[(set VR128:$dst, (F32Int sse_load_f32:$src))]>;
}
-/// sse1_fp_unop_p - SSE1 unops in scalar form.
-multiclass sse1_fp_unop_p<bits<8> opc, string OpcodeStr,
- SDNode OpNode, Intrinsic V4F32Int> {
- def PSr : PSI<opc, MRMSrcReg, (outs VR128:$dst), (ins VR128:$src),
- !strconcat(OpcodeStr, "ps\t{$src, $dst|$dst, $src}"),
- [(set VR128:$dst, (v4f32 (OpNode VR128:$src)))]>;
- def PSm : PSI<opc, MRMSrcMem, (outs VR128:$dst), (ins f128mem:$src),
- !strconcat(OpcodeStr, "ps\t{$src, $dst|$dst, $src}"),
- [(set VR128:$dst, (OpNode (memopv4f32 addr:$src)))]>;
- def PSr_Int : PSI<opc, MRMSrcReg, (outs VR128:$dst), (ins VR128:$src),
- !strconcat(OpcodeStr, "ps\t{$src, $dst|$dst, $src}"),
- [(set VR128:$dst, (V4F32Int VR128:$src))]>;
- def PSm_Int : PSI<opc, MRMSrcMem, (outs VR128:$dst), (ins f128mem:$src),
- !strconcat(OpcodeStr, "ps\t{$src, $dst|$dst, $src}"),
- [(set VR128:$dst, (V4F32Int (memopv4f32 addr:$src)))]>;
-}
-
/// sse1_fp_unop_s_avx - AVX SSE1 unops in scalar form.
multiclass sse1_fp_unop_s_avx<bits<8> opc, string OpcodeStr,
SDNode OpNode, Intrinsic F32Int> {
"ss\t{$src2, $src1, $dst|$dst, $src1, $src2}"), []>;
}
+/// sse1_fp_unop_p - SSE1 unops in packed form.
+multiclass sse1_fp_unop_p<bits<8> opc, string OpcodeStr, SDNode OpNode> {
+ def PSr : PSI<opc, MRMSrcReg, (outs VR128:$dst), (ins VR128:$src),
+ !strconcat(OpcodeStr, "ps\t{$src, $dst|$dst, $src}"),
+ [(set VR128:$dst, (v4f32 (OpNode VR128:$src)))]>;
+ def PSm : PSI<opc, MRMSrcMem, (outs VR128:$dst), (ins f128mem:$src),
+ !strconcat(OpcodeStr, "ps\t{$src, $dst|$dst, $src}"),
+ [(set VR128:$dst, (OpNode (memopv4f32 addr:$src)))]>;
+}
+
+/// sse1_fp_unop_p_y - AVX 256-bit SSE1 unops in packed form.
+multiclass sse1_fp_unop_p_y<bits<8> opc, string OpcodeStr, SDNode OpNode> {
+ def PSYr : PSI<opc, MRMSrcReg, (outs VR256:$dst), (ins VR256:$src),
+ !strconcat(OpcodeStr, "ps\t{$src, $dst|$dst, $src}"),
+ [(set VR256:$dst, (v8f32 (OpNode VR256:$src)))]>;
+ def PSYm : PSI<opc, MRMSrcMem, (outs VR256:$dst), (ins f256mem:$src),
+ !strconcat(OpcodeStr, "ps\t{$src, $dst|$dst, $src}"),
+ [(set VR256:$dst, (OpNode (memopv8f32 addr:$src)))]>;
+}
+
+/// sse1_fp_unop_p_int - SSE1 intrinsics unops in packed forms.
+multiclass sse1_fp_unop_p_int<bits<8> opc, string OpcodeStr,
+ Intrinsic V4F32Int> {
+ def PSr_Int : PSI<opc, MRMSrcReg, (outs VR128:$dst), (ins VR128:$src),
+ !strconcat(OpcodeStr, "ps\t{$src, $dst|$dst, $src}"),
+ [(set VR128:$dst, (V4F32Int VR128:$src))]>;
+ def PSm_Int : PSI<opc, MRMSrcMem, (outs VR128:$dst), (ins f128mem:$src),
+ !strconcat(OpcodeStr, "ps\t{$src, $dst|$dst, $src}"),
+ [(set VR128:$dst, (V4F32Int (memopv4f32 addr:$src)))]>;
+}
+
+
/// sse2_fp_unop_s - SSE2 unops in scalar form.
multiclass sse2_fp_unop_s<bits<8> opc, string OpcodeStr,
SDNode OpNode, Intrinsic F64Int> {
[(set VR128:$dst, (F64Int sse_load_f64:$src))]>;
}
-/// sse2_fp_unop_p - SSE2 unops in vector forms.
