # %bb.0:
; RV64IM-NEXT: slli a1, a0, 6
; RV64IM-NEXT: add a0, a1, a0
; RV64IM-NEXT: neg a0, a0
; RV64IM-NEXT: ret
%1 = mul i64 %a, -65
ret i64 %1
}