diff options
Diffstat (limited to 'gcc/config/i386/i386-expand.cc')
| -rw-r--r-- | gcc/config/i386/i386-expand.cc | 50 |
1 files changed, 38 insertions, 12 deletions
diff --git a/gcc/config/i386/i386-expand.cc b/gcc/config/i386/i386-expand.cc index cdfd94d..a314800 100644 --- a/gcc/config/i386/i386-expand.cc +++ b/gcc/config/i386/i386-expand.cc @@ -4138,6 +4138,10 @@ ix86_expand_sse_fp_minmax (rtx dest, enum rtx_code code, rtx cmp_op0, return false; mode = GET_MODE (dest); + if (immediate_operand (if_false, mode)) + if_false = force_reg (mode, if_false); + if (immediate_operand (if_true, mode)) + if_true = force_reg (mode, if_true); /* We want to check HONOR_NANS and HONOR_SIGNED_ZEROS here, but MODE may be a vector mode and thus not appropriate. */ @@ -4687,6 +4691,8 @@ ix86_expand_fp_movcc (rtx operands[]) compare_op = ix86_expand_compare (NE, tmp, const0_rtx); } + operands[2] = force_reg (mode, operands[2]); + operands[3] = force_reg (mode, operands[3]); emit_insn (gen_rtx_SET (operands[0], gen_rtx_IF_THEN_ELSE (mode, compare_op, operands[2], operands[3]))); @@ -19256,8 +19262,6 @@ ix86_emit_swdivsf (rtx res, rtx a, rtx b, machine_mode mode) e1 = gen_reg_rtx (mode); x1 = gen_reg_rtx (mode); - /* a / b = a * ((rcp(b) + rcp(b)) - (b * rcp(b) * rcp (b))) */ - b = force_reg (mode, b); /* x0 = rcp(b) estimate */ @@ -19270,20 +19274,42 @@ ix86_emit_swdivsf (rtx res, rtx a, rtx b, machine_mode mode) emit_insn (gen_rtx_SET (x0, gen_rtx_UNSPEC (mode, gen_rtvec (1, b), UNSPEC_RCP))); - /* e0 = x0 * b */ - emit_insn (gen_rtx_SET (e0, gen_rtx_MULT (mode, x0, b))); + unsigned vector_size = GET_MODE_SIZE (mode); + + /* (a - (rcp(b) * a * b)) * rcp(b) + rcp(b) * a + N-R step with 2 fma implementation. */ + if (TARGET_FMA + || (TARGET_AVX512F && vector_size == 64) + || (TARGET_AVX512VL && (vector_size == 32 || vector_size == 16))) + { + /* e0 = x0 * a */ + emit_insn (gen_rtx_SET (e0, gen_rtx_MULT (mode, x0, a))); + /* e1 = e0 * b - a */ + emit_insn (gen_rtx_SET (e1, gen_rtx_FMA (mode, e0, b, + gen_rtx_NEG (mode, a)))); + /* res = - e1 * x0 + e0 */ + emit_insn (gen_rtx_SET (res, gen_rtx_FMA (mode, + gen_rtx_NEG (mode, e1), + x0, e0))); + } + else + /* a / b = a * ((rcp(b) + rcp(b)) - (b * rcp(b) * rcp (b))) */ + { + /* e0 = x0 * b */ + emit_insn (gen_rtx_SET (e0, gen_rtx_MULT (mode, x0, b))); - /* e0 = x0 * e0 */ - emit_insn (gen_rtx_SET (e0, gen_rtx_MULT (mode, x0, e0))); + /* e1 = x0 + x0 */ + emit_insn (gen_rtx_SET (e1, gen_rtx_PLUS (mode, x0, x0))); - /* e1 = x0 + x0 */ - emit_insn (gen_rtx_SET (e1, gen_rtx_PLUS (mode, x0, x0))); + /* e0 = x0 * e0 */ + emit_insn (gen_rtx_SET (e0, gen_rtx_MULT (mode, x0, e0))); - /* x1 = e1 - e0 */ - emit_insn (gen_rtx_SET (x1, gen_rtx_MINUS (mode, e1, e0))); + /* x1 = e1 - e0 */ + emit_insn (gen_rtx_SET (x1, gen_rtx_MINUS (mode, e1, e0))); - /* res = a * x1 */ - emit_insn (gen_rtx_SET (res, gen_rtx_MULT (mode, a, x1))); + /* res = a * x1 */ + emit_insn (gen_rtx_SET (res, gen_rtx_MULT (mode, a, x1))); + } } /* Output code to perform a Newton-Rhapson approximation of a |