-multiclass sse2_fp_unop_p<bits<8> opc, string OpcodeStr,
- SDNode OpNode, Intrinsic V2F64Int> {
- def PDr : PDI<opc, MRMSrcReg, (outs VR128:$dst), (ins VR128:$src),
- !strconcat(OpcodeStr, "pd\t{$src, $dst|$dst, $src}"),
- [(set VR128:$dst, (v2f64 (OpNode VR128:$src)))]>;
- def PDm : PDI<opc, MRMSrcMem, (outs VR128:$dst), (ins f128mem:$src),
- !strconcat(OpcodeStr, "pd\t{$src, $dst|$dst, $src}"),
- [(set VR128:$dst, (OpNode (memopv2f64 addr:$src)))]>;
- def PDr_Int : PDI<opc, MRMSrcReg, (outs VR128:$dst), (ins VR128:$src),
- !strconcat(OpcodeStr, "pd\t{$src, $dst|$dst, $src}"),
- [(set VR128:$dst, (V2F64Int VR128:$src))]>;
- def PDm_Int : PDI<opc, MRMSrcMem, (outs VR128:$dst), (ins f128mem:$src),
- !strconcat(OpcodeStr, "pd\t{$src, $dst|$dst, $src}"),
- [(set VR128:$dst, (V2F64Int (memopv2f64 addr:$src)))]>;
-}
-
/// sse2_fp_unop_s_avx - AVX SSE2 unops in scalar form.
multiclass sse2_fp_unop_s_avx<bits<8> opc, string OpcodeStr,
SDNode OpNode, Intrinsic F64Int> {
[]>;
}
-let isAsmParserOnly = 1 in {
- // Square root.
- let Predicates = [HasAVX] in {
- defm VSQRT : sse2_fp_unop_s_avx<0x51, "sqrt", fsqrt, int_x86_sse2_sqrt_sd>,
- VEX_4V;
+/// sse2_fp_unop_p - SSE2 unops in vector forms.
+multiclass sse2_fp_unop_p<bits<8> opc, string OpcodeStr,
+ SDNode OpNode> {
+ def PDr : PDI<opc, MRMSrcReg, (outs VR128:$dst), (ins VR128:$src),
+ !strconcat(OpcodeStr, "pd\t{$src, $dst|$dst, $src}"),
+ [(set VR128:$dst, (v2f64 (OpNode VR128:$src)))]>;
+ def PDm : PDI<opc, MRMSrcMem, (outs VR128:$dst), (ins f128mem:$src),
+ !strconcat(OpcodeStr, "pd\t{$src, $dst|$dst, $src}"),
+ [(set VR128:$dst, (OpNode (memopv2f64 addr:$src)))]>;
+}
- defm VSQRT : sse2_fp_unop_p<0x51, "vsqrt", fsqrt, int_x86_sse2_sqrt_pd>, VEX;
- }
+/// sse2_fp_unop_p_y - AVX SSE2 256-bit unops in vector forms.
+multiclass sse2_fp_unop_p_y<bits<8> opc, string OpcodeStr, SDNode OpNode> {
+ def PDYr : PDI<opc, MRMSrcReg, (outs VR256:$dst), (ins VR256:$src),
+ !strconcat(OpcodeStr, "pd\t{$src, $dst|$dst, $src}"),
+ [(set VR256:$dst, (v4f64 (OpNode VR256:$src)))]>;
+ def PDYm : PDI<opc, MRMSrcMem, (outs VR256:$dst), (ins f256mem:$src),
+ !strconcat(OpcodeStr, "pd\t{$src, $dst|$dst, $src}"),
+ [(set VR256:$dst, (OpNode (memopv4f64 addr:$src)))]>;
+}
+
+/// sse2_fp_unop_p_int - SSE2 intrinsic unops in vector forms.
+multiclass sse2_fp_unop_p_int<bits<8> opc, string OpcodeStr,
+ Intrinsic V2F64Int> {
+ def PDr_Int : PDI<opc, MRMSrcReg, (outs VR128:$dst), (ins VR128:$src),
+ !strconcat(OpcodeStr, "pd\t{$src, $dst|$dst, $src}"),
+ [(set VR128:$dst, (V2F64Int VR128:$src))]>;
+ def PDm_Int : PDI<opc, MRMSrcMem, (outs VR128:$dst), (ins f128mem:$src),
+ !strconcat(OpcodeStr, "pd\t{$src, $dst|$dst, $src}"),
+ [(set VR128:$dst, (V2F64Int (memopv2f64 addr:$src)))]>;
+}
- let Predicates = [HasAVX] in {
+let isAsmParserOnly = 1, Predicates = [HasAVX] in {
+ // Square root.
defm VSQRT : sse1_fp_unop_s_avx<0x51, "sqrt", fsqrt, int_x86_sse_sqrt_ss>,
- VEX_4V;
- defm VSQRT : sse1_fp_unop_p<0x51, "vsqrt", fsqrt, int_x86_sse_sqrt_ps>, VEX;
+ sse2_fp_unop_s_avx<0x51, "sqrt", fsqrt, int_x86_sse2_sqrt_sd>,
+ VEX_4V;
+
+ defm VSQRT : sse1_fp_unop_p<0x51, "vsqrt", fsqrt>,
+ sse2_fp_unop_p<0x51, "vsqrt", fsqrt>,
+ sse1_fp_unop_p_y<0x51, "vsqrt", fsqrt>,
+ sse2_fp_unop_p_y<0x51, "vsqrt", fsqrt>,
+ VEX;
+
// Reciprocal approximations. Note that these typically require refinement
// in order to obtain suitable precision.
defm VRSQRT : sse1_fp_unop_s_avx<0x52, "rsqrt", X86frsqrt,
int_x86_sse_rsqrt_ss>, VEX_4V;
- defm VRSQRT : sse1_fp_unop_p<0x52, "vrsqrt", X86frsqrt, int_x86_sse_rsqrt_ps>,
- VEX;
+ defm VRSQRT : sse1_fp_unop_p<0x52, "vrsqrt", X86frsqrt>,
+ sse1_fp_unop_p_y<0x52, "vrsqrt", X86frsqrt>, VEX;
+
defm VRCP : sse1_fp_unop_s_avx<0x53, "rcp", X86frcp, int_x86_sse_rcp_ss>,
VEX_4V;
- defm VRCP : sse1_fp_unop_p<0x53, "vrcp", X86frcp, int_x86_sse_rcp_ps>,
- VEX;
- }
+ defm VRCP : sse1_fp_unop_p<0x53, "vrcp", X86frcp>,
+ sse1_fp_unop_p_y<0x53, "vrcp", X86frcp>, VEX;
}
// Square root.
defm SQRT : sse1_fp_unop_s<0x51, "sqrt", fsqrt, int_x86_sse_sqrt_ss>,
- sse1_fp_unop_p<0x51, "sqrt", fsqrt, int_x86_sse_sqrt_ps>,
+ sse1_fp_unop_p<0x51, "sqrt", fsqrt>,
+ sse1_fp_unop_p_int<0x51, "sqrt", int_x86_sse_sqrt_ps>,
sse2_fp_unop_s<0x51, "sqrt", fsqrt, int_x86_sse2_sqrt_sd>,
- sse2_fp_unop_p<0x51, "sqrt", fsqrt, int_x86_sse2_sqrt_pd>;
+ sse2_fp_unop_p<0x51, "sqrt", fsqrt>,
+ sse2_fp_unop_p_int<0x51, "sqrt", int_x86_sse2_sqrt_pd>;
// Reciprocal approximations. Note that these typically require refinement
// in order to obtain suitable precision.
defm RSQRT : sse1_fp_unop_s<0x52, "rsqrt", X86frsqrt, int_x86_sse_rsqrt_ss>,
- sse1_fp_unop_p<0x52, "rsqrt", X86frsqrt, int_x86_sse_rsqrt_ps>;
+ sse1_fp_unop_p<0x52, "rsqrt", X86frsqrt>,
+ sse1_fp_unop_p_int<0x52, "rsqrt", int_x86_sse_rsqrt_ps>;
defm RCP : sse1_fp_unop_s<0x53, "rcp", X86frcp, int_x86_sse_rcp_ss>,
- sse1_fp_unop_p<0x53, "rcp", X86frcp, int_x86_sse_rcp_ps>;
+ sse1_fp_unop_p<0x53, "rcp", X86frcp>,
+ sse1_fp_unop_p_int<0x53, "rcp", int_x86_sse_rcp_ps>;
// There is no f64 version of the reciprocal approximation instructions